From ae454f41d472617f3af0a184482c576c722b7e7e Mon Sep 17 00:00:00 2001 From: amyeroberts <22614925+amyeroberts@users.noreply.github.com> Date: Thu, 29 Jun 2023 10:17:36 +0100 Subject: [PATCH] Update old existing feature extractor references (#24552) * Update old existing feature extractor references * Typo * Apply suggestions from code review * Apply suggestions from code review * Apply suggestions from code review * Address comments from review - update 'feature extractor' Co-authored by: Yih-Dar <2521628+ydshieh@users.noreply.github.com> --- docs/source/de/preprocessing.md | 10 +-- docs/source/en/create_a_model.md | 4 +- docs/source/en/model_doc/clip.md | 4 +- docs/source/en/model_doc/donut.md | 4 +- docs/source/en/model_doc/layoutlmv2.md | 18 ++--- docs/source/en/model_doc/layoutlmv3.md | 2 +- docs/source/en/model_doc/layoutxlm.md | 2 +- docs/source/en/model_doc/owlvit.md | 2 +- docs/source/en/model_doc/vilt.md | 2 +- docs/source/en/tasks/object_detection.md | 7 +- docs/source/es/tasks/image_classification.md | 12 ++-- docs/source/ko/tasks/object_detection.md | 7 +- .../models/align/convert_align_tf_to_hf.py | 6 +- .../beit/convert_beit_unilm_to_pytorch.py | 12 ++-- .../configuration_chinese_clip.py | 2 +- .../models/clip/configuration_clip.py | 2 +- .../convert_clipseg_original_pytorch_to_hf.py | 6 +- ..._original_pytorch_checkpoint_to_pytorch.py | 14 ++-- .../convnext/convert_convnext_to_pytorch.py | 12 ++-- ..._original_pytorch_checkpoint_to_pytorch.py | 8 +-- ..._original_pytorch_checkpoint_to_pytorch.py | 8 +-- .../convert_deformable_detr_to_pytorch.py | 14 ++-- .../deit/convert_deit_timm_to_pytorch.py | 12 ++-- ..._original_pytorch_checkpoint_to_pytorch.py | 14 ++-- .../models/detr/image_processing_detr.py | 3 +- .../dit/convert_dit_unilm_to_pytorch.py | 14 ++-- .../models/donut/convert_donut_to_pytorch.py | 6 +- .../dpt/convert_dpt_hybrid_to_pytorch.py | 12 ++-- .../models/dpt/convert_dpt_to_pytorch.py | 14 ++-- ..._original_pytorch_checkpoint_to_pytorch.py | 6 +- .../modeling_efficientformer.py | 4 +- .../convert_efficientnet_to_pytorch.py | 6 +- .../models/glpn/convert_glpn_to_pytorch.py | 14 ++-- .../models/groupvit/configuration_groupvit.py | 2 +- .../imagegpt/image_processing_imagegpt.py | 2 +- .../layoutlmv3/configuration_layoutlmv3.py | 2 +- .../models/layoutxlm/processing_layoutxlm.py | 72 ++++++++++++++----- .../levit/convert_levit_timm_to_pytorch.py | 10 +-- ..._original_pytorch_checkpoint_to_pytorch.py | 14 ++-- .../mask2former/modeling_mask2former.py | 4 +- ..._original_pytorch_checkpoint_to_pytorch.py | 22 +++--- .../convert_maskformer_resnet_to_pytorch.py | 14 ++-- .../convert_maskformer_swin_to_pytorch.py | 14 ++-- ...nvert_original_tf_checkpoint_to_pytorch.py | 14 ++-- ...nvert_original_tf_checkpoint_to_pytorch.py | 10 +-- .../mobilevit/convert_mlcvnets_to_pytorch.py | 14 ++-- .../convert_mlcvnets_to_pytorch.py | 8 +-- .../models/owlvit/configuration_owlvit.py | 2 +- .../convert_owlvit_original_flax_to_hf.py | 10 +-- .../convert_perceiver_haiku_to_pytorch.py | 6 +- .../convert_poolformer_original_to_pytorch.py | 22 +++--- .../convert_regnet_seer_10b_to_pytorch.py | 10 +-- .../regnet/convert_regnet_to_pytorch.py | 10 +-- .../resnet/convert_resnet_to_pytorch.py | 10 +-- .../convert_segformer_original_to_pytorch.py | 14 ++-- .../swin/convert_swin_simmim_to_pytorch.py | 14 ++-- .../swin/convert_swin_timm_to_pytorch.py | 10 +-- .../swinv2/convert_swinv2_timm_to_pytorch.py | 10 +-- ..._original_pytorch_checkpoint_to_pytorch.py | 12 ++-- .../convert_timesformer_to_pytorch.py | 10 +-- .../timesformer/modeling_timesformer.py | 4 +- .../trocr/convert_trocr_unilm_to_pytorch.py | 6 +- .../models/van/convert_van_to_pytorch.py | 10 +-- .../videomae/convert_videomae_to_pytorch.py | 10 +-- .../vilt/convert_vilt_original_to_pytorch.py | 6 +- .../models/vit/convert_dino_to_pytorch.py | 12 ++-- .../models/vit/convert_vit_timm_to_pytorch.py | 14 ++-- .../vit_mae/convert_vit_mae_to_pytorch.py | 12 ++-- .../models/vit_msn/convert_msn_to_pytorch.py | 12 ++-- .../convert_x_clip_original_pytorch_to_hf.py | 6 +- .../models/yolos/convert_yolos_to_pytorch.py | 14 ++-- src/transformers/onnx/__main__.py | 6 +- tests/models/beit/test_modeling_beit.py | 32 ++++----- tests/models/beit/test_modeling_flax_beit.py | 20 +++--- tests/models/bit/test_modeling_bit.py | 6 +- .../test_image_processing_bridgetower.py | 8 +-- .../test_modeling_conditional_detr.py | 16 ++--- .../models/convnext/test_modeling_convnext.py | 10 +-- .../convnext/test_modeling_tf_convnext.py | 12 ++-- tests/models/cvt/test_modeling_cvt.py | 10 +-- tests/models/cvt/test_modeling_tf_cvt.py | 10 +-- .../data2vec/test_modeling_data2vec_vision.py | 12 ++-- .../test_modeling_tf_data2vec_vision.py | 12 ++-- .../test_modeling_deformable_detr.py | 20 +++--- tests/models/deit/test_modeling_deit.py | 14 ++-- tests/models/deit/test_modeling_tf_deit.py | 10 +-- tests/models/detr/test_modeling_detr.py | 30 ++++---- tests/models/dinat/test_modeling_dinat.py | 6 +- tests/models/dit/test_modeling_dit.py | 6 +- tests/models/dpt/test_modeling_dpt.py | 18 ++--- tests/models/dpt/test_modeling_dpt_hybrid.py | 6 +- .../test_modeling_efficientformer.py | 10 +-- tests/models/glpn/test_modeling_glpn.py | 6 +- .../models/imagegpt/test_modeling_imagegpt.py | 10 +-- .../layoutlmv3/test_modeling_layoutlmv3.py | 10 +-- .../layoutlmv3/test_modeling_tf_layoutlmv3.py | 10 +-- .../layoutxlm/test_processor_layoutxlm.py | 60 ++++++++-------- tests/models/levit/test_modeling_levit.py | 10 +-- .../test_image_processing_mask2former.py | 6 +- .../mask2former/test_modeling_mask2former.py | 14 ++-- .../test_image_processing_maskformer.py | 6 +- .../maskformer/test_modeling_maskformer.py | 22 +++--- .../models/mgp_str/test_processor_mgp_str.py | 2 +- .../test_modeling_mobilenet_v1.py | 12 ++-- .../test_modeling_mobilenet_v2.py | 16 ++--- .../mobilevit/test_modeling_mobilevit.py | 22 +++--- .../mobilevit/test_modeling_tf_mobilevit.py | 10 +-- tests/models/nat/test_modeling_nat.py | 6 +- .../perceiver/test_modeling_perceiver.py | 14 ++-- .../poolformer/test_modeling_poolformer.py | 6 +- .../regnet/test_modeling_flax_regnet.py | 10 +-- tests/models/regnet/test_modeling_regnet.py | 10 +-- .../models/regnet/test_modeling_tf_regnet.py | 10 +-- .../resnet/test_modeling_flax_resnet.py | 10 +-- tests/models/resnet/test_modeling_resnet.py | 10 +-- .../models/resnet/test_modeling_tf_resnet.py | 10 +-- .../segformer/test_modeling_segformer.py | 18 ++--- .../segformer/test_modeling_tf_segformer.py | 10 +-- .../swiftformer/test_modeling_swiftformer.py | 6 +- tests/models/swin/test_modeling_swin.py | 10 +-- tests/models/swin/test_modeling_tf_swin.py | 10 +-- tests/models/swinv2/test_modeling_swinv2.py | 10 +-- .../test_modeling_table_transformer.py | 6 +- .../timesformer/test_modeling_timesformer.py | 10 +-- tests/models/tvlt/test_modeling_tvlt.py | 6 +- tests/models/van/test_modeling_van.py | 10 +-- .../models/videomae/test_modeling_videomae.py | 14 ++-- ...st_modeling_flax_vision_encoder_decoder.py | 6 +- ...test_modeling_tf_vision_encoder_decoder.py | 12 ++-- .../test_modeling_vision_encoder_decoder.py | 6 +- ...test_processor_vision_text_dual_encoder.py | 4 +- tests/models/vit/test_modeling_tf_vit.py | 10 +-- tests/models/vit/test_modeling_vit.py | 18 ++--- .../vit_hybrid/test_modeling_vit_hybrid.py | 10 +-- .../vit_mae/test_modeling_tf_vit_mae.py | 10 +-- tests/models/vit_mae/test_modeling_vit_mae.py | 10 +-- tests/models/vit_msn/test_modeling_vit_msn.py | 10 +-- tests/models/yolos/test_modeling_yolos.py | 12 ++-- 138 files changed, 762 insertions(+), 743 deletions(-) diff --git a/docs/source/de/preprocessing.md b/docs/source/de/preprocessing.md index eb3b3057c3..1e8f6ff406 100644 --- a/docs/source/de/preprocessing.md +++ b/docs/source/de/preprocessing.md @@ -354,12 +354,12 @@ Als Nächstes sehen Sie sich das Bild mit dem Merkmal 🤗 Datensätze [Bild] (h ### Merkmalsextraktor -Laden Sie den Merkmalsextraktor mit [`AutoFeatureExtractor.from_pretrained`]: +Laden Sie den Merkmalsextraktor mit [`AutoImageProcessor.from_pretrained`]: ```py ->>> from transformers import AutoFeatureExtractor +>>> from transformers import AutoImageProcessor ->>> feature_extractor = AutoFeatureExtractor.from_pretrained("google/vit-base-patch16-224") +>>> image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224") ``` ### Datenerweiterung @@ -371,9 +371,9 @@ Bei Bildverarbeitungsaufgaben ist es üblich, den Bildern als Teil der Vorverarb ```py >>> from torchvision.transforms import Compose, Normalize, RandomResizedCrop, ColorJitter, ToTensor ->>> normalize = Normalize(mean=feature_extractor.image_mean, std=feature_extractor.image_std) +>>> normalize = Normalize(mean=image_processor.image_mean, std=image_processor.image_std) >>> _transforms = Compose( -... [RandomResizedCrop(feature_extractor.size), ColorJitter(brightness=0.5, hue=0.5), ToTensor(), normalize] +... [RandomResizedCrop(image_processor.size["height"]), ColorJitter(brightness=0.5, hue=0.5), ToTensor(), normalize] ... ) ``` diff --git a/docs/source/en/create_a_model.md b/docs/source/en/create_a_model.md index 239edf085c..91dd99e725 100644 --- a/docs/source/en/create_a_model.md +++ b/docs/source/en/create_a_model.md @@ -263,7 +263,7 @@ To use, create an image processor associated with the model you're using. For ex ViTImageProcessor { "do_normalize": true, "do_resize": true, - "feature_extractor_type": "ViTImageProcessor", + "image_processor_type": "ViTImageProcessor", "image_mean": [ 0.5, 0.5, @@ -295,7 +295,7 @@ Modify any of the [`ViTImageProcessor`] parameters to create your custom image p ViTImageProcessor { "do_normalize": false, "do_resize": true, - "feature_extractor_type": "ViTImageProcessor", + "image_processor_type": "ViTImageProcessor", "image_mean": [ 0.3, 0.3, diff --git a/docs/source/en/model_doc/clip.md b/docs/source/en/model_doc/clip.md index 7bd40fc05b..be98edfb2a 100644 --- a/docs/source/en/model_doc/clip.md +++ b/docs/source/en/model_doc/clip.md @@ -50,10 +50,10 @@ product between the projected image and text features is then used as a similar To feed images to the Transformer encoder, each image is split into a sequence of fixed-size non-overlapping patches, which are then linearly embedded. A [CLS] token is added to serve as representation of an entire image. The authors also add absolute position embeddings, and feed the resulting sequence of vectors to a standard Transformer encoder. -The [`CLIPFeatureExtractor`] can be used to resize (or rescale) and normalize images for the model. +The [`CLIPImageProcessor`] can be used to resize (or rescale) and normalize images for the model. The [`CLIPTokenizer`] is used to encode the text. The [`CLIPProcessor`] wraps -[`CLIPFeatureExtractor`] and [`CLIPTokenizer`] into a single instance to both +[`CLIPImageProcessor`] and [`CLIPTokenizer`] into a single instance to both encode the text and prepare the images. The following example shows how to get the image-text similarity scores using [`CLIPProcessor`] and [`CLIPModel`]. diff --git a/docs/source/en/model_doc/donut.md b/docs/source/en/model_doc/donut.md index 6ccfe39dbb..1e214da8bc 100644 --- a/docs/source/en/model_doc/donut.md +++ b/docs/source/en/model_doc/donut.md @@ -46,9 +46,9 @@ Tips: Donut's [`VisionEncoderDecoder`] model accepts images as input and makes use of [`~generation.GenerationMixin.generate`] to autoregressively generate text given the input image. -The [`DonutFeatureExtractor`] class is responsible for preprocessing the input image and +The [`DonutImageProcessor`] class is responsible for preprocessing the input image and [`XLMRobertaTokenizer`/`XLMRobertaTokenizerFast`] decodes the generated target tokens to the target string. The -[`DonutProcessor`] wraps [`DonutFeatureExtractor`] and [`XLMRobertaTokenizer`/`XLMRobertaTokenizerFast`] +[`DonutProcessor`] wraps [`DonutImageProcessor`] and [`XLMRobertaTokenizer`/`XLMRobertaTokenizerFast`] into a single instance to both extract the input features and decode the predicted token ids. - Step-by-step Document Image Classification diff --git a/docs/source/en/model_doc/layoutlmv2.md b/docs/source/en/model_doc/layoutlmv2.md index 37d1c1671e..f2a1c65a42 100644 --- a/docs/source/en/model_doc/layoutlmv2.md +++ b/docs/source/en/model_doc/layoutlmv2.md @@ -150,23 +150,23 @@ A list of official Hugging Face and community (indicated by 🌎) resources to h ## Usage: LayoutLMv2Processor The easiest way to prepare data for the model is to use [`LayoutLMv2Processor`], which internally -combines a feature extractor ([`LayoutLMv2FeatureExtractor`]) and a tokenizer -([`LayoutLMv2Tokenizer`] or [`LayoutLMv2TokenizerFast`]). The feature extractor +combines a image processor ([`LayoutLMv2ImageProcessor`]) and a tokenizer +([`LayoutLMv2Tokenizer`] or [`LayoutLMv2TokenizerFast`]). The image processor handles the image modality, while the tokenizer handles the text modality. A processor combines both, which is ideal for a multi-modal model like LayoutLMv2. Note that you can still use both separately, if you only want to handle one modality. ```python -from transformers import LayoutLMv2FeatureExtractor, LayoutLMv2TokenizerFast, LayoutLMv2Processor +from transformers import LayoutLMv2ImageProcessor, LayoutLMv2TokenizerFast, LayoutLMv2Processor -feature_extractor = LayoutLMv2FeatureExtractor() # apply_ocr is set to True by default +image_processor = LayoutLMv2ImageProcessor() # apply_ocr is set to True by default tokenizer = LayoutLMv2TokenizerFast.from_pretrained("microsoft/layoutlmv2-base-uncased") -processor = LayoutLMv2Processor(feature_extractor, tokenizer) +processor = LayoutLMv2Processor(image_processor, tokenizer) ``` In short, one can provide a document image (and possibly additional data) to [`LayoutLMv2Processor`], and it will create the inputs expected by the model. Internally, the processor first uses -[`LayoutLMv2FeatureExtractor`] to apply OCR on the image to get a list of words and normalized +[`LayoutLMv2ImageProcessor`] to apply OCR on the image to get a list of words and normalized bounding boxes, as well to resize the image to a given size in order to get the `image` input. The words and normalized bounding boxes are then provided to [`LayoutLMv2Tokenizer`] or [`LayoutLMv2TokenizerFast`], which converts them to token-level `input_ids`, @@ -176,7 +176,7 @@ which are turned into token-level `labels`. [`LayoutLMv2Processor`] uses [PyTesseract](https://pypi.org/project/pytesseract/), a Python wrapper around Google's Tesseract OCR engine, under the hood. Note that you can still use your own OCR engine of choice, and provide the words and normalized boxes yourself. This requires initializing -[`LayoutLMv2FeatureExtractor`] with `apply_ocr` set to `False`. +[`LayoutLMv2ImageProcessor`] with `apply_ocr` set to `False`. In total, there are 5 use cases that are supported by the processor. Below, we list them all. Note that each of these use cases work for both batched and non-batched inputs (we illustrate them for non-batched inputs). @@ -184,7 +184,7 @@ use cases work for both batched and non-batched inputs (we illustrate them for n **Use case 1: document image classification (training, inference) + token classification (inference), apply_ocr = True** -This is the simplest case, in which the processor (actually the feature extractor) will perform OCR on the image to get +This is the simplest case, in which the processor (actually the image processor) will perform OCR on the image to get the words and normalized bounding boxes. ```python @@ -205,7 +205,7 @@ print(encoding.keys()) **Use case 2: document image classification (training, inference) + token classification (inference), apply_ocr=False** -In case one wants to do OCR themselves, one can initialize the feature extractor with `apply_ocr` set to +In case one wants to do OCR themselves, one can initialize the image processor with `apply_ocr` set to `False`. In that case, one should provide the words and corresponding (normalized) bounding boxes themselves to the processor. diff --git a/docs/source/en/model_doc/layoutlmv3.md b/docs/source/en/model_doc/layoutlmv3.md index 39408ab88a..22e2c3ff71 100644 --- a/docs/source/en/model_doc/layoutlmv3.md +++ b/docs/source/en/model_doc/layoutlmv3.md @@ -31,7 +31,7 @@ Tips: - In terms of data processing, LayoutLMv3 is identical to its predecessor [LayoutLMv2](layoutlmv2), except that: - images need to be resized and normalized with channels in regular RGB format. LayoutLMv2 on the other hand normalizes the images internally and expects the channels in BGR format. - text is tokenized using byte-pair encoding (BPE), as opposed to WordPiece. - Due to these differences in data preprocessing, one can use [`LayoutLMv3Processor`] which internally combines a [`LayoutLMv3FeatureExtractor`] (for the image modality) and a [`LayoutLMv3Tokenizer`]/[`LayoutLMv3TokenizerFast`] (for the text modality) to prepare all data for the model. + Due to these differences in data preprocessing, one can use [`LayoutLMv3Processor`] which internally combines a [`LayoutLMv3ImageProcessor`] (for the image modality) and a [`LayoutLMv3Tokenizer`]/[`LayoutLMv3TokenizerFast`] (for the text modality) to prepare all data for the model. - Regarding usage of [`LayoutLMv3Processor`], we refer to the [usage guide](layoutlmv2#usage-layoutlmv2processor) of its predecessor. - Demo notebooks for LayoutLMv3 can be found [here](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/LayoutLMv3). - Demo scripts can be found [here](https://github.com/huggingface/transformers/tree/main/examples/research_projects/layoutlmv3). diff --git a/docs/source/en/model_doc/layoutxlm.md b/docs/source/en/model_doc/layoutxlm.md index 20f9ffd603..8858560bbb 100644 --- a/docs/source/en/model_doc/layoutxlm.md +++ b/docs/source/en/model_doc/layoutxlm.md @@ -52,7 +52,7 @@ tokenizer = LayoutXLMTokenizer.from_pretrained("microsoft/layoutxlm-base") ``` Similar to LayoutLMv2, you can use [`LayoutXLMProcessor`] (which internally applies -[`LayoutLMv2FeatureExtractor`] and +[`LayoutLMv2ImageProcessor`] and [`LayoutXLMTokenizer`]/[`LayoutXLMTokenizerFast`] in sequence) to prepare all data for the model. diff --git a/docs/source/en/model_doc/owlvit.md b/docs/source/en/model_doc/owlvit.md index 59a4aa0bc3..737e42e253 100644 --- a/docs/source/en/model_doc/owlvit.md +++ b/docs/source/en/model_doc/owlvit.md @@ -28,7 +28,7 @@ The abstract from the paper is the following: OWL-ViT is a zero-shot text-conditioned object detection model. OWL-ViT uses [CLIP](clip) as its multi-modal backbone, with a ViT-like Transformer to get visual features and a causal language model to get the text features. To use CLIP for detection, OWL-ViT removes the final token pooling layer of the vision model and attaches a lightweight classification and box head to each transformer output token. Open-vocabulary classification is enabled by replacing the fixed classification layer weights with the class-name embeddings obtained from the text model. The authors first train CLIP from scratch and fine-tune it end-to-end with the classification and box heads on standard detection datasets using a bipartite matching loss. One or multiple text queries per image can be used to perform zero-shot text-conditioned object detection. -[`OwlViTFeatureExtractor`] can be used to resize (or rescale) and normalize images for the model and [`CLIPTokenizer`] is used to encode the text. [`OwlViTProcessor`] wraps [`OwlViTFeatureExtractor`] and [`CLIPTokenizer`] into a single instance to both encode the text and prepare the images. The following example shows how to perform object detection using [`OwlViTProcessor`] and [`OwlViTForObjectDetection`]. +[`OwlViTImageProcessor`] can be used to resize (or rescale) and normalize images for the model and [`CLIPTokenizer`] is used to encode the text. [`OwlViTProcessor`] wraps [`OwlViTImageProcessor`] and [`CLIPTokenizer`] into a single instance to both encode the text and prepare the images. The following example shows how to perform object detection using [`OwlViTProcessor`] and [`OwlViTForObjectDetection`]. ```python diff --git a/docs/source/en/model_doc/vilt.md b/docs/source/en/model_doc/vilt.md index 4170e374d8..2e2f4a140d 100644 --- a/docs/source/en/model_doc/vilt.md +++ b/docs/source/en/model_doc/vilt.md @@ -39,7 +39,7 @@ Tips: - The quickest way to get started with ViLT is by checking the [example notebooks](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/ViLT) (which showcase both inference and fine-tuning on custom data). - ViLT is a model that takes both `pixel_values` and `input_ids` as input. One can use [`ViltProcessor`] to prepare data for the model. - This processor wraps a feature extractor (for the image modality) and a tokenizer (for the language modality) into one. + This processor wraps a image processor (for the image modality) and a tokenizer (for the language modality) into one. - ViLT is trained with images of various sizes: the authors resize the shorter edge of input images to 384 and limit the longer edge to under 640 while preserving the aspect ratio. To make batching of images possible, the authors use a `pixel_mask` that indicates which pixel values are real and which are padding. [`ViltProcessor`] automatically creates this for you. diff --git a/docs/source/en/tasks/object_detection.md b/docs/source/en/tasks/object_detection.md index a38c33c927..56d6a1d8c4 100644 --- a/docs/source/en/tasks/object_detection.md +++ b/docs/source/en/tasks/object_detection.md @@ -462,9 +462,9 @@ Next, prepare an instance of a `CocoDetection` class that can be used with `coco >>> class CocoDetection(torchvision.datasets.CocoDetection): -... def __init__(self, img_folder, feature_extractor, ann_file): +... def __init__(self, img_folder, image_processor, ann_file): ... super().__init__(img_folder, ann_file) -... self.feature_extractor = feature_extractor +... self.image_processor = image_processor ... def __getitem__(self, idx): ... # read in PIL image and target in COCO format @@ -474,7 +474,7 @@ Next, prepare an instance of a `CocoDetection` class that can be used with `coco ... # resizing + normalization of both image and target) ... image_id = self.ids[idx] ... target = {"image_id": image_id, "annotations": target} -... encoding = self.feature_extractor(images=img, annotations=target, return_tensors="pt") +... encoding = self.image_processor(images=img, annotations=target, return_tensors="pt") ... pixel_values = encoding["pixel_values"].squeeze() # remove batch dimension ... target = encoding["labels"][0] # remove batch dimension @@ -591,4 +591,3 @@ Let's plot the result:
Object detection result on a new image
- diff --git a/docs/source/es/tasks/image_classification.md b/docs/source/es/tasks/image_classification.md index ef67131d73..3a959aa934 100644 --- a/docs/source/es/tasks/image_classification.md +++ b/docs/source/es/tasks/image_classification.md @@ -73,12 +73,12 @@ Cada clase de alimento - o label - corresponde a un número; `79` indica una cos ## Preprocesa -Carga el feature extractor de ViT para procesar la imagen en un tensor: +Carga el image processor de ViT para procesar la imagen en un tensor: ```py ->>> from transformers import AutoFeatureExtractor +>>> from transformers import AutoImageProcessor ->>> feature_extractor = AutoFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k") +>>> image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k") ``` Aplica varias transformaciones de imagen al dataset para hacer el modelo más robusto contra el overfitting. En este caso se utilizará el módulo [`transforms`](https://pytorch.org/vision/stable/transforms.html) de torchvision. Recorta una parte aleatoria de la imagen, cambia su tamaño y normalízala con la media y la desviación estándar de la imagen: @@ -86,8 +86,8 @@ Aplica varias transformaciones de imagen al dataset para hacer el modelo más ro ```py >>> from torchvision.transforms import RandomResizedCrop, Compose, Normalize, ToTensor ->>> normalize = Normalize(mean=feature_extractor.image_mean, std=feature_extractor.image_std) ->>> _transforms = Compose([RandomResizedCrop(feature_extractor.size), ToTensor(), normalize]) +>>> normalize = Normalize(mean=image_processor.image_mean, std=image_processor.image_std) +>>> _transforms = Compose([RandomResizedCrop(image_processor.size["height"]), ToTensor(), normalize]) ``` Crea una función de preprocesamiento que aplique las transformaciones y devuelva los `pixel_values` - los inputs al modelo - de la imagen: @@ -160,7 +160,7 @@ Al llegar a este punto, solo quedan tres pasos: ... data_collator=data_collator, ... train_dataset=food["train"], ... eval_dataset=food["test"], -... tokenizer=feature_extractor, +... tokenizer=image_processor, ... ) >>> trainer.train() diff --git a/docs/source/ko/tasks/object_detection.md b/docs/source/ko/tasks/object_detection.md index f29ca5d61b..9eb3f4f74a 100644 --- a/docs/source/ko/tasks/object_detection.md +++ b/docs/source/ko/tasks/object_detection.md @@ -454,9 +454,9 @@ COCO 데이터 세트를 빌드하는 API는 데이터를 특정 형식으로 >>> class CocoDetection(torchvision.datasets.CocoDetection): -... def __init__(self, img_folder, feature_extractor, ann_file): +... def __init__(self, img_folder, image_processor, ann_file): ... super().__init__(img_folder, ann_file) -... self.feature_extractor = feature_extractor +... self.image_processor = image_processor ... def __getitem__(self, idx): ... # read in PIL image and target in COCO format @@ -466,7 +466,7 @@ COCO 데이터 세트를 빌드하는 API는 데이터를 특정 형식으로 ... # resizing + normalization of both image and target) ... image_id = self.ids[idx] ... target = {"image_id": image_id, "annotations": target} -... encoding = self.feature_extractor(images=img, annotations=target, return_tensors="pt") +... encoding = self.image_processor(images=img, annotations=target, return_tensors="pt") ... pixel_values = encoding["pixel_values"].squeeze() # remove batch dimension ... target = encoding["labels"][0] # remove batch dimension @@ -586,4 +586,3 @@ Detected Mask with confidence 0.584 at location [2449.06, 823.19, 3256.43, 1413.
Object detection result on a new image
- diff --git a/src/transformers/models/align/convert_align_tf_to_hf.py b/src/transformers/models/align/convert_align_tf_to_hf.py index fbf53844ab..e4221d5283 100644 --- a/src/transformers/models/align/convert_align_tf_to_hf.py +++ b/src/transformers/models/align/convert_align_tf_to_hf.py @@ -354,12 +354,12 @@ def convert_align_checkpoint(checkpoint_path, pytorch_dump_folder_path, save_mod # Create folder to save model if not os.path.isdir(pytorch_dump_folder_path): os.mkdir(pytorch_dump_folder_path) - # Save converted model and feature extractor + # Save converted model and image processor hf_model.save_pretrained(pytorch_dump_folder_path) processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: - # Push model and feature extractor to hub + # Push model and image processor to hub print("Pushing converted ALIGN to the hub...") processor.push_to_hub("align-base") hf_model.push_to_hub("align-base") @@ -381,7 +381,7 @@ if __name__ == "__main__": help="Path to the output PyTorch model directory.", ) parser.add_argument("--save_model", action="store_true", help="Save model to local") - parser.add_argument("--push_to_hub", action="store_true", help="Push model and feature extractor to the hub") + parser.add_argument("--push_to_hub", action="store_true", help="Push model and image processor to the hub") args = parser.parse_args() convert_align_checkpoint(args.checkpoint_path, args.pytorch_dump_folder_path, args.save_model, args.push_to_hub) diff --git a/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py b/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py index f80d52db7d..1797f3a7fb 100644 --- a/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py +++ b/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py @@ -27,10 +27,10 @@ from PIL import Image from transformers import ( BeitConfig, - BeitFeatureExtractor, BeitForImageClassification, BeitForMaskedImageModeling, BeitForSemanticSegmentation, + BeitImageProcessor, ) from transformers.image_utils import PILImageResampling from transformers.utils import logging @@ -266,16 +266,16 @@ def convert_beit_checkpoint(checkpoint_url, pytorch_dump_folder_path): # Check outputs on an image if is_semantic: - feature_extractor = BeitFeatureExtractor(size=config.image_size, do_center_crop=False) + image_processor = BeitImageProcessor(size=config.image_size, do_center_crop=False) ds = load_dataset("hf-internal-testing/fixtures_ade20k", split="test") image = Image.open(ds[0]["file"]) else: - feature_extractor = BeitFeatureExtractor( + image_processor = BeitImageProcessor( size=config.image_size, resample=PILImageResampling.BILINEAR, do_center_crop=False ) image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt") + encoding = image_processor(images=image, return_tensors="pt") pixel_values = encoding["pixel_values"] outputs = model(pixel_values) @@ -353,8 +353,8 @@ def convert_beit_checkpoint(checkpoint_url, pytorch_dump_folder_path): Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/chinese_clip/configuration_chinese_clip.py b/src/transformers/models/chinese_clip/configuration_chinese_clip.py index a1243b1852..941b769696 100644 --- a/src/transformers/models/chinese_clip/configuration_chinese_clip.py +++ b/src/transformers/models/chinese_clip/configuration_chinese_clip.py @@ -468,7 +468,7 @@ class ChineseCLIPOnnxConfig(OnnxConfig): processor.tokenizer, batch_size=batch_size, seq_length=seq_length, framework=framework ) image_input_dict = super().generate_dummy_inputs( - processor.feature_extractor, batch_size=batch_size, framework=framework + processor.image_processor, batch_size=batch_size, framework=framework ) return {**text_input_dict, **image_input_dict} diff --git a/src/transformers/models/clip/configuration_clip.py b/src/transformers/models/clip/configuration_clip.py index 0a3f6b9fc1..e3efba36c5 100644 --- a/src/transformers/models/clip/configuration_clip.py +++ b/src/transformers/models/clip/configuration_clip.py @@ -449,7 +449,7 @@ class CLIPOnnxConfig(OnnxConfig): processor.tokenizer, batch_size=batch_size, seq_length=seq_length, framework=framework ) image_input_dict = super().generate_dummy_inputs( - processor.feature_extractor, batch_size=batch_size, framework=framework + processor.image_processor, batch_size=batch_size, framework=framework ) return {**text_input_dict, **image_input_dict} diff --git a/src/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py b/src/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py index 183bb93b9e..c614d61e5b 100644 --- a/src/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py +++ b/src/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py @@ -28,7 +28,7 @@ from transformers import ( CLIPSegTextConfig, CLIPSegVisionConfig, CLIPTokenizer, - ViTFeatureExtractor, + ViTImageProcessor, ) @@ -185,9 +185,9 @@ def convert_clipseg_checkpoint(model_name, checkpoint_path, pytorch_dump_folder_ if unexpected_keys != ["decoder.reduce.weight", "decoder.reduce.bias"]: raise ValueError(f"Unexpected keys: {unexpected_keys}") - feature_extractor = ViTFeatureExtractor(size=352) + image_processor = ViTImageProcessor(size=352) tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32") - processor = CLIPSegProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer) + processor = CLIPSegProcessor(image_processor=image_processor, tokenizer=tokenizer) image = prepare_img() text = ["a glass", "something to fill", "wood", "a jar"] diff --git a/src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py index 083b3c681e..b1a1b1c817 100644 --- a/src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py @@ -27,9 +27,9 @@ from PIL import Image from transformers import ( ConditionalDetrConfig, - ConditionalDetrFeatureExtractor, ConditionalDetrForObjectDetection, ConditionalDetrForSegmentation, + ConditionalDetrImageProcessor, ) from transformers.utils import logging @@ -244,13 +244,13 @@ def convert_conditional_detr_checkpoint(model_name, pytorch_dump_folder_path): config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} - # load feature extractor + # load image processor format = "coco_panoptic" if is_panoptic else "coco_detection" - feature_extractor = ConditionalDetrFeatureExtractor(format=format) + image_processor = ConditionalDetrImageProcessor(format=format) # prepare image img = prepare_img() - encoding = feature_extractor(images=img, return_tensors="pt") + encoding = image_processor(images=img, return_tensors="pt") pixel_values = encoding["pixel_values"] logger.info(f"Converting model {model_name}...") @@ -302,11 +302,11 @@ def convert_conditional_detr_checkpoint(model_name, pytorch_dump_folder_path): if is_panoptic: assert torch.allclose(outputs.pred_masks, original_outputs["pred_masks"], atol=1e-4) - # Save model and feature extractor - logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...") + # Save model and image processor + logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...") Path(pytorch_dump_folder_path).mkdir(exist_ok=True) model.save_pretrained(pytorch_dump_folder_path) - feature_extractor.save_pretrained(pytorch_dump_folder_path) + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/convnext/convert_convnext_to_pytorch.py b/src/transformers/models/convnext/convert_convnext_to_pytorch.py index 69c300eee4..cdcbf24d55 100644 --- a/src/transformers/models/convnext/convert_convnext_to_pytorch.py +++ b/src/transformers/models/convnext/convert_convnext_to_pytorch.py @@ -26,7 +26,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import ConvNextConfig, ConvNextFeatureExtractor, ConvNextForImageClassification +from transformers import ConvNextConfig, ConvNextForImageClassification, ConvNextImageProcessor from transformers.utils import logging @@ -144,10 +144,10 @@ def convert_convnext_checkpoint(checkpoint_url, pytorch_dump_folder_path): model.load_state_dict(state_dict) model.eval() - # Check outputs on an image, prepared by ConvNextFeatureExtractor + # Check outputs on an image, prepared by ConvNextImageProcessor size = 224 if "224" in checkpoint_url else 384 - feature_extractor = ConvNextFeatureExtractor(size=size) - pixel_values = feature_extractor(images=prepare_img(), return_tensors="pt").pixel_values + image_processor = ConvNextImageProcessor(size=size) + pixel_values = image_processor(images=prepare_img(), return_tensors="pt").pixel_values logits = model(pixel_values).logits @@ -191,8 +191,8 @@ def convert_convnext_checkpoint(checkpoint_url, pytorch_dump_folder_path): Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) print("Pushing model to the hub...") model_name = "convnext" diff --git a/src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py index 30a65beb7e..ea4edac16c 100644 --- a/src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py @@ -24,7 +24,7 @@ from collections import OrderedDict import torch from huggingface_hub import cached_download, hf_hub_url -from transformers import AutoFeatureExtractor, CvtConfig, CvtForImageClassification +from transformers import AutoImageProcessor, CvtConfig, CvtForImageClassification def embeddings(idx): @@ -307,8 +307,8 @@ def convert_cvt_checkpoint(cvt_model, image_size, cvt_file_name, pytorch_dump_fo config.embed_dim = [192, 768, 1024] model = CvtForImageClassification(config) - feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k-1k") - feature_extractor.size["shortest_edge"] = image_size + image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-base-224-22k-1k") + image_processor.size["shortest_edge"] = image_size original_weights = torch.load(cvt_file_name, map_location=torch.device("cpu")) huggingface_weights = OrderedDict() @@ -329,7 +329,7 @@ def convert_cvt_checkpoint(cvt_model, image_size, cvt_file_name, pytorch_dump_fo model.load_state_dict(huggingface_weights) model.save_pretrained(pytorch_dump_folder) - feature_extractor.save_pretrained(pytorch_dump_folder) + image_processor.save_pretrained(pytorch_dump_folder) # Download the weights from zoo: https://1drv.ms/u/s!AhIXJn_J-blW9RzF3rMW7SsLHa8h?e=blQ0Al diff --git a/src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py index 8ff8c1b910..0c6f42f4ba 100755 --- a/src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py @@ -8,7 +8,7 @@ from PIL import Image from timm.models import create_model from transformers import ( - BeitFeatureExtractor, + BeitImageProcessor, Data2VecVisionConfig, Data2VecVisionForImageClassification, Data2VecVisionModel, @@ -304,9 +304,9 @@ def main(): orig_model.eval() # 3. Forward Beit model - feature_extractor = BeitFeatureExtractor(size=config.image_size, do_center_crop=False) + image_processor = BeitImageProcessor(size=config.image_size, do_center_crop=False) image = Image.open("../../../../tests/fixtures/tests_samples/COCO/000000039769.png") - encoding = feature_extractor(images=image, return_tensors="pt") + encoding = image_processor(images=image, return_tensors="pt") pixel_values = encoding["pixel_values"] orig_args = (pixel_values,) if is_finetuned else (pixel_values, None) @@ -354,7 +354,7 @@ def main(): # 7. Save print(f"Saving to {args.hf_checkpoint_name}") hf_model.save_pretrained(args.hf_checkpoint_name) - feature_extractor.save_pretrained(args.hf_checkpoint_name) + image_processor.save_pretrained(args.hf_checkpoint_name) if __name__ == "__main__": diff --git a/src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py b/src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py index d1fd8bcbe4..928fa368ed 100644 --- a/src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py +++ b/src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py @@ -24,7 +24,7 @@ import torch from huggingface_hub import cached_download, hf_hub_url from PIL import Image -from transformers import DeformableDetrConfig, DeformableDetrFeatureExtractor, DeformableDetrForObjectDetection +from transformers import DeformableDetrConfig, DeformableDetrForObjectDetection, DeformableDetrImageProcessor from transformers.utils import logging @@ -115,12 +115,12 @@ def convert_deformable_detr_checkpoint( config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} - # load feature extractor - feature_extractor = DeformableDetrFeatureExtractor(format="coco_detection") + # load image processor + image_processor = DeformableDetrImageProcessor(format="coco_detection") # prepare image img = prepare_img() - encoding = feature_extractor(images=img, return_tensors="pt") + encoding = image_processor(images=img, return_tensors="pt") pixel_values = encoding["pixel_values"] logger.info("Converting model...") @@ -185,11 +185,11 @@ def convert_deformable_detr_checkpoint( print("Everything ok!") - # Save model and feature extractor - logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...") + # Save model and image processor + logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...") Path(pytorch_dump_folder_path).mkdir(exist_ok=True) model.save_pretrained(pytorch_dump_folder_path) - feature_extractor.save_pretrained(pytorch_dump_folder_path) + image_processor.save_pretrained(pytorch_dump_folder_path) # Push to hub if push_to_hub: diff --git a/src/transformers/models/deit/convert_deit_timm_to_pytorch.py b/src/transformers/models/deit/convert_deit_timm_to_pytorch.py index a91702106e..2b5c795ff2 100644 --- a/src/transformers/models/deit/convert_deit_timm_to_pytorch.py +++ b/src/transformers/models/deit/convert_deit_timm_to_pytorch.py @@ -25,7 +25,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import DeiTConfig, DeiTFeatureExtractor, DeiTForImageClassificationWithTeacher +from transformers import DeiTConfig, DeiTForImageClassificationWithTeacher, DeiTImageProcessor from transformers.utils import logging @@ -182,12 +182,12 @@ def convert_deit_checkpoint(deit_name, pytorch_dump_folder_path): model = DeiTForImageClassificationWithTeacher(config).eval() model.load_state_dict(state_dict) - # Check outputs on an image, prepared by DeiTFeatureExtractor + # Check outputs on an image, prepared by DeiTImageProcessor size = int( (256 / 224) * config.image_size ) # to maintain same ratio w.r.t. 224 images, see https://github.com/facebookresearch/deit/blob/ab5715372db8c6cad5740714b2216d55aeae052e/datasets.py#L103 - feature_extractor = DeiTFeatureExtractor(size=size, crop_size=config.image_size) - encoding = feature_extractor(images=prepare_img(), return_tensors="pt") + image_processor = DeiTImageProcessor(size=size, crop_size=config.image_size) + encoding = image_processor(images=prepare_img(), return_tensors="pt") pixel_values = encoding["pixel_values"] outputs = model(pixel_values) @@ -198,8 +198,8 @@ def convert_deit_checkpoint(deit_name, pytorch_dump_folder_path): Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model {deit_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py index b6dcc617da..72de2be870 100644 --- a/src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py @@ -25,7 +25,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import DetrConfig, DetrFeatureExtractor, DetrForObjectDetection, DetrForSegmentation +from transformers import DetrConfig, DetrForObjectDetection, DetrForSegmentation, DetrImageProcessor from transformers.utils import logging @@ -201,13 +201,13 @@ def convert_detr_checkpoint(model_name, pytorch_dump_folder_path): config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} - # load feature extractor + # load image processor format = "coco_panoptic" if is_panoptic else "coco_detection" - feature_extractor = DetrFeatureExtractor(format=format) + image_processor = DetrImageProcessor(format=format) # prepare image img = prepare_img() - encoding = feature_extractor(images=img, return_tensors="pt") + encoding = image_processor(images=img, return_tensors="pt") pixel_values = encoding["pixel_values"] logger.info(f"Converting model {model_name}...") @@ -258,11 +258,11 @@ def convert_detr_checkpoint(model_name, pytorch_dump_folder_path): if is_panoptic: assert torch.allclose(outputs.pred_masks, original_outputs["pred_masks"], atol=1e-4) - # Save model and feature extractor - logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...") + # Save model and image processor + logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...") Path(pytorch_dump_folder_path).mkdir(exist_ok=True) model.save_pretrained(pytorch_dump_folder_path) - feature_extractor.save_pretrained(pytorch_dump_folder_path) + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/detr/image_processing_detr.py b/src/transformers/models/detr/image_processing_detr.py index f39db7b8de..c8ea81eac7 100644 --- a/src/transformers/models/detr/image_processing_detr.py +++ b/src/transformers/models/detr/image_processing_detr.py @@ -1341,8 +1341,7 @@ class DetrImageProcessor(BaseImageProcessor): Args: results (`List[Dict]`): - Results list obtained by [`~DetrFeatureExtractor.post_process`], to which "masks" results will be - added. + Results list obtained by [`~DetrImageProcessor.post_process`], to which "masks" results will be added. outputs ([`DetrSegmentationOutput`]): Raw outputs of the model. orig_target_sizes (`torch.Tensor` of shape `(batch_size, 2)`): diff --git a/src/transformers/models/dit/convert_dit_unilm_to_pytorch.py b/src/transformers/models/dit/convert_dit_unilm_to_pytorch.py index d80e9d890d..c754b9bbf3 100644 --- a/src/transformers/models/dit/convert_dit_unilm_to_pytorch.py +++ b/src/transformers/models/dit/convert_dit_unilm_to_pytorch.py @@ -24,7 +24,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import BeitConfig, BeitFeatureExtractor, BeitForImageClassification, BeitForMaskedImageModeling +from transformers import BeitConfig, BeitForImageClassification, BeitForMaskedImageModeling, BeitImageProcessor from transformers.image_utils import PILImageResampling from transformers.utils import logging @@ -171,12 +171,12 @@ def convert_dit_checkpoint(checkpoint_url, pytorch_dump_folder_path, push_to_hub model.load_state_dict(state_dict) # Check outputs on an image - feature_extractor = BeitFeatureExtractor( + image_processor = BeitImageProcessor( size=config.image_size, resample=PILImageResampling.BILINEAR, do_center_crop=False ) image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt") + encoding = image_processor(images=image, return_tensors="pt") pixel_values = encoding["pixel_values"] outputs = model(pixel_values) @@ -189,18 +189,18 @@ def convert_dit_checkpoint(checkpoint_url, pytorch_dump_folder_path, push_to_hub Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: if has_lm_head: model_name = "dit-base" if "base" in checkpoint_url else "dit-large" else: model_name = "dit-base-finetuned-rvlcdip" if "dit-b" in checkpoint_url else "dit-large-finetuned-rvlcdip" - feature_extractor.push_to_hub( + image_processor.push_to_hub( repo_path_or_name=Path(pytorch_dump_folder_path, model_name), organization="nielsr", - commit_message="Add feature extractor", + commit_message="Add image processor", use_temp_dir=True, ) model.push_to_hub( diff --git a/src/transformers/models/donut/convert_donut_to_pytorch.py b/src/transformers/models/donut/convert_donut_to_pytorch.py index cd0f437735..13f669ad97 100644 --- a/src/transformers/models/donut/convert_donut_to_pytorch.py +++ b/src/transformers/models/donut/convert_donut_to_pytorch.py @@ -21,7 +21,7 @@ from datasets import load_dataset from donut import DonutModel from transformers import ( - DonutFeatureExtractor, + DonutImageProcessor, DonutProcessor, DonutSwinConfig, DonutSwinModel, @@ -152,10 +152,10 @@ def convert_donut_checkpoint(model_name, pytorch_dump_folder_path=None, push_to_ image = dataset["test"][0]["image"].convert("RGB") tokenizer = XLMRobertaTokenizerFast.from_pretrained(model_name, from_slow=True) - feature_extractor = DonutFeatureExtractor( + image_processor = DonutImageProcessor( do_align_long_axis=original_model.config.align_long_axis, size=original_model.config.input_size[::-1] ) - processor = DonutProcessor(feature_extractor, tokenizer) + processor = DonutProcessor(image_processor, tokenizer) pixel_values = processor(image, return_tensors="pt").pixel_values if model_name == "naver-clova-ix/donut-base-finetuned-docvqa": diff --git a/src/transformers/models/dpt/convert_dpt_hybrid_to_pytorch.py b/src/transformers/models/dpt/convert_dpt_hybrid_to_pytorch.py index a563436b13..0fa69adfaf 100644 --- a/src/transformers/models/dpt/convert_dpt_hybrid_to_pytorch.py +++ b/src/transformers/models/dpt/convert_dpt_hybrid_to_pytorch.py @@ -24,7 +24,7 @@ import torch from huggingface_hub import cached_download, hf_hub_url from PIL import Image -from transformers import DPTConfig, DPTFeatureExtractor, DPTForDepthEstimation, DPTForSemanticSegmentation +from transformers import DPTConfig, DPTForDepthEstimation, DPTForSemanticSegmentation, DPTImageProcessor from transformers.utils import logging @@ -244,10 +244,10 @@ def convert_dpt_checkpoint(checkpoint_url, pytorch_dump_folder_path, push_to_hub # Check outputs on an image size = 480 if "ade" in checkpoint_url else 384 - feature_extractor = DPTFeatureExtractor(size=size) + image_processor = DPTImageProcessor(size=size) image = prepare_img() - encoding = feature_extractor(image, return_tensors="pt") + encoding = image_processor(image, return_tensors="pt") # forward pass outputs = model(**encoding).logits if "ade" in checkpoint_url else model(**encoding).predicted_depth @@ -271,12 +271,12 @@ def convert_dpt_checkpoint(checkpoint_url, pytorch_dump_folder_path, push_to_hub Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: model.push_to_hub("ybelkada/dpt-hybrid-midas") - feature_extractor.push_to_hub("ybelkada/dpt-hybrid-midas") + image_processor.push_to_hub("ybelkada/dpt-hybrid-midas") if __name__ == "__main__": diff --git a/src/transformers/models/dpt/convert_dpt_to_pytorch.py b/src/transformers/models/dpt/convert_dpt_to_pytorch.py index 7ef5f7cf11..cee5be88c3 100644 --- a/src/transformers/models/dpt/convert_dpt_to_pytorch.py +++ b/src/transformers/models/dpt/convert_dpt_to_pytorch.py @@ -24,7 +24,7 @@ import torch from huggingface_hub import cached_download, hf_hub_url from PIL import Image -from transformers import DPTConfig, DPTFeatureExtractor, DPTForDepthEstimation, DPTForSemanticSegmentation +from transformers import DPTConfig, DPTForDepthEstimation, DPTForSemanticSegmentation, DPTImageProcessor from transformers.utils import logging @@ -211,10 +211,10 @@ def convert_dpt_checkpoint(checkpoint_url, pytorch_dump_folder_path, push_to_hub # Check outputs on an image size = 480 if "ade" in checkpoint_url else 384 - feature_extractor = DPTFeatureExtractor(size=size) + image_processor = DPTImageProcessor(size=size) image = prepare_img() - encoding = feature_extractor(image, return_tensors="pt") + encoding = image_processor(image, return_tensors="pt") # forward pass outputs = model(**encoding).logits if "ade" in checkpoint_url else model(**encoding).predicted_depth @@ -233,8 +233,8 @@ def convert_dpt_checkpoint(checkpoint_url, pytorch_dump_folder_path, push_to_hub Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: print("Pushing model to hub...") @@ -244,10 +244,10 @@ def convert_dpt_checkpoint(checkpoint_url, pytorch_dump_folder_path, push_to_hub commit_message="Add model", use_temp_dir=True, ) - feature_extractor.push_to_hub( + image_processor.push_to_hub( repo_path_or_name=Path(pytorch_dump_folder_path, model_name), organization="nielsr", - commit_message="Add feature extractor", + commit_message="Add image processor", use_temp_dir=True, ) diff --git a/src/transformers/models/efficientformer/convert_efficientformer_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/efficientformer/convert_efficientformer_original_pytorch_checkpoint_to_pytorch.py index 2f5e441226..7431cd6136 100644 --- a/src/transformers/models/efficientformer/convert_efficientformer_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/efficientformer/convert_efficientformer_original_pytorch_checkpoint_to_pytorch.py @@ -208,7 +208,7 @@ def convert_efficientformer_checkpoint( ) processor.push_to_hub( repo_id=f"Bearnardd/{pytorch_dump_path}", - commit_message="Add feature extractor", + commit_message="Add image processor", use_temp_dir=True, ) @@ -234,12 +234,12 @@ if __name__ == "__main__": "--pytorch_dump_path", default=None, type=str, required=True, help="Path to the output PyTorch model." ) - parser.add_argument("--push_to_hub", action="store_true", help="Push model and feature extractor to the hub") + parser.add_argument("--push_to_hub", action="store_true", help="Push model and image processor to the hub") parser.add_argument( "--no-push_to_hub", dest="push_to_hub", action="store_false", - help="Do not push model and feature extractor to the hub", + help="Do not push model and image processor to the hub", ) parser.set_defaults(push_to_hub=True) diff --git a/src/transformers/models/efficientformer/modeling_efficientformer.py b/src/transformers/models/efficientformer/modeling_efficientformer.py index cd38b2d813..c3ed5cace8 100644 --- a/src/transformers/models/efficientformer/modeling_efficientformer.py +++ b/src/transformers/models/efficientformer/modeling_efficientformer.py @@ -537,8 +537,8 @@ EFFICIENTFORMER_START_DOCSTRING = r""" EFFICIENTFORMER_INPUTS_DOCSTRING = r""" Args: pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): - Pixel values. Pixel values can be obtained using [`ViTFeatureExtractor`]. See - [`ViTFeatureExtractor.__call__`] for details. + Pixel values. Pixel values can be obtained using [`ViTImageProcessor`]. See + [`ViTImageProcessor.preprocess`] for details. output_attentions (`bool`, *optional*): Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. diff --git a/src/transformers/models/efficientnet/convert_efficientnet_to_pytorch.py b/src/transformers/models/efficientnet/convert_efficientnet_to_pytorch.py index 9813ccb9b8..e9988524ac 100644 --- a/src/transformers/models/efficientnet/convert_efficientnet_to_pytorch.py +++ b/src/transformers/models/efficientnet/convert_efficientnet_to_pytorch.py @@ -305,12 +305,12 @@ def convert_efficientnet_checkpoint(model_name, pytorch_dump_folder_path, save_m # Create folder to save model if not os.path.isdir(pytorch_dump_folder_path): os.mkdir(pytorch_dump_folder_path) - # Save converted model and feature extractor + # Save converted model and image processor hf_model.save_pretrained(pytorch_dump_folder_path) preprocessor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: - # Push model and feature extractor to hub + # Push model and image processor to hub print(f"Pushing converted {model_name} to the hub...") model_name = f"efficientnet-{model_name}" preprocessor.push_to_hub(model_name) @@ -333,7 +333,7 @@ if __name__ == "__main__": help="Path to the output PyTorch model directory.", ) parser.add_argument("--save_model", action="store_true", help="Save model to local") - parser.add_argument("--push_to_hub", action="store_true", help="Push model and feature extractor to the hub") + parser.add_argument("--push_to_hub", action="store_true", help="Push model and image processor to the hub") args = parser.parse_args() convert_efficientnet_checkpoint(args.model_name, args.pytorch_dump_folder_path, args.save_model, args.push_to_hub) diff --git a/src/transformers/models/glpn/convert_glpn_to_pytorch.py b/src/transformers/models/glpn/convert_glpn_to_pytorch.py index fa0af4691a..5f0183783e 100644 --- a/src/transformers/models/glpn/convert_glpn_to_pytorch.py +++ b/src/transformers/models/glpn/convert_glpn_to_pytorch.py @@ -23,7 +23,7 @@ import requests import torch from PIL import Image -from transformers import GLPNConfig, GLPNFeatureExtractor, GLPNForDepthEstimation +from transformers import GLPNConfig, GLPNForDepthEstimation, GLPNImageProcessor from transformers.utils import logging @@ -131,12 +131,12 @@ def convert_glpn_checkpoint(checkpoint_path, pytorch_dump_folder_path, push_to_h # load GLPN configuration (Segformer-B4 size) config = GLPNConfig(hidden_sizes=[64, 128, 320, 512], decoder_hidden_size=64, depths=[3, 8, 27, 3]) - # load feature extractor (only resize + rescale) - feature_extractor = GLPNFeatureExtractor() + # load image processor (only resize + rescale) + image_processor = GLPNImageProcessor() # prepare image image = prepare_img() - pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values + pixel_values = image_processor(images=image, return_tensors="pt").pixel_values logger.info("Converting model...") @@ -179,17 +179,17 @@ def convert_glpn_checkpoint(checkpoint_path, pytorch_dump_folder_path, push_to_h # finally, push to hub if required if push_to_hub: - logger.info("Pushing model and feature extractor to the hub...") + logger.info("Pushing model and image processor to the hub...") model.push_to_hub( repo_path_or_name=Path(pytorch_dump_folder_path, model_name), organization="nielsr", commit_message="Add model", use_temp_dir=True, ) - feature_extractor.push_to_hub( + image_processor.push_to_hub( repo_path_or_name=Path(pytorch_dump_folder_path, model_name), organization="nielsr", - commit_message="Add feature extractor", + commit_message="Add image processor", use_temp_dir=True, ) diff --git a/src/transformers/models/groupvit/configuration_groupvit.py b/src/transformers/models/groupvit/configuration_groupvit.py index 9f29b9a481..867377a863 100644 --- a/src/transformers/models/groupvit/configuration_groupvit.py +++ b/src/transformers/models/groupvit/configuration_groupvit.py @@ -458,7 +458,7 @@ class GroupViTOnnxConfig(OnnxConfig): processor.tokenizer, batch_size=batch_size, seq_length=seq_length, framework=framework ) image_input_dict = super().generate_dummy_inputs( - processor.feature_extractor, batch_size=batch_size, framework=framework + processor.image_processor, batch_size=batch_size, framework=framework ) return {**text_input_dict, **image_input_dict} diff --git a/src/transformers/models/imagegpt/image_processing_imagegpt.py b/src/transformers/models/imagegpt/image_processing_imagegpt.py index e40e09a533..b00ef83dda 100644 --- a/src/transformers/models/imagegpt/image_processing_imagegpt.py +++ b/src/transformers/models/imagegpt/image_processing_imagegpt.py @@ -81,7 +81,7 @@ class ImageGPTImageProcessor(BaseImageProcessor): def __init__( self, - # clusters is a first argument to maintain backwards compatibility with the old ImageGPTFeatureExtractor + # clusters is a first argument to maintain backwards compatibility with the old ImageGPTImageProcessor clusters: Optional[Union[List[List[int]], np.ndarray]] = None, do_resize: bool = True, size: Dict[str, int] = None, diff --git a/src/transformers/models/layoutlmv3/configuration_layoutlmv3.py b/src/transformers/models/layoutlmv3/configuration_layoutlmv3.py index e39e5b61e2..31ca2e00e4 100644 --- a/src/transformers/models/layoutlmv3/configuration_layoutlmv3.py +++ b/src/transformers/models/layoutlmv3/configuration_layoutlmv3.py @@ -260,7 +260,7 @@ class LayoutLMv3OnnxConfig(OnnxConfig): """ # A dummy image is used so OCR should not be applied - setattr(processor.feature_extractor, "apply_ocr", False) + setattr(processor.image_processor, "apply_ocr", False) # If dynamic axis (-1) we forward with a fixed dimension of 2 samples to avoid optimizations made by ONNX batch_size = compute_effective_axis_dimension( diff --git a/src/transformers/models/layoutxlm/processing_layoutxlm.py b/src/transformers/models/layoutxlm/processing_layoutxlm.py index 250c8c7fc6..1fd621f888 100644 --- a/src/transformers/models/layoutxlm/processing_layoutxlm.py +++ b/src/transformers/models/layoutxlm/processing_layoutxlm.py @@ -15,6 +15,7 @@ """ Processor class for LayoutXLM. """ +import warnings from typing import List, Optional, Union from ...processing_utils import ProcessorMixin @@ -24,26 +25,45 @@ from ...utils import TensorType class LayoutXLMProcessor(ProcessorMixin): r""" - Constructs a LayoutXLM processor which combines a LayoutXLM feature extractor and a LayoutXLM tokenizer into a - single processor. + Constructs a LayoutXLM processor which combines a LayoutXLM image processor and a LayoutXLM tokenizer into a single + processor. [`LayoutXLMProcessor`] offers all the functionalities you need to prepare data for the model. - It first uses [`LayoutLMv2FeatureExtractor`] to resize document images to a fixed size, and optionally applies OCR - to get words and normalized bounding boxes. These are then provided to [`LayoutXLMTokenizer`] or + It first uses [`LayoutLMv2ImageProcessor`] to resize document images to a fixed size, and optionally applies OCR to + get words and normalized bounding boxes. These are then provided to [`LayoutXLMTokenizer`] or [`LayoutXLMTokenizerFast`], which turns the words and bounding boxes into token-level `input_ids`, `attention_mask`, `token_type_ids`, `bbox`. Optionally, one can provide integer `word_labels`, which are turned into token-level `labels` for token classification tasks (such as FUNSD, CORD). Args: - feature_extractor (`LayoutLMv2FeatureExtractor`): - An instance of [`LayoutLMv2FeatureExtractor`]. The feature extractor is a required input. + image_processor (`LayoutLMv2ImageProcessor`): + An instance of [`LayoutLMv2ImageProcessor`]. The image processor is a required input. tokenizer (`LayoutXLMTokenizer` or `LayoutXLMTokenizerFast`): An instance of [`LayoutXLMTokenizer`] or [`LayoutXLMTokenizerFast`]. The tokenizer is a required input. """ - feature_extractor_class = "LayoutLMv2FeatureExtractor" + + attributes = ["image_processor", "tokenizer"] + image_processor_class = "LayoutLMv2ImageProcessor" tokenizer_class = ("LayoutXLMTokenizer", "LayoutXLMTokenizerFast") + def __init__(self, image_processor=None, tokenizer=None, **kwargs): + if "feature_extractor" in kwargs: + warnings.warn( + "The `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor`" + " instead.", + FutureWarning, + ) + feature_extractor = kwargs.pop("feature_extractor") + + image_processor = image_processor if image_processor is not None else feature_extractor + if image_processor is None: + raise ValueError("You need to specify an `image_processor`.") + if tokenizer is None: + raise ValueError("You need to specify a `tokenizer`.") + + super().__init__(image_processor, tokenizer) + def __call__( self, images, @@ -68,37 +88,37 @@ class LayoutXLMProcessor(ProcessorMixin): **kwargs, ) -> BatchEncoding: """ - This method first forwards the `images` argument to [`~LayoutLMv2FeatureExtractor.__call__`]. In case - [`LayoutLMv2FeatureExtractor`] was initialized with `apply_ocr` set to `True`, it passes the obtained words and + This method first forwards the `images` argument to [`~LayoutLMv2ImagePrpcessor.__call__`]. In case + [`LayoutLMv2ImagePrpcessor`] was initialized with `apply_ocr` set to `True`, it passes the obtained words and bounding boxes along with the additional arguments to [`~LayoutXLMTokenizer.__call__`] and returns the output, - together with resized `images`. In case [`LayoutLMv2FeatureExtractor`] was initialized with `apply_ocr` set to + together with resized `images`. In case [`LayoutLMv2ImagePrpcessor`] was initialized with `apply_ocr` set to `False`, it passes the words (`text`/``text_pair`) and `boxes` specified by the user along with the additional arguments to [`~LayoutXLMTokenizer.__call__`] and returns the output, together with resized `images``. Please refer to the docstring of the above two methods for more information. """ # verify input - if self.feature_extractor.apply_ocr and (boxes is not None): + if self.image_processor.apply_ocr and (boxes is not None): raise ValueError( "You cannot provide bounding boxes " - "if you initialized the feature extractor with apply_ocr set to True." + "if you initialized the image processor with apply_ocr set to True." ) - if self.feature_extractor.apply_ocr and (word_labels is not None): + if self.image_processor.apply_ocr and (word_labels is not None): raise ValueError( - "You cannot provide word labels if you initialized the feature extractor with apply_ocr set to True." + "You cannot provide word labels if you initialized the image processor with apply_ocr set to True." ) if return_overflowing_tokens is True and return_offsets_mapping is False: raise ValueError("You cannot return overflowing tokens without returning the offsets mapping.") - # first, apply the feature extractor - features = self.feature_extractor(images=images, return_tensors=return_tensors) + # first, apply the image processor + features = self.image_processor(images=images, return_tensors=return_tensors) # second, apply the tokenizer - if text is not None and self.feature_extractor.apply_ocr and text_pair is None: + if text is not None and self.image_processor.apply_ocr and text_pair is None: if isinstance(text, str): - text = [text] # add batch dimension (as the feature extractor always adds a batch dimension) + text = [text] # add batch dimension (as the image processor always adds a batch dimension) text_pair = features["words"] encoded_inputs = self.tokenizer( @@ -162,3 +182,19 @@ class LayoutXLMProcessor(ProcessorMixin): @property def model_input_names(self): return ["input_ids", "bbox", "attention_mask", "image"] + + @property + def feature_extractor_class(self): + warnings.warn( + "`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.", + FutureWarning, + ) + return self.image_processor_class + + @property + def feature_extractor(self): + warnings.warn( + "`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.", + FutureWarning, + ) + return self.image_processor diff --git a/src/transformers/models/levit/convert_levit_timm_to_pytorch.py b/src/transformers/models/levit/convert_levit_timm_to_pytorch.py index a6ae6603e5..6f285a6de3 100644 --- a/src/transformers/models/levit/convert_levit_timm_to_pytorch.py +++ b/src/transformers/models/levit/convert_levit_timm_to_pytorch.py @@ -25,7 +25,7 @@ import timm import torch from huggingface_hub import hf_hub_download -from transformers import LevitConfig, LevitFeatureExtractor, LevitForImageClassificationWithTeacher +from transformers import LevitConfig, LevitForImageClassificationWithTeacher, LevitImageProcessor from transformers.utils import logging @@ -74,8 +74,8 @@ def convert_weight_and_push( if push_to_hub: our_model.save_pretrained(save_directory / checkpoint_name) - feature_extractor = LevitFeatureExtractor() - feature_extractor.save_pretrained(save_directory / checkpoint_name) + image_processor = LevitImageProcessor() + image_processor.save_pretrained(save_directory / checkpoint_name) print(f"Pushed {checkpoint_name}") @@ -167,12 +167,12 @@ if __name__ == "__main__": required=False, help="Path to the output PyTorch model directory.", ) - parser.add_argument("--push_to_hub", action="store_true", help="Push model and feature extractor to the hub") + parser.add_argument("--push_to_hub", action="store_true", help="Push model and image processor to the hub") parser.add_argument( "--no-push_to_hub", dest="push_to_hub", action="store_false", - help="Do not push model and feature extractor to the hub", + help="Do not push model and image processor to the hub", ) args = parser.parse_args() diff --git a/src/transformers/models/mask2former/convert_mask2former_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/mask2former/convert_mask2former_original_pytorch_checkpoint_to_pytorch.py index 20ff7e780d..ea1c578509 100644 --- a/src/transformers/models/mask2former/convert_mask2former_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/mask2former/convert_mask2former_original_pytorch_checkpoint_to_pytorch.py @@ -192,7 +192,7 @@ class OriginalMask2FormerConfigToOursConverter: return config -class OriginalMask2FormerConfigToFeatureExtractorConverter: +class OriginalMask2FormerConfigToImageProcessorConverter: def __call__(self, original_config: object) -> Mask2FormerImageProcessor: model = original_config.MODEL model_input = original_config.INPUT @@ -846,7 +846,7 @@ class OriginalMask2FormerCheckpointToOursConverter: def test( original_model, our_model: Mask2FormerForUniversalSegmentation, - feature_extractor: Mask2FormerImageProcessor, + image_processor: Mask2FormerImageProcessor, tolerance: float, ): with torch.no_grad(): @@ -854,7 +854,7 @@ def test( our_model = our_model.eval() im = prepare_img() - x = feature_extractor(images=im, return_tensors="pt")["pixel_values"] + x = image_processor(images=im, return_tensors="pt")["pixel_values"] original_model_backbone_features = original_model.backbone(x.clone()) our_model_output: Mask2FormerModelOutput = our_model.model(x.clone(), output_hidden_states=True) @@ -979,10 +979,10 @@ if __name__ == "__main__": checkpoints_dir, config_dir ): model_name = get_model_name(checkpoint_file) - feature_extractor = OriginalMask2FormerConfigToFeatureExtractorConverter()( + image_processor = OriginalMask2FormerConfigToImageProcessorConverter()( setup_cfg(Args(config_file=config_file)) ) - feature_extractor.size = {"height": 384, "width": 384} + image_processor.size = {"height": 384, "width": 384} original_config = setup_cfg(Args(config_file=config_file)) mask2former_kwargs = OriginalMask2Former.from_config(original_config) @@ -1012,8 +1012,8 @@ if __name__ == "__main__": tolerance = 3e-1 logger.info(f"🪄 Testing {model_name}...") - test(original_model, mask2former_for_segmentation, feature_extractor, tolerance) + test(original_model, mask2former_for_segmentation, image_processor, tolerance) logger.info(f"🪄 Pushing {model_name} to hub...") - feature_extractor.push_to_hub(model_name) + image_processor.push_to_hub(model_name) mask2former_for_segmentation.push_to_hub(model_name) diff --git a/src/transformers/models/mask2former/modeling_mask2former.py b/src/transformers/models/mask2former/modeling_mask2former.py index 47a4a18d1a..f814e1a081 100644 --- a/src/transformers/models/mask2former/modeling_mask2former.py +++ b/src/transformers/models/mask2former/modeling_mask2former.py @@ -2106,8 +2106,8 @@ MASK2FORMER_START_DOCSTRING = r""" MASK2FORMER_INPUTS_DOCSTRING = r""" Args: pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`): - Pixel values. Pixel values can be obtained using [`AutoFeatureExtractor`]. See - [`AutoFeatureExtractor.__call__`] for details. + Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See + [`AutoImageProcessor.preprocess`] for details. pixel_mask (`torch.LongTensor` of shape `(batch_size, height, width)`, *optional*): Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`: diff --git a/src/transformers/models/maskformer/convert_maskformer_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/maskformer/convert_maskformer_original_pytorch_checkpoint_to_pytorch.py index df7c7aa7e1..999eee136a 100644 --- a/src/transformers/models/maskformer/convert_maskformer_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/maskformer/convert_maskformer_original_pytorch_checkpoint_to_pytorch.py @@ -29,7 +29,7 @@ from detectron2.projects.deeplab import add_deeplab_config from PIL import Image from torch import Tensor, nn -from transformers.models.maskformer.feature_extraction_maskformer import MaskFormerFeatureExtractor +from transformers.models.maskformer.feature_extraction_maskformer import MaskFormerImageProcessor from transformers.models.maskformer.modeling_maskformer import ( MaskFormerConfig, MaskFormerForInstanceSegmentation, @@ -164,13 +164,13 @@ class OriginalMaskFormerConfigToOursConverter: return config -class OriginalMaskFormerConfigToFeatureExtractorConverter: - def __call__(self, original_config: object) -> MaskFormerFeatureExtractor: +class OriginalMaskFormerConfigToImageProcessorConverter: + def __call__(self, original_config: object) -> MaskFormerImageProcessor: model = original_config.MODEL model_input = original_config.INPUT dataset_catalog = MetadataCatalog.get(original_config.DATASETS.TEST[0]) - return MaskFormerFeatureExtractor( + return MaskFormerImageProcessor( image_mean=(torch.tensor(model.PIXEL_MEAN) / 255).tolist(), image_std=(torch.tensor(model.PIXEL_STD) / 255).tolist(), size=model_input.MIN_SIZE_TEST, @@ -554,7 +554,7 @@ class OriginalMaskFormerCheckpointToOursConverter: yield config, checkpoint -def test(original_model, our_model: MaskFormerForInstanceSegmentation, feature_extractor: MaskFormerFeatureExtractor): +def test(original_model, our_model: MaskFormerForInstanceSegmentation, image_processor: MaskFormerImageProcessor): with torch.no_grad(): original_model = original_model.eval() our_model = our_model.eval() @@ -600,7 +600,7 @@ def test(original_model, our_model: MaskFormerForInstanceSegmentation, feature_e our_model_out: MaskFormerForInstanceSegmentationOutput = our_model(x) - our_segmentation = feature_extractor.post_process_segmentation(our_model_out, target_size=(384, 384)) + our_segmentation = image_processor.post_process_segmentation(our_model_out, target_size=(384, 384)) assert torch.allclose( original_segmentation, our_segmentation, atol=1e-3 @@ -686,9 +686,7 @@ if __name__ == "__main__": for config_file, checkpoint_file in OriginalMaskFormerCheckpointToOursConverter.using_dirs( checkpoints_dir, config_dir ): - feature_extractor = OriginalMaskFormerConfigToFeatureExtractorConverter()( - setup_cfg(Args(config_file=config_file)) - ) + image_processor = OriginalMaskFormerConfigToImageProcessorConverter()(setup_cfg(Args(config_file=config_file))) original_config = setup_cfg(Args(config_file=config_file)) mask_former_kwargs = OriginalMaskFormer.from_config(original_config) @@ -712,15 +710,15 @@ if __name__ == "__main__": mask_former_for_instance_segmentation ) - test(original_model, mask_former_for_instance_segmentation, feature_extractor) + test(original_model, mask_former_for_instance_segmentation, image_processor) model_name = get_name(checkpoint_file) logger.info(f"🪄 Saving {model_name}") - feature_extractor.save_pretrained(save_directory / model_name) + image_processor.save_pretrained(save_directory / model_name) mask_former_for_instance_segmentation.save_pretrained(save_directory / model_name) - feature_extractor.push_to_hub( + image_processor.push_to_hub( repo_path_or_name=save_directory / model_name, commit_message="Add model", use_temp_dir=True, diff --git a/src/transformers/models/maskformer/convert_maskformer_resnet_to_pytorch.py b/src/transformers/models/maskformer/convert_maskformer_resnet_to_pytorch.py index 0657de9ee6..fec508de41 100644 --- a/src/transformers/models/maskformer/convert_maskformer_resnet_to_pytorch.py +++ b/src/transformers/models/maskformer/convert_maskformer_resnet_to_pytorch.py @@ -26,7 +26,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import MaskFormerConfig, MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation, ResNetConfig +from transformers import MaskFormerConfig, MaskFormerForInstanceSegmentation, MaskFormerImageProcessor, ResNetConfig from transformers.utils import logging @@ -297,9 +297,9 @@ def convert_maskformer_checkpoint( else: ignore_index = 255 reduce_labels = True if "ade" in model_name else False - feature_extractor = MaskFormerFeatureExtractor(ignore_index=ignore_index, reduce_labels=reduce_labels) + image_processor = MaskFormerImageProcessor(ignore_index=ignore_index, reduce_labels=reduce_labels) - inputs = feature_extractor(image, return_tensors="pt") + inputs = image_processor(image, return_tensors="pt") outputs = model(**inputs) @@ -340,15 +340,15 @@ def convert_maskformer_checkpoint( print("Looks ok!") if pytorch_dump_folder_path is not None: - print(f"Saving model and feature extractor of {model_name} to {pytorch_dump_folder_path}") + print(f"Saving model and image processor of {model_name} to {pytorch_dump_folder_path}") Path(pytorch_dump_folder_path).mkdir(exist_ok=True) model.save_pretrained(pytorch_dump_folder_path) - feature_extractor.save_pretrained(pytorch_dump_folder_path) + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: - print(f"Pushing model and feature extractor of {model_name} to the hub...") + print(f"Pushing model and image processor of {model_name} to the hub...") model.push_to_hub(f"facebook/{model_name}") - feature_extractor.push_to_hub(f"facebook/{model_name}") + image_processor.push_to_hub(f"facebook/{model_name}") if __name__ == "__main__": diff --git a/src/transformers/models/maskformer/convert_maskformer_swin_to_pytorch.py b/src/transformers/models/maskformer/convert_maskformer_swin_to_pytorch.py index 4ec5f64f22..8f0d0e99df 100644 --- a/src/transformers/models/maskformer/convert_maskformer_swin_to_pytorch.py +++ b/src/transformers/models/maskformer/convert_maskformer_swin_to_pytorch.py @@ -26,7 +26,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import MaskFormerConfig, MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation, SwinConfig +from transformers import MaskFormerConfig, MaskFormerForInstanceSegmentation, MaskFormerImageProcessor, SwinConfig from transformers.utils import logging @@ -278,9 +278,9 @@ def convert_maskformer_checkpoint( else: ignore_index = 255 reduce_labels = True if "ade" in model_name else False - feature_extractor = MaskFormerFeatureExtractor(ignore_index=ignore_index, reduce_labels=reduce_labels) + image_processor = MaskFormerImageProcessor(ignore_index=ignore_index, reduce_labels=reduce_labels) - inputs = feature_extractor(image, return_tensors="pt") + inputs = image_processor(image, return_tensors="pt") outputs = model(**inputs) @@ -294,15 +294,15 @@ def convert_maskformer_checkpoint( print("Looks ok!") if pytorch_dump_folder_path is not None: - print(f"Saving model and feature extractor to {pytorch_dump_folder_path}") + print(f"Saving model and image processor to {pytorch_dump_folder_path}") Path(pytorch_dump_folder_path).mkdir(exist_ok=True) model.save_pretrained(pytorch_dump_folder_path) - feature_extractor.save_pretrained(pytorch_dump_folder_path) + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: - print("Pushing model and feature extractor to the hub...") + print("Pushing model and image processor to the hub...") model.push_to_hub(f"nielsr/{model_name}") - feature_extractor.push_to_hub(f"nielsr/{model_name}") + image_processor.push_to_hub(f"nielsr/{model_name}") if __name__ == "__main__": diff --git a/src/transformers/models/mobilenet_v1/convert_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/mobilenet_v1/convert_original_tf_checkpoint_to_pytorch.py index 66533cb8d0..4985e0ff22 100644 --- a/src/transformers/models/mobilenet_v1/convert_original_tf_checkpoint_to_pytorch.py +++ b/src/transformers/models/mobilenet_v1/convert_original_tf_checkpoint_to_pytorch.py @@ -27,8 +27,8 @@ from PIL import Image from transformers import ( MobileNetV1Config, - MobileNetV1FeatureExtractor, MobileNetV1ForImageClassification, + MobileNetV1ImageProcessor, load_tf_weights_in_mobilenet_v1, ) from transformers.utils import logging @@ -83,12 +83,12 @@ def convert_movilevit_checkpoint(model_name, checkpoint_path, pytorch_dump_folde # Load weights from TensorFlow checkpoint load_tf_weights_in_mobilenet_v1(model, config, checkpoint_path) - # Check outputs on an image, prepared by MobileNetV1FeatureExtractor - feature_extractor = MobileNetV1FeatureExtractor( + # Check outputs on an image, prepared by MobileNetV1ImageProcessor + image_processor = MobileNetV1ImageProcessor( crop_size={"width": config.image_size, "height": config.image_size}, size={"shortest_edge": config.image_size + 32}, ) - encoding = feature_extractor(images=prepare_img(), return_tensors="pt") + encoding = image_processor(images=prepare_img(), return_tensors="pt") outputs = model(**encoding) logits = outputs.logits @@ -107,13 +107,13 @@ def convert_movilevit_checkpoint(model_name, checkpoint_path, pytorch_dump_folde Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model {model_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: print("Pushing to the hub...") repo_id = "google/" + model_name - feature_extractor.push_to_hub(repo_id) + image_processor.push_to_hub(repo_id) model.push_to_hub(repo_id) diff --git a/src/transformers/models/mobilenet_v2/convert_original_tf_checkpoint_to_pytorch.py b/src/transformers/models/mobilenet_v2/convert_original_tf_checkpoint_to_pytorch.py index 8b216aecb8..443bf8fd7e 100644 --- a/src/transformers/models/mobilenet_v2/convert_original_tf_checkpoint_to_pytorch.py +++ b/src/transformers/models/mobilenet_v2/convert_original_tf_checkpoint_to_pytorch.py @@ -99,11 +99,11 @@ def convert_movilevit_checkpoint(model_name, checkpoint_path, pytorch_dump_folde load_tf_weights_in_mobilenet_v2(model, config, checkpoint_path) # Check outputs on an image, prepared by MobileNetV2ImageProcessor - feature_extractor = MobileNetV2ImageProcessor( + image_processor = MobileNetV2ImageProcessor( crop_size={"width": config.image_size, "height": config.image_size}, size={"shortest_edge": config.image_size + 32}, ) - encoding = feature_extractor(images=prepare_img(), return_tensors="pt") + encoding = image_processor(images=prepare_img(), return_tensors="pt") outputs = model(**encoding) logits = outputs.logits @@ -143,13 +143,13 @@ def convert_movilevit_checkpoint(model_name, checkpoint_path, pytorch_dump_folde Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model {model_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: print("Pushing to the hub...") repo_id = "google/" + model_name - feature_extractor.push_to_hub(repo_id) + image_processor.push_to_hub(repo_id) model.push_to_hub(repo_id) diff --git a/src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py b/src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py index 50da675851..e251b124b4 100644 --- a/src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py +++ b/src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py @@ -26,9 +26,9 @@ from PIL import Image from transformers import ( MobileViTConfig, - MobileViTFeatureExtractor, MobileViTForImageClassification, MobileViTForSemanticSegmentation, + MobileViTImageProcessor, ) from transformers.utils import logging @@ -211,9 +211,9 @@ def convert_movilevit_checkpoint(mobilevit_name, checkpoint_path, pytorch_dump_f new_state_dict = convert_state_dict(state_dict, model) model.load_state_dict(new_state_dict) - # Check outputs on an image, prepared by MobileViTFeatureExtractor - feature_extractor = MobileViTFeatureExtractor(crop_size=config.image_size, size=config.image_size + 32) - encoding = feature_extractor(images=prepare_img(), return_tensors="pt") + # Check outputs on an image, prepared by MobileViTImageProcessor + image_processor = MobileViTImageProcessor(crop_size=config.image_size, size=config.image_size + 32) + encoding = image_processor(images=prepare_img(), return_tensors="pt") outputs = model(**encoding) logits = outputs.logits @@ -265,8 +265,8 @@ def convert_movilevit_checkpoint(mobilevit_name, checkpoint_path, pytorch_dump_f Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model {mobilevit_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: model_mapping = { @@ -280,7 +280,7 @@ def convert_movilevit_checkpoint(mobilevit_name, checkpoint_path, pytorch_dump_f print("Pushing to the hub...") model_name = model_mapping[mobilevit_name] - feature_extractor.push_to_hub(model_name, organization="apple") + image_processor.push_to_hub(model_name, organization="apple") model.push_to_hub(model_name, organization="apple") diff --git a/src/transformers/models/mobilevitv2/convert_mlcvnets_to_pytorch.py b/src/transformers/models/mobilevitv2/convert_mlcvnets_to_pytorch.py index 16e9029d72..2e2d31295d 100644 --- a/src/transformers/models/mobilevitv2/convert_mlcvnets_to_pytorch.py +++ b/src/transformers/models/mobilevitv2/convert_mlcvnets_to_pytorch.py @@ -259,8 +259,8 @@ def convert_mobilevitv2_checkpoint(task_name, checkpoint_path, orig_config_path, model.load_state_dict(state_dict) # Check outputs on an image, prepared by MobileViTImageProcessor - feature_extractor = MobileViTImageProcessor(crop_size=config.image_size, size=config.image_size + 32) - encoding = feature_extractor(images=prepare_img(), return_tensors="pt") + image_processor = MobileViTImageProcessor(crop_size=config.image_size, size=config.image_size + 32) + encoding = image_processor(images=prepare_img(), return_tensors="pt") outputs = model(**encoding) # verify classification model @@ -276,8 +276,8 @@ def convert_mobilevitv2_checkpoint(task_name, checkpoint_path, orig_config_path, Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model {task_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/owlvit/configuration_owlvit.py b/src/transformers/models/owlvit/configuration_owlvit.py index 673f6d7ee6..2403937b89 100644 --- a/src/transformers/models/owlvit/configuration_owlvit.py +++ b/src/transformers/models/owlvit/configuration_owlvit.py @@ -383,7 +383,7 @@ class OwlViTOnnxConfig(OnnxConfig): processor.tokenizer, batch_size=batch_size, seq_length=seq_length, framework=framework ) image_input_dict = super().generate_dummy_inputs( - processor.feature_extractor, batch_size=batch_size, framework=framework + processor.image_processor, batch_size=batch_size, framework=framework ) return {**text_input_dict, **image_input_dict} diff --git a/src/transformers/models/owlvit/convert_owlvit_original_flax_to_hf.py b/src/transformers/models/owlvit/convert_owlvit_original_flax_to_hf.py index 934c23b4d3..1e9fbb9504 100644 --- a/src/transformers/models/owlvit/convert_owlvit_original_flax_to_hf.py +++ b/src/transformers/models/owlvit/convert_owlvit_original_flax_to_hf.py @@ -29,8 +29,8 @@ from huggingface_hub import Repository from transformers import ( CLIPTokenizer, OwlViTConfig, - OwlViTFeatureExtractor, OwlViTForObjectDetection, + OwlViTImageProcessor, OwlViTModel, OwlViTProcessor, ) @@ -350,16 +350,16 @@ def convert_owlvit_checkpoint(pt_backbone, flax_params, attn_params, pytorch_dum # Save HF model hf_model.save_pretrained(repo.local_dir) - # Initialize feature extractor - feature_extractor = OwlViTFeatureExtractor( + # Initialize image processor + image_processor = OwlViTImageProcessor( size=config.vision_config.image_size, crop_size=config.vision_config.image_size ) # Initialize tokenizer tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32", pad_token="!", model_max_length=16) # Initialize processor - processor = OwlViTProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer) - feature_extractor.save_pretrained(repo.local_dir) + processor = OwlViTProcessor(image_processor=image_processor, tokenizer=tokenizer) + image_processor.save_pretrained(repo.local_dir) processor.save_pretrained(repo.local_dir) repo.git_add() diff --git a/src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py b/src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py index 9b9b3cb454..1ea9798127 100644 --- a/src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py +++ b/src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py @@ -29,13 +29,13 @@ from PIL import Image from transformers import ( PerceiverConfig, - PerceiverFeatureExtractor, PerceiverForImageClassificationConvProcessing, PerceiverForImageClassificationFourier, PerceiverForImageClassificationLearned, PerceiverForMaskedLM, PerceiverForMultimodalAutoencoding, PerceiverForOpticalFlow, + PerceiverImageProcessor, PerceiverTokenizer, ) from transformers.utils import logging @@ -389,9 +389,9 @@ def convert_perceiver_checkpoint(pickle_file, pytorch_dump_folder_path, architec inputs = encoding.input_ids input_mask = encoding.attention_mask elif architecture in ["image_classification", "image_classification_fourier", "image_classification_conv"]: - feature_extractor = PerceiverFeatureExtractor() + image_processor = PerceiverImageProcessor() image = prepare_img() - encoding = feature_extractor(image, return_tensors="pt") + encoding = image_processor(image, return_tensors="pt") inputs = encoding.pixel_values elif architecture == "optical_flow": inputs = torch.randn(1, 2, 27, 368, 496) diff --git a/src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py b/src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py index d00a9970aa..e5fad6da1a 100644 --- a/src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py +++ b/src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py @@ -24,7 +24,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import PoolFormerConfig, PoolFormerFeatureExtractor, PoolFormerForImageClassification +from transformers import PoolFormerConfig, PoolFormerForImageClassification, PoolFormerImageProcessor from transformers.utils import logging @@ -141,12 +141,12 @@ def convert_poolformer_checkpoint(model_name, checkpoint_path, pytorch_dump_fold else: raise ValueError(f"Size {size} not supported") - # load feature extractor - feature_extractor = PoolFormerFeatureExtractor(crop_pct=crop_pct) + # load image processor + image_processor = PoolFormerImageProcessor(crop_pct=crop_pct) # Prepare image image = prepare_img() - pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values + pixel_values = image_processor(images=image, return_tensors="pt").pixel_values logger.info(f"Converting model {model_name}...") @@ -161,9 +161,9 @@ def convert_poolformer_checkpoint(model_name, checkpoint_path, pytorch_dump_fold model.load_state_dict(state_dict) model.eval() - # Define feature extractor - feature_extractor = PoolFormerFeatureExtractor(crop_pct=crop_pct) - pixel_values = feature_extractor(images=prepare_img(), return_tensors="pt").pixel_values + # Define image processor + image_processor = PoolFormerImageProcessor(crop_pct=crop_pct) + pixel_values = image_processor(images=prepare_img(), return_tensors="pt").pixel_values # forward pass outputs = model(pixel_values) @@ -187,12 +187,12 @@ def convert_poolformer_checkpoint(model_name, checkpoint_path, pytorch_dump_fold assert logits.shape == expected_shape assert torch.allclose(logits[0, :3], expected_slice, atol=1e-2) - # finally, save model and feature extractor - logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...") + # finally, save model and image processor + logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...") Path(pytorch_dump_folder_path).mkdir(exist_ok=True) model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py b/src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py index f379b40d2a..93a516fb3c 100644 --- a/src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py +++ b/src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py @@ -34,7 +34,7 @@ from huggingface_hub import cached_download, hf_hub_url from torch import Tensor from vissl.models.model_helpers import get_trunk_forward_outputs -from transformers import AutoFeatureExtractor, RegNetConfig, RegNetForImageClassification, RegNetModel +from transformers import AutoImageProcessor, RegNetConfig, RegNetForImageClassification, RegNetModel from transformers.modeling_utils import PreTrainedModel from transformers.utils import logging @@ -262,10 +262,10 @@ def convert_weights_and_push(save_directory: Path, model_name: str = None, push_ ) size = 384 # we can use the convnext one - feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k-1k", size=size) - feature_extractor.push_to_hub( + image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-base-224-22k-1k", size=size) + image_processor.push_to_hub( repo_path_or_name=save_directory / model_name, - commit_message="Add feature extractor", + commit_message="Add image processor", output_dir=save_directory / model_name, ) @@ -294,7 +294,7 @@ if __name__ == "__main__": default=True, type=bool, required=False, - help="If True, push model and feature extractor to the hub.", + help="If True, push model and image processor to the hub.", ) args = parser.parse_args() diff --git a/src/transformers/models/regnet/convert_regnet_to_pytorch.py b/src/transformers/models/regnet/convert_regnet_to_pytorch.py index 1228e65c46..14d01ae445 100644 --- a/src/transformers/models/regnet/convert_regnet_to_pytorch.py +++ b/src/transformers/models/regnet/convert_regnet_to_pytorch.py @@ -30,7 +30,7 @@ from huggingface_hub import cached_download, hf_hub_url from torch import Tensor from vissl.models.model_helpers import get_trunk_forward_outputs -from transformers import AutoFeatureExtractor, RegNetConfig, RegNetForImageClassification, RegNetModel +from transformers import AutoImageProcessor, RegNetConfig, RegNetForImageClassification, RegNetModel from transformers.utils import logging @@ -209,10 +209,10 @@ def convert_weight_and_push( size = 224 if "seer" not in name else 384 # we can use the convnext one - feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k-1k", size=size) - feature_extractor.push_to_hub( + image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-base-224-22k-1k", size=size) + image_processor.push_to_hub( repo_path_or_name=save_directory / name, - commit_message="Add feature extractor", + commit_message="Add image processor", use_temp_dir=True, ) @@ -449,7 +449,7 @@ if __name__ == "__main__": default=True, type=bool, required=False, - help="If True, push model and feature extractor to the hub.", + help="If True, push model and image processor to the hub.", ) args = parser.parse_args() diff --git a/src/transformers/models/resnet/convert_resnet_to_pytorch.py b/src/transformers/models/resnet/convert_resnet_to_pytorch.py index f32887c964..52b0bd9068 100644 --- a/src/transformers/models/resnet/convert_resnet_to_pytorch.py +++ b/src/transformers/models/resnet/convert_resnet_to_pytorch.py @@ -28,7 +28,7 @@ import torch.nn as nn from huggingface_hub import hf_hub_download from torch import Tensor -from transformers import AutoFeatureExtractor, ResNetConfig, ResNetForImageClassification +from transformers import AutoImageProcessor, ResNetConfig, ResNetForImageClassification from transformers.utils import logging @@ -113,10 +113,10 @@ def convert_weight_and_push(name: str, config: ResNetConfig, save_directory: Pat ) # we can use the convnext one - feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k-1k") - feature_extractor.push_to_hub( + image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-base-224-22k-1k") + image_processor.push_to_hub( repo_path_or_name=save_directory / checkpoint_name, - commit_message="Add feature extractor", + commit_message="Add image processor", use_temp_dir=True, ) @@ -191,7 +191,7 @@ if __name__ == "__main__": default=True, type=bool, required=False, - help="If True, push model and feature extractor to the hub.", + help="If True, push model and image processor to the hub.", ) args = parser.parse_args() diff --git a/src/transformers/models/segformer/convert_segformer_original_to_pytorch.py b/src/transformers/models/segformer/convert_segformer_original_to_pytorch.py index 024a8699b0..48dd453309 100644 --- a/src/transformers/models/segformer/convert_segformer_original_to_pytorch.py +++ b/src/transformers/models/segformer/convert_segformer_original_to_pytorch.py @@ -27,9 +27,9 @@ from PIL import Image from transformers import ( SegformerConfig, - SegformerFeatureExtractor, SegformerForImageClassification, SegformerForSemanticSegmentation, + SegformerImageProcessor, ) from transformers.utils import logging @@ -179,14 +179,14 @@ def convert_segformer_checkpoint(model_name, checkpoint_path, pytorch_dump_folde else: raise ValueError(f"Size {size} not supported") - # load feature extractor (only resize + normalize) - feature_extractor = SegformerFeatureExtractor( + # load image processor (only resize + normalize) + image_processor = SegformerImageProcessor( image_scale=(512, 512), keep_ratio=False, align=False, do_random_crop=False ) # prepare image image = prepare_img() - pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values + pixel_values = image_processor(images=image, return_tensors="pt").pixel_values logger.info(f"Converting model {model_name}...") @@ -362,11 +362,11 @@ def convert_segformer_checkpoint(model_name, checkpoint_path, pytorch_dump_folde assert logits.shape == expected_shape assert torch.allclose(logits[0, :3, :3, :3], expected_slice, atol=1e-2) - # finally, save model and feature extractor - logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...") + # finally, save model and image processor + logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...") Path(pytorch_dump_folder_path).mkdir(exist_ok=True) model.save_pretrained(pytorch_dump_folder_path) - feature_extractor.save_pretrained(pytorch_dump_folder_path) + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/swin/convert_swin_simmim_to_pytorch.py b/src/transformers/models/swin/convert_swin_simmim_to_pytorch.py index 72e6bce5b0..156b0ba86c 100644 --- a/src/transformers/models/swin/convert_swin_simmim_to_pytorch.py +++ b/src/transformers/models/swin/convert_swin_simmim_to_pytorch.py @@ -22,7 +22,7 @@ import requests import torch from PIL import Image -from transformers import SwinConfig, SwinForMaskedImageModeling, ViTFeatureExtractor +from transformers import SwinConfig, SwinForMaskedImageModeling, ViTImageProcessor def get_swin_config(model_name): @@ -132,9 +132,9 @@ def convert_swin_checkpoint(model_name, checkpoint_path, pytorch_dump_folder_pat url = "http://images.cocodataset.org/val2017/000000039769.jpg" - feature_extractor = ViTFeatureExtractor(size={"height": 192, "width": 192}) + image_processor = ViTImageProcessor(size={"height": 192, "width": 192}) image = Image.open(requests.get(url, stream=True).raw) - inputs = feature_extractor(images=image, return_tensors="pt") + inputs = image_processor(images=image, return_tensors="pt") with torch.no_grad(): outputs = model(**inputs).logits @@ -146,13 +146,13 @@ def convert_swin_checkpoint(model_name, checkpoint_path, pytorch_dump_folder_pat print(f"Saving model {model_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: - print(f"Pushing model and feature extractor for {model_name} to hub") + print(f"Pushing model and image processor for {model_name} to hub") model.push_to_hub(f"microsoft/{model_name}") - feature_extractor.push_to_hub(f"microsoft/{model_name}") + image_processor.push_to_hub(f"microsoft/{model_name}") if __name__ == "__main__": diff --git a/src/transformers/models/swin/convert_swin_timm_to_pytorch.py b/src/transformers/models/swin/convert_swin_timm_to_pytorch.py index c5734757e6..828237490e 100644 --- a/src/transformers/models/swin/convert_swin_timm_to_pytorch.py +++ b/src/transformers/models/swin/convert_swin_timm_to_pytorch.py @@ -7,7 +7,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import AutoFeatureExtractor, SwinConfig, SwinForImageClassification +from transformers import AutoImageProcessor, SwinConfig, SwinForImageClassification def get_swin_config(swin_name): @@ -140,9 +140,9 @@ def convert_swin_checkpoint(swin_name, pytorch_dump_folder_path): url = "http://images.cocodataset.org/val2017/000000039769.jpg" - feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/{}".format(swin_name.replace("_", "-"))) + image_processor = AutoImageProcessor.from_pretrained("microsoft/{}".format(swin_name.replace("_", "-"))) image = Image.open(requests.get(url, stream=True).raw) - inputs = feature_extractor(images=image, return_tensors="pt") + inputs = image_processor(images=image, return_tensors="pt") timm_outs = timm_model(inputs["pixel_values"]) hf_outs = model(**inputs).logits @@ -152,8 +152,8 @@ def convert_swin_checkpoint(swin_name, pytorch_dump_folder_path): print(f"Saving model {swin_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py b/src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py index ba70e707a9..21deda864c 100644 --- a/src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py +++ b/src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py @@ -24,7 +24,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import AutoFeatureExtractor, Swinv2Config, Swinv2ForImageClassification +from transformers import AutoImageProcessor, Swinv2Config, Swinv2ForImageClassification def get_swinv2_config(swinv2_name): @@ -180,9 +180,9 @@ def convert_swinv2_checkpoint(swinv2_name, pytorch_dump_folder_path): url = "http://images.cocodataset.org/val2017/000000039769.jpg" - feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/{}".format(swinv2_name.replace("_", "-"))) + image_processor = AutoImageProcessor.from_pretrained("microsoft/{}".format(swinv2_name.replace("_", "-"))) image = Image.open(requests.get(url, stream=True).raw) - inputs = feature_extractor(images=image, return_tensors="pt") + inputs = image_processor(images=image, return_tensors="pt") timm_outs = timm_model(inputs["pixel_values"]) hf_outs = model(**inputs).logits @@ -192,8 +192,8 @@ def convert_swinv2_checkpoint(swinv2_name, pytorch_dump_folder_path): print(f"Saving model {swinv2_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) model.push_to_hub( repo_path_or_name=Path(pytorch_dump_folder_path, swinv2_name), diff --git a/src/transformers/models/table_transformer/convert_table_transformer_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/table_transformer/convert_table_transformer_original_pytorch_checkpoint_to_pytorch.py index 1973fe82e9..d351473e22 100644 --- a/src/transformers/models/table_transformer/convert_table_transformer_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/table_transformer/convert_table_transformer_original_pytorch_checkpoint_to_pytorch.py @@ -27,7 +27,7 @@ from huggingface_hub import hf_hub_download from PIL import Image from torchvision.transforms import functional as F -from transformers import DetrFeatureExtractor, TableTransformerConfig, TableTransformerForObjectDetection +from transformers import DetrImageProcessor, TableTransformerConfig, TableTransformerForObjectDetection from transformers.utils import logging @@ -242,7 +242,7 @@ def convert_table_transformer_checkpoint(checkpoint_url, pytorch_dump_folder_pat config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} - feature_extractor = DetrFeatureExtractor( + image_processor = DetrImageProcessor( format="coco_detection", max_size=800 if "detection" in checkpoint_url else 1000 ) model = TableTransformerForObjectDetection(config) @@ -277,11 +277,11 @@ def convert_table_transformer_checkpoint(checkpoint_url, pytorch_dump_folder_pat print("Looks ok!") if pytorch_dump_folder_path is not None: - # Save model and feature extractor - logger.info(f"Saving PyTorch model and feature extractor to {pytorch_dump_folder_path}...") + # Save model and image processor + logger.info(f"Saving PyTorch model and image processor to {pytorch_dump_folder_path}...") Path(pytorch_dump_folder_path).mkdir(exist_ok=True) model.save_pretrained(pytorch_dump_folder_path) - feature_extractor.save_pretrained(pytorch_dump_folder_path) + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: # Push model to HF hub @@ -292,7 +292,7 @@ def convert_table_transformer_checkpoint(checkpoint_url, pytorch_dump_folder_pat else "microsoft/table-transformer-structure-recognition" ) model.push_to_hub(model_name) - feature_extractor.push_to_hub(model_name) + image_processor.push_to_hub(model_name) if __name__ == "__main__": diff --git a/src/transformers/models/timesformer/convert_timesformer_to_pytorch.py b/src/transformers/models/timesformer/convert_timesformer_to_pytorch.py index 5a66776d43..ce4d13421f 100644 --- a/src/transformers/models/timesformer/convert_timesformer_to_pytorch.py +++ b/src/transformers/models/timesformer/convert_timesformer_to_pytorch.py @@ -22,7 +22,7 @@ import numpy as np import torch from huggingface_hub import hf_hub_download -from transformers import TimesformerConfig, TimesformerForVideoClassification, VideoMAEFeatureExtractor +from transformers import TimesformerConfig, TimesformerForVideoClassification, VideoMAEImageProcessor def get_timesformer_config(model_name): @@ -156,9 +156,9 @@ def convert_timesformer_checkpoint(checkpoint_url, pytorch_dump_folder_path, mod model.eval() # verify model on basic input - feature_extractor = VideoMAEFeatureExtractor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5]) + image_processor = VideoMAEImageProcessor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5]) video = prepare_video() - inputs = feature_extractor(video[:8], return_tensors="pt") + inputs = image_processor(video[:8], return_tensors="pt") outputs = model(**inputs) logits = outputs.logits @@ -215,8 +215,8 @@ def convert_timesformer_checkpoint(checkpoint_url, pytorch_dump_folder_path, mod print("Logits ok!") if pytorch_dump_folder_path is not None: - print(f"Saving model and feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving model and image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) model.save_pretrained(pytorch_dump_folder_path) if push_to_hub: diff --git a/src/transformers/models/timesformer/modeling_timesformer.py b/src/transformers/models/timesformer/modeling_timesformer.py index 9f886b6ece..ad5120ab57 100644 --- a/src/transformers/models/timesformer/modeling_timesformer.py +++ b/src/transformers/models/timesformer/modeling_timesformer.py @@ -513,8 +513,8 @@ TIMESFORMER_START_DOCSTRING = r""" TIMESFORMER_INPUTS_DOCSTRING = r""" Args: pixel_values (`torch.FloatTensor` of shape `(batch_size, num_frames, num_channels, height, width)`): - Pixel values. Pixel values can be obtained using [`AutoFeatureExtractor`]. See - [`VideoMAEFeatureExtractor.__call__`] for details. + Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See + [`VideoMAEImageProcessor.preprocess`] for details. output_attentions (`bool`, *optional*): Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned diff --git a/src/transformers/models/trocr/convert_trocr_unilm_to_pytorch.py b/src/transformers/models/trocr/convert_trocr_unilm_to_pytorch.py index 2629129681..b82adf690e 100644 --- a/src/transformers/models/trocr/convert_trocr_unilm_to_pytorch.py +++ b/src/transformers/models/trocr/convert_trocr_unilm_to_pytorch.py @@ -29,7 +29,7 @@ from transformers import ( TrOCRProcessor, VisionEncoderDecoderModel, ViTConfig, - ViTFeatureExtractor, + ViTImageProcessor, ViTModel, ) from transformers.utils import logging @@ -182,9 +182,9 @@ def convert_tr_ocr_checkpoint(checkpoint_url, pytorch_dump_folder_path): model.load_state_dict(state_dict) # Check outputs on an image - feature_extractor = ViTFeatureExtractor(size=encoder_config.image_size) + image_processor = ViTImageProcessor(size=encoder_config.image_size) tokenizer = RobertaTokenizer.from_pretrained("roberta-large") - processor = TrOCRProcessor(feature_extractor, tokenizer) + processor = TrOCRProcessor(image_processor, tokenizer) pixel_values = processor(images=prepare_img(checkpoint_url), return_tensors="pt").pixel_values diff --git a/src/transformers/models/van/convert_van_to_pytorch.py b/src/transformers/models/van/convert_van_to_pytorch.py index 0cb51e59e6..c9bbc0fc91 100644 --- a/src/transformers/models/van/convert_van_to_pytorch.py +++ b/src/transformers/models/van/convert_van_to_pytorch.py @@ -30,7 +30,7 @@ import torch.nn as nn from huggingface_hub import cached_download, hf_hub_download from torch import Tensor -from transformers import AutoFeatureExtractor, VanConfig, VanForImageClassification +from transformers import AutoImageProcessor, VanConfig, VanForImageClassification from transformers.models.van.modeling_van import VanLayerScaling from transformers.utils import logging @@ -154,10 +154,10 @@ def convert_weight_and_push( ) # we can use the convnext one - feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k-1k") - feature_extractor.push_to_hub( + image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-base-224-22k-1k") + image_processor.push_to_hub( repo_path_or_name=save_directory / checkpoint_name, - commit_message="Add feature extractor", + commit_message="Add image processor", use_temp_dir=True, ) @@ -277,7 +277,7 @@ if __name__ == "__main__": default=True, type=bool, required=False, - help="If True, push model and feature extractor to the hub.", + help="If True, push model and image processor to the hub.", ) args = parser.parse_args() diff --git a/src/transformers/models/videomae/convert_videomae_to_pytorch.py b/src/transformers/models/videomae/convert_videomae_to_pytorch.py index f0a058c42a..c98160a6bb 100644 --- a/src/transformers/models/videomae/convert_videomae_to_pytorch.py +++ b/src/transformers/models/videomae/convert_videomae_to_pytorch.py @@ -24,9 +24,9 @@ from huggingface_hub import hf_hub_download from transformers import ( VideoMAEConfig, - VideoMAEFeatureExtractor, VideoMAEForPreTraining, VideoMAEForVideoClassification, + VideoMAEImageProcessor, ) @@ -198,9 +198,9 @@ def convert_videomae_checkpoint(checkpoint_url, pytorch_dump_folder_path, model_ model.eval() # verify model on basic input - feature_extractor = VideoMAEFeatureExtractor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5]) + image_processor = VideoMAEImageProcessor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5]) video = prepare_video() - inputs = feature_extractor(video, return_tensors="pt") + inputs = image_processor(video, return_tensors="pt") if "finetuned" not in model_name: local_path = hf_hub_download(repo_id="hf-internal-testing/bool-masked-pos", filename="bool_masked_pos.pt") @@ -288,8 +288,8 @@ def convert_videomae_checkpoint(checkpoint_url, pytorch_dump_folder_path, model_ print("Loss ok!") if pytorch_dump_folder_path is not None: - print(f"Saving model and feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving model and image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) model.save_pretrained(pytorch_dump_folder_path) if push_to_hub: diff --git a/src/transformers/models/vilt/convert_vilt_original_to_pytorch.py b/src/transformers/models/vilt/convert_vilt_original_to_pytorch.py index 693ca34efc..015db07453 100644 --- a/src/transformers/models/vilt/convert_vilt_original_to_pytorch.py +++ b/src/transformers/models/vilt/convert_vilt_original_to_pytorch.py @@ -27,11 +27,11 @@ from PIL import Image from transformers import ( BertTokenizer, ViltConfig, - ViltFeatureExtractor, ViltForImageAndTextRetrieval, ViltForImagesAndTextClassification, ViltForMaskedLM, ViltForQuestionAnswering, + ViltImageProcessor, ViltProcessor, ) from transformers.utils import logging @@ -223,9 +223,9 @@ def convert_vilt_checkpoint(checkpoint_url, pytorch_dump_folder_path): model.load_state_dict(state_dict) # Define processor - feature_extractor = ViltFeatureExtractor(size=384) + image_processor = ViltImageProcessor(size=384) tokenizer = BertTokenizer.from_pretrained("bert-base-uncased") - processor = ViltProcessor(feature_extractor, tokenizer) + processor = ViltProcessor(image_processor, tokenizer) # Forward pass on example inputs (image + text) if nlvr_model: diff --git a/src/transformers/models/vit/convert_dino_to_pytorch.py b/src/transformers/models/vit/convert_dino_to_pytorch.py index ceedc2603a..7eec823ad5 100644 --- a/src/transformers/models/vit/convert_dino_to_pytorch.py +++ b/src/transformers/models/vit/convert_dino_to_pytorch.py @@ -24,7 +24,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import ViTConfig, ViTFeatureExtractor, ViTForImageClassification, ViTModel +from transformers import ViTConfig, ViTForImageClassification, ViTImageProcessor, ViTModel from transformers.utils import logging @@ -175,9 +175,9 @@ def convert_vit_checkpoint(model_name, pytorch_dump_folder_path, base_model=True model = ViTForImageClassification(config).eval() model.load_state_dict(state_dict) - # Check outputs on an image, prepared by ViTFeatureExtractor - feature_extractor = ViTFeatureExtractor() - encoding = feature_extractor(images=prepare_img(), return_tensors="pt") + # Check outputs on an image, prepared by ViTImageProcessor + image_processor = ViTImageProcessor() + encoding = image_processor(images=prepare_img(), return_tensors="pt") pixel_values = encoding["pixel_values"] outputs = model(pixel_values) @@ -192,8 +192,8 @@ def convert_vit_checkpoint(model_name, pytorch_dump_folder_path, base_model=True Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model {model_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/vit/convert_vit_timm_to_pytorch.py b/src/transformers/models/vit/convert_vit_timm_to_pytorch.py index 718e8624cc..b73c5f346d 100644 --- a/src/transformers/models/vit/convert_vit_timm_to_pytorch.py +++ b/src/transformers/models/vit/convert_vit_timm_to_pytorch.py @@ -25,7 +25,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import DeiTFeatureExtractor, ViTConfig, ViTFeatureExtractor, ViTForImageClassification, ViTModel +from transformers import DeiTImageProcessor, ViTConfig, ViTForImageClassification, ViTImageProcessor, ViTModel from transformers.utils import logging @@ -208,12 +208,12 @@ def convert_vit_checkpoint(vit_name, pytorch_dump_folder_path): model = ViTForImageClassification(config).eval() model.load_state_dict(state_dict) - # Check outputs on an image, prepared by ViTFeatureExtractor/DeiTFeatureExtractor + # Check outputs on an image, prepared by ViTImageProcessor/DeiTImageProcessor if "deit" in vit_name: - feature_extractor = DeiTFeatureExtractor(size=config.image_size) + image_processor = DeiTImageProcessor(size=config.image_size) else: - feature_extractor = ViTFeatureExtractor(size=config.image_size) - encoding = feature_extractor(images=prepare_img(), return_tensors="pt") + image_processor = ViTImageProcessor(size=config.image_size) + encoding = image_processor(images=prepare_img(), return_tensors="pt") pixel_values = encoding["pixel_values"] outputs = model(pixel_values) @@ -229,8 +229,8 @@ def convert_vit_checkpoint(vit_name, pytorch_dump_folder_path): Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model {vit_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/vit_mae/convert_vit_mae_to_pytorch.py b/src/transformers/models/vit_mae/convert_vit_mae_to_pytorch.py index fc61d8924c..47e77593f6 100644 --- a/src/transformers/models/vit_mae/convert_vit_mae_to_pytorch.py +++ b/src/transformers/models/vit_mae/convert_vit_mae_to_pytorch.py @@ -20,7 +20,7 @@ import requests import torch from PIL import Image -from transformers import ViTMAEConfig, ViTMAEFeatureExtractor, ViTMAEForPreTraining +from transformers import ViTMAEConfig, ViTMAEForPreTraining, ViTMAEImageProcessor def rename_key(name): @@ -120,7 +120,7 @@ def convert_vit_mae_checkpoint(checkpoint_url, pytorch_dump_folder_path): state_dict = torch.hub.load_state_dict_from_url(checkpoint_url, map_location="cpu")["model"] - feature_extractor = ViTMAEFeatureExtractor(size=config.image_size) + image_processor = ViTMAEImageProcessor(size=config.image_size) new_state_dict = convert_state_dict(state_dict, config) @@ -130,8 +130,8 @@ def convert_vit_mae_checkpoint(checkpoint_url, pytorch_dump_folder_path): url = "https://user-images.githubusercontent.com/11435359/147738734-196fd92f-9260-48d5-ba7e-bf103d29364d.jpg" image = Image.open(requests.get(url, stream=True).raw) - feature_extractor = ViTMAEFeatureExtractor(size=config.image_size) - inputs = feature_extractor(images=image, return_tensors="pt") + image_processor = ViTMAEImageProcessor(size=config.image_size) + inputs = image_processor(images=image, return_tensors="pt") # forward pass torch.manual_seed(2) @@ -157,8 +157,8 @@ def convert_vit_mae_checkpoint(checkpoint_url, pytorch_dump_folder_path): print(f"Saving model to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/vit_msn/convert_msn_to_pytorch.py b/src/transformers/models/vit_msn/convert_msn_to_pytorch.py index 482073a4fa..899c74f183 100644 --- a/src/transformers/models/vit_msn/convert_msn_to_pytorch.py +++ b/src/transformers/models/vit_msn/convert_msn_to_pytorch.py @@ -22,7 +22,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import ViTFeatureExtractor, ViTMSNConfig, ViTMSNModel +from transformers import ViTImageProcessor, ViTMSNConfig, ViTMSNModel from transformers.image_utils import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD @@ -180,7 +180,7 @@ def convert_vit_msn_checkpoint(checkpoint_url, pytorch_dump_folder_path): state_dict = torch.hub.load_state_dict_from_url(checkpoint_url, map_location="cpu")["target_encoder"] - feature_extractor = ViTFeatureExtractor(size=config.image_size) + image_processor = ViTImageProcessor(size=config.image_size) remove_projection_head(state_dict) rename_keys = create_rename_keys(config, base_model=True) @@ -195,10 +195,10 @@ def convert_vit_msn_checkpoint(checkpoint_url, pytorch_dump_folder_path): url = "http://images.cocodataset.org/val2017/000000039769.jpg" image = Image.open(requests.get(url, stream=True).raw) - feature_extractor = ViTFeatureExtractor( + image_processor = ViTImageProcessor( size=config.image_size, image_mean=IMAGENET_DEFAULT_MEAN, image_std=IMAGENET_DEFAULT_STD ) - inputs = feature_extractor(images=image, return_tensors="pt") + inputs = image_processor(images=image, return_tensors="pt") # forward pass torch.manual_seed(2) @@ -224,8 +224,8 @@ def convert_vit_msn_checkpoint(checkpoint_url, pytorch_dump_folder_path): print(f"Saving model to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if __name__ == "__main__": diff --git a/src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py b/src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py index d4281fe849..8ff878f2cc 100644 --- a/src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py +++ b/src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py @@ -23,7 +23,7 @@ from huggingface_hub import hf_hub_download from transformers import ( CLIPTokenizer, CLIPTokenizerFast, - VideoMAEFeatureExtractor, + VideoMAEImageProcessor, XCLIPConfig, XCLIPModel, XCLIPProcessor, @@ -291,10 +291,10 @@ def convert_xclip_checkpoint(model_name, pytorch_dump_folder_path=None, push_to_ model.eval() size = 336 if model_name == "xclip-large-patch14-16-frames" else 224 - feature_extractor = VideoMAEFeatureExtractor(size=size) + image_processor = VideoMAEImageProcessor(size=size) slow_tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32") fast_tokenizer = CLIPTokenizerFast.from_pretrained("openai/clip-vit-base-patch32") - processor = XCLIPProcessor(feature_extractor=feature_extractor, tokenizer=fast_tokenizer) + processor = XCLIPProcessor(image_processor=image_processor, tokenizer=fast_tokenizer) video = prepare_video(num_frames) inputs = processor( diff --git a/src/transformers/models/yolos/convert_yolos_to_pytorch.py b/src/transformers/models/yolos/convert_yolos_to_pytorch.py index 0227951883..35238151ab 100644 --- a/src/transformers/models/yolos/convert_yolos_to_pytorch.py +++ b/src/transformers/models/yolos/convert_yolos_to_pytorch.py @@ -24,7 +24,7 @@ import torch from huggingface_hub import hf_hub_download from PIL import Image -from transformers import YolosConfig, YolosFeatureExtractor, YolosForObjectDetection +from transformers import YolosConfig, YolosForObjectDetection, YolosImageProcessor from transformers.utils import logging @@ -172,10 +172,10 @@ def convert_yolos_checkpoint( new_state_dict = convert_state_dict(state_dict, model) model.load_state_dict(new_state_dict) - # Check outputs on an image, prepared by YolosFeatureExtractor + # Check outputs on an image, prepared by YolosImageProcessor size = 800 if yolos_name != "yolos_ti" else 512 - feature_extractor = YolosFeatureExtractor(format="coco_detection", size=size) - encoding = feature_extractor(images=prepare_img(), return_tensors="pt") + image_processor = YolosImageProcessor(format="coco_detection", size=size) + encoding = image_processor(images=prepare_img(), return_tensors="pt") outputs = model(**encoding) logits, pred_boxes = outputs.logits, outputs.pred_boxes @@ -224,8 +224,8 @@ def convert_yolos_checkpoint( Path(pytorch_dump_folder_path).mkdir(exist_ok=True) print(f"Saving model {yolos_name} to {pytorch_dump_folder_path}") model.save_pretrained(pytorch_dump_folder_path) - print(f"Saving feature extractor to {pytorch_dump_folder_path}") - feature_extractor.save_pretrained(pytorch_dump_folder_path) + print(f"Saving image processor to {pytorch_dump_folder_path}") + image_processor.save_pretrained(pytorch_dump_folder_path) if push_to_hub: model_mapping = { @@ -238,7 +238,7 @@ def convert_yolos_checkpoint( print("Pushing to the hub...") model_name = model_mapping[yolos_name] - feature_extractor.push_to_hub(model_name, organization="hustvl") + image_processor.push_to_hub(model_name, organization="hustvl") model.push_to_hub(model_name, organization="hustvl") diff --git a/src/transformers/onnx/__main__.py b/src/transformers/onnx/__main__.py index 1a0cdb68b1..92dba71ed7 100644 --- a/src/transformers/onnx/__main__.py +++ b/src/transformers/onnx/__main__.py @@ -19,7 +19,7 @@ from pathlib import Path from packaging import version -from .. import AutoFeatureExtractor, AutoProcessor, AutoTokenizer +from .. import AutoFeatureExtractor, AutoImageProcessor, AutoProcessor, AutoTokenizer from ..utils import logging from ..utils.import_utils import is_optimum_available from .convert import export, validate_model_outputs @@ -145,6 +145,8 @@ def export_with_transformers(args): preprocessor = get_preprocessor(args.model) elif args.preprocessor == "tokenizer": preprocessor = AutoTokenizer.from_pretrained(args.model) + elif args.preprocessor == "image_processor": + preprocessor = AutoImageProcessor.from_pretrained(args.model) elif args.preprocessor == "feature_extractor": preprocessor = AutoFeatureExtractor.from_pretrained(args.model) elif args.preprocessor == "processor": @@ -213,7 +215,7 @@ def main(): parser.add_argument( "--preprocessor", type=str, - choices=["auto", "tokenizer", "feature_extractor", "processor"], + choices=["auto", "tokenizer", "feature_extractor", "image_processor", "processor"], default="auto", help="Which type of preprocessor to use. 'auto' tries to automatically detect it.", ) diff --git a/tests/models/beit/test_modeling_beit.py b/tests/models/beit/test_modeling_beit.py index f9aa7339f7..4c0e5e5a45 100644 --- a/tests/models/beit/test_modeling_beit.py +++ b/tests/models/beit/test_modeling_beit.py @@ -49,7 +49,7 @@ if is_vision_available(): import PIL from PIL import Image - from transformers import BeitFeatureExtractor + from transformers import BeitImageProcessor class BeitModelTester: @@ -342,18 +342,16 @@ def prepare_img(): @require_vision class BeitModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ( - BeitFeatureExtractor.from_pretrained("microsoft/beit-base-patch16-224") if is_vision_available() else None - ) + def default_image_processor(self): + return BeitImageProcessor.from_pretrained("microsoft/beit-base-patch16-224") if is_vision_available() else None @slow def test_inference_masked_image_modeling_head(self): model = BeitForMaskedImageModeling.from_pretrained("microsoft/beit-base-patch16-224-pt22k").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values.to(torch_device) + pixel_values = image_processor(images=image, return_tensors="pt").pixel_values.to(torch_device) # prepare bool_masked_pos bool_masked_pos = torch.ones((1, 196), dtype=torch.bool).to(torch_device) @@ -377,9 +375,9 @@ class BeitModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head_imagenet_1k(self): model = BeitForImageClassification.from_pretrained("microsoft/beit-base-patch16-224").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -403,9 +401,9 @@ class BeitModelIntegrationTest(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -428,11 +426,11 @@ class BeitModelIntegrationTest(unittest.TestCase): model = BeitForSemanticSegmentation.from_pretrained("microsoft/beit-base-finetuned-ade-640-640") model = model.to(torch_device) - feature_extractor = BeitFeatureExtractor(do_resize=True, size=640, do_center_crop=False) + image_processor = BeitImageProcessor(do_resize=True, size=640, do_center_crop=False) ds = load_dataset("hf-internal-testing/fixtures_ade20k", split="test") image = Image.open(ds[0]["file"]) - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -471,11 +469,11 @@ class BeitModelIntegrationTest(unittest.TestCase): model = BeitForSemanticSegmentation.from_pretrained("microsoft/beit-base-finetuned-ade-640-640") model = model.to(torch_device) - feature_extractor = BeitFeatureExtractor(do_resize=True, size=640, do_center_crop=False) + image_processor = BeitImageProcessor(do_resize=True, size=640, do_center_crop=False) ds = load_dataset("hf-internal-testing/fixtures_ade20k", split="test") image = Image.open(ds[0]["file"]) - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -483,10 +481,10 @@ class BeitModelIntegrationTest(unittest.TestCase): outputs.logits = outputs.logits.detach().cpu() - segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(500, 300)]) + segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(500, 300)]) expected_shape = torch.Size((500, 300)) self.assertEqual(segmentation[0].shape, expected_shape) - segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs) + segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs) expected_shape = torch.Size((160, 160)) self.assertEqual(segmentation[0].shape, expected_shape) diff --git a/tests/models/beit/test_modeling_flax_beit.py b/tests/models/beit/test_modeling_flax_beit.py index 75c58aec47..0587174bac 100644 --- a/tests/models/beit/test_modeling_flax_beit.py +++ b/tests/models/beit/test_modeling_flax_beit.py @@ -33,7 +33,7 @@ if is_flax_available(): if is_vision_available(): from PIL import Image - from transformers import BeitFeatureExtractor + from transformers import BeitImageProcessor class FlaxBeitModelTester(unittest.TestCase): @@ -219,18 +219,16 @@ def prepare_img(): @require_flax class FlaxBeitModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ( - BeitFeatureExtractor.from_pretrained("microsoft/beit-base-patch16-224") if is_vision_available() else None - ) + def default_image_processor(self): + return BeitImageProcessor.from_pretrained("microsoft/beit-base-patch16-224") if is_vision_available() else None @slow def test_inference_masked_image_modeling_head(self): model = FlaxBeitForMaskedImageModeling.from_pretrained("microsoft/beit-base-patch16-224-pt22k") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - pixel_values = feature_extractor(images=image, return_tensors="np").pixel_values + pixel_values = image_processor(images=image, return_tensors="np").pixel_values # prepare bool_masked_pos bool_masked_pos = np.ones((1, 196), dtype=bool) @@ -253,9 +251,9 @@ class FlaxBeitModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head_imagenet_1k(self): model = FlaxBeitForImageClassification.from_pretrained("microsoft/beit-base-patch16-224") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="np") + inputs = image_processor(images=image, return_tensors="np") # forward pass outputs = model(**inputs) @@ -276,9 +274,9 @@ class FlaxBeitModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head_imagenet_22k(self): model = FlaxBeitForImageClassification.from_pretrained("microsoft/beit-large-patch16-224-pt22k-ft22k") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="np") + inputs = image_processor(images=image, return_tensors="np") # forward pass outputs = model(**inputs) diff --git a/tests/models/bit/test_modeling_bit.py b/tests/models/bit/test_modeling_bit.py index cec997e594..d7d2c60347 100644 --- a/tests/models/bit/test_modeling_bit.py +++ b/tests/models/bit/test_modeling_bit.py @@ -297,7 +297,7 @@ def prepare_img(): @require_vision class BitModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( BitImageProcessor.from_pretrained(BIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) if is_vision_available() else None ) @@ -306,9 +306,9 @@ class BitModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head(self): model = BitForImageClassification.from_pretrained(BIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/bridgetower/test_image_processing_bridgetower.py b/tests/models/bridgetower/test_image_processing_bridgetower.py index fe84227bad..9a9bff9fc3 100644 --- a/tests/models/bridgetower/test_image_processing_bridgetower.py +++ b/tests/models/bridgetower/test_image_processing_bridgetower.py @@ -145,7 +145,7 @@ class BridgeTowerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te pass def test_call_pil(self): - # Initialize feature_extractor + # Initialize image processor image_processing = self.image_processing_class(**self.image_processor_dict) # create random PIL images image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False) @@ -176,7 +176,7 @@ class BridgeTowerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te ) def test_call_numpy(self): - # Initialize feature_extractor + # Initialize image processor image_processing = self.image_processing_class(**self.image_processor_dict) # create random numpy tensors image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False, numpify=True) @@ -207,7 +207,7 @@ class BridgeTowerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te ) def test_call_pytorch(self): - # Initialize feature_extractor + # Initialize image processor image_processing = self.image_processing_class(**self.image_processor_dict) # create random PyTorch tensors image_inputs = prepare_image_inputs(self.image_processor_tester, equal_resolution=False, torchify=True) @@ -238,7 +238,7 @@ class BridgeTowerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te ) def test_equivalence_pad_and_create_pixel_mask(self): - # Initialize feature_extractors + # Initialize image processors image_processing_1 = self.image_processing_class(**self.image_processor_dict) image_processing_2 = self.image_processing_class(do_resize=False, do_normalize=False, do_rescale=False) # create random PyTorch tensors diff --git a/tests/models/conditional_detr/test_modeling_conditional_detr.py b/tests/models/conditional_detr/test_modeling_conditional_detr.py index 11a548df92..e1827f0213 100644 --- a/tests/models/conditional_detr/test_modeling_conditional_detr.py +++ b/tests/models/conditional_detr/test_modeling_conditional_detr.py @@ -43,7 +43,7 @@ if is_timm_available(): if is_vision_available(): from PIL import Image - from transformers import ConditionalDetrFeatureExtractor + from transformers import ConditionalDetrImageProcessor class ConditionalDetrModelTester: @@ -493,9 +493,9 @@ def prepare_img(): @slow class ConditionalDetrModelIntegrationTests(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - ConditionalDetrFeatureExtractor.from_pretrained("microsoft/conditional-detr-resnet-50") + ConditionalDetrImageProcessor.from_pretrained("microsoft/conditional-detr-resnet-50") if is_vision_available() else None ) @@ -503,9 +503,9 @@ class ConditionalDetrModelIntegrationTests(unittest.TestCase): def test_inference_no_head(self): model = ConditionalDetrModel.from_pretrained("microsoft/conditional-detr-resnet-50").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device) + encoding = image_processor(images=image, return_tensors="pt").to(torch_device) with torch.no_grad(): outputs = model(**encoding) @@ -522,9 +522,9 @@ class ConditionalDetrModelIntegrationTests(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device) + encoding = image_processor(images=image, return_tensors="pt").to(torch_device) pixel_values = encoding["pixel_values"].to(torch_device) pixel_mask = encoding["pixel_mask"].to(torch_device) @@ -547,7 +547,7 @@ class ConditionalDetrModelIntegrationTests(unittest.TestCase): self.assertTrue(torch.allclose(outputs.pred_boxes[0, :3, :3], expected_slice_boxes, atol=1e-4)) # verify postprocessing - results = feature_extractor.post_process_object_detection( + results = image_processor.post_process_object_detection( outputs, threshold=0.3, target_sizes=[image.size[::-1]] )[0] expected_scores = torch.tensor([0.8330, 0.8313, 0.8039, 0.6829, 0.5355]).to(torch_device) diff --git a/tests/models/convnext/test_modeling_convnext.py b/tests/models/convnext/test_modeling_convnext.py index 16d57d7e96..397fa596f1 100644 --- a/tests/models/convnext/test_modeling_convnext.py +++ b/tests/models/convnext/test_modeling_convnext.py @@ -38,7 +38,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class ConvNextModelTester: @@ -285,16 +285,16 @@ def prepare_img(): @require_vision class ConvNextModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return AutoFeatureExtractor.from_pretrained("facebook/convnext-tiny-224") if is_vision_available() else None + def default_image_processor(self): + return AutoImageProcessor.from_pretrained("facebook/convnext-tiny-224") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = ConvNextForImageClassification.from_pretrained("facebook/convnext-tiny-224").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/convnext/test_modeling_tf_convnext.py b/tests/models/convnext/test_modeling_tf_convnext.py index a508e038df..4a06632513 100644 --- a/tests/models/convnext/test_modeling_tf_convnext.py +++ b/tests/models/convnext/test_modeling_tf_convnext.py @@ -38,7 +38,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import ConvNextFeatureExtractor + from transformers import ConvNextImageProcessor class TFConvNextModelTester: @@ -279,18 +279,16 @@ def prepare_img(): @require_vision class TFConvNextModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ( - ConvNextFeatureExtractor.from_pretrained("facebook/convnext-tiny-224") if is_vision_available() else None - ) + def default_image_processor(self): + return ConvNextImageProcessor.from_pretrained("facebook/convnext-tiny-224") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = TFConvNextForImageClassification.from_pretrained("facebook/convnext-tiny-224") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(**inputs) diff --git a/tests/models/cvt/test_modeling_cvt.py b/tests/models/cvt/test_modeling_cvt.py index 35ecf50217..e7fc756ea8 100644 --- a/tests/models/cvt/test_modeling_cvt.py +++ b/tests/models/cvt/test_modeling_cvt.py @@ -38,7 +38,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class CvtConfigTester(ConfigTester): @@ -264,16 +264,16 @@ def prepare_img(): @require_vision class CvtModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return AutoFeatureExtractor.from_pretrained(CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + def default_image_processor(self): + return AutoImageProcessor.from_pretrained(CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) @slow def test_inference_image_classification_head(self): model = CvtForImageClassification.from_pretrained(CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/cvt/test_modeling_tf_cvt.py b/tests/models/cvt/test_modeling_tf_cvt.py index 2a42732e67..d1d5835d7b 100644 --- a/tests/models/cvt/test_modeling_tf_cvt.py +++ b/tests/models/cvt/test_modeling_tf_cvt.py @@ -28,7 +28,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class TFCvtConfigTester(ConfigTester): @@ -265,16 +265,16 @@ def prepare_img(): @require_vision class TFCvtModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return AutoFeatureExtractor.from_pretrained(TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + def default_image_processor(self): + return AutoImageProcessor.from_pretrained(TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) @slow def test_inference_image_classification_head(self): model = TFCvtForImageClassification.from_pretrained(TF_CVT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(**inputs) diff --git a/tests/models/data2vec/test_modeling_data2vec_vision.py b/tests/models/data2vec/test_modeling_data2vec_vision.py index b4c391fea1..299ffad3e7 100644 --- a/tests/models/data2vec/test_modeling_data2vec_vision.py +++ b/tests/models/data2vec/test_modeling_data2vec_vision.py @@ -44,7 +44,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import BeitFeatureExtractor + from transformers import BeitImageProcessor class Data2VecVisionModelTester: @@ -327,11 +327,9 @@ def prepare_img(): @require_vision class Data2VecVisionModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - BeitFeatureExtractor.from_pretrained("facebook/data2vec-vision-base-ft1k") - if is_vision_available() - else None + BeitImageProcessor.from_pretrained("facebook/data2vec-vision-base-ft1k") if is_vision_available() else None ) @slow @@ -340,9 +338,9 @@ class Data2VecVisionModelIntegrationTest(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/data2vec/test_modeling_tf_data2vec_vision.py b/tests/models/data2vec/test_modeling_tf_data2vec_vision.py index b3f2eec8fb..9e3701c17a 100644 --- a/tests/models/data2vec/test_modeling_tf_data2vec_vision.py +++ b/tests/models/data2vec/test_modeling_tf_data2vec_vision.py @@ -46,7 +46,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import BeitFeatureExtractor + from transformers import BeitImageProcessor class TFData2VecVisionModelTester: @@ -469,20 +469,18 @@ def prepare_img(): @require_vision class TFData2VecVisionModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - BeitFeatureExtractor.from_pretrained("facebook/data2vec-vision-base-ft1k") - if is_vision_available() - else None + BeitImageProcessor.from_pretrained("facebook/data2vec-vision-base-ft1k") if is_vision_available() else None ) @slow def test_inference_image_classification_head_imagenet_1k(self): model = TFData2VecVisionForImageClassification.from_pretrained("facebook/data2vec-vision-base-ft1k") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(**inputs) diff --git a/tests/models/deformable_detr/test_modeling_deformable_detr.py b/tests/models/deformable_detr/test_modeling_deformable_detr.py index 3c7c2f640a..180f57f042 100644 --- a/tests/models/deformable_detr/test_modeling_deformable_detr.py +++ b/tests/models/deformable_detr/test_modeling_deformable_detr.py @@ -39,7 +39,7 @@ if is_timm_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class DeformableDetrModelTester: @@ -563,15 +563,15 @@ def prepare_img(): @slow class DeformableDetrModelIntegrationTests(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return AutoFeatureExtractor.from_pretrained("SenseTime/deformable-detr") if is_vision_available() else None + def default_image_processor(self): + return AutoImageProcessor.from_pretrained("SenseTime/deformable-detr") if is_vision_available() else None def test_inference_object_detection_head(self): model = DeformableDetrForObjectDetection.from_pretrained("SenseTime/deformable-detr").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device) + encoding = image_processor(images=image, return_tensors="pt").to(torch_device) pixel_values = encoding["pixel_values"].to(torch_device) pixel_mask = encoding["pixel_mask"].to(torch_device) @@ -595,7 +595,7 @@ class DeformableDetrModelIntegrationTests(unittest.TestCase): self.assertTrue(torch.allclose(outputs.pred_boxes[0, :3, :3], expected_boxes, atol=1e-4)) # verify postprocessing - results = feature_extractor.post_process_object_detection( + results = image_processor.post_process_object_detection( outputs, threshold=0.3, target_sizes=[image.size[::-1]] )[0] expected_scores = torch.tensor([0.7999, 0.7894, 0.6331, 0.4720, 0.4382]).to(torch_device) @@ -612,9 +612,9 @@ class DeformableDetrModelIntegrationTests(unittest.TestCase): "SenseTime/deformable-detr-with-box-refine-two-stage" ).to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device) + encoding = image_processor(images=image, return_tensors="pt").to(torch_device) pixel_values = encoding["pixel_values"].to(torch_device) pixel_mask = encoding["pixel_mask"].to(torch_device) @@ -639,9 +639,9 @@ class DeformableDetrModelIntegrationTests(unittest.TestCase): @require_torch_gpu def test_inference_object_detection_head_equivalence_cpu_gpu(self): - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt") + encoding = image_processor(images=image, return_tensors="pt") pixel_values = encoding["pixel_values"] pixel_mask = encoding["pixel_mask"] diff --git a/tests/models/deit/test_modeling_deit.py b/tests/models/deit/test_modeling_deit.py index 1564b23aa6..37bfe3fa70 100644 --- a/tests/models/deit/test_modeling_deit.py +++ b/tests/models/deit/test_modeling_deit.py @@ -55,7 +55,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import DeiTFeatureExtractor + from transformers import DeiTImageProcessor class DeiTModelTester: @@ -381,9 +381,9 @@ def prepare_img(): @require_vision class DeiTModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224") + DeiTImageProcessor.from_pretrained("facebook/deit-base-distilled-patch16-224") if is_vision_available() else None ) @@ -394,9 +394,9 @@ class DeiTModelIntegrationTest(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -420,10 +420,10 @@ class DeiTModelIntegrationTest(unittest.TestCase): model = DeiTModel.from_pretrained( "facebook/deit-base-distilled-patch16-224", torch_dtype=torch.float16, device_map="auto" ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt") + inputs = image_processor(images=image, return_tensors="pt") pixel_values = inputs.pixel_values.to(torch_device) # forward pass to make sure inference works in fp16 diff --git a/tests/models/deit/test_modeling_tf_deit.py b/tests/models/deit/test_modeling_tf_deit.py index b350a5d546..3987b11d19 100644 --- a/tests/models/deit/test_modeling_tf_deit.py +++ b/tests/models/deit/test_modeling_tf_deit.py @@ -46,7 +46,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import DeiTFeatureExtractor + from transformers import DeiTImageProcessor class TFDeiTModelTester: @@ -266,9 +266,9 @@ def prepare_img(): @require_vision class DeiTModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224") + DeiTImageProcessor.from_pretrained("facebook/deit-base-distilled-patch16-224") if is_vision_available() else None ) @@ -277,9 +277,9 @@ class DeiTModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head(self): model = TFDeiTForImageClassificationWithTeacher.from_pretrained("facebook/deit-base-distilled-patch16-224") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(**inputs) diff --git a/tests/models/detr/test_modeling_detr.py b/tests/models/detr/test_modeling_detr.py index 31d3db444c..f993a96dcb 100644 --- a/tests/models/detr/test_modeling_detr.py +++ b/tests/models/detr/test_modeling_detr.py @@ -38,7 +38,7 @@ if is_timm_available(): if is_vision_available(): from PIL import Image - from transformers import DetrFeatureExtractor + from transformers import DetrImageProcessor class DetrModelTester: @@ -512,15 +512,15 @@ def prepare_img(): @slow class DetrModelIntegrationTestsTimmBackbone(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return DetrFeatureExtractor.from_pretrained("facebook/detr-resnet-50") if is_vision_available() else None + def default_image_processor(self): + return DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") if is_vision_available() else None def test_inference_no_head(self): model = DetrModel.from_pretrained("facebook/detr-resnet-50").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device) + encoding = image_processor(images=image, return_tensors="pt").to(torch_device) with torch.no_grad(): outputs = model(**encoding) @@ -535,9 +535,9 @@ class DetrModelIntegrationTestsTimmBackbone(unittest.TestCase): def test_inference_object_detection_head(self): model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device) + encoding = image_processor(images=image, return_tensors="pt").to(torch_device) pixel_values = encoding["pixel_values"].to(torch_device) pixel_mask = encoding["pixel_mask"].to(torch_device) @@ -560,7 +560,7 @@ class DetrModelIntegrationTestsTimmBackbone(unittest.TestCase): self.assertTrue(torch.allclose(outputs.pred_boxes[0, :3, :3], expected_slice_boxes, atol=1e-4)) # verify postprocessing - results = feature_extractor.post_process_object_detection( + results = image_processor.post_process_object_detection( outputs, threshold=0.3, target_sizes=[image.size[::-1]] )[0] expected_scores = torch.tensor([0.9982, 0.9960, 0.9955, 0.9988, 0.9987]).to(torch_device) @@ -575,9 +575,9 @@ class DetrModelIntegrationTestsTimmBackbone(unittest.TestCase): def test_inference_panoptic_segmentation_head(self): model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50-panoptic").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device) + encoding = image_processor(images=image, return_tensors="pt").to(torch_device) pixel_values = encoding["pixel_values"].to(torch_device) pixel_mask = encoding["pixel_mask"].to(torch_device) @@ -607,7 +607,7 @@ class DetrModelIntegrationTestsTimmBackbone(unittest.TestCase): self.assertTrue(torch.allclose(outputs.pred_masks[0, 0, :3, :3], expected_slice_masks, atol=1e-3)) # verify postprocessing - results = feature_extractor.post_process_panoptic_segmentation( + results = image_processor.post_process_panoptic_segmentation( outputs, threshold=0.3, target_sizes=[image.size[::-1]] )[0] @@ -633,9 +633,9 @@ class DetrModelIntegrationTestsTimmBackbone(unittest.TestCase): @slow class DetrModelIntegrationTests(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - DetrFeatureExtractor.from_pretrained("facebook/detr-resnet-50", revision="no_timm") + DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm") if is_vision_available() else None ) @@ -643,9 +643,9 @@ class DetrModelIntegrationTests(unittest.TestCase): def test_inference_no_head(self): model = DetrModel.from_pretrained("facebook/detr-resnet-50", revision="no_timm").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - encoding = feature_extractor(images=image, return_tensors="pt").to(torch_device) + encoding = image_processor(images=image, return_tensors="pt").to(torch_device) with torch.no_grad(): outputs = model(**encoding) diff --git a/tests/models/dinat/test_modeling_dinat.py b/tests/models/dinat/test_modeling_dinat.py index c08abf3d12..a7e0b7d065 100644 --- a/tests/models/dinat/test_modeling_dinat.py +++ b/tests/models/dinat/test_modeling_dinat.py @@ -367,16 +367,16 @@ class DinatModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @require_torch class DinatModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return AutoImageProcessor.from_pretrained("shi-labs/dinat-mini-in1k-224") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = DinatForImageClassification.from_pretrained("shi-labs/dinat-mini-in1k-224").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png") - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/dit/test_modeling_dit.py b/tests/models/dit/test_modeling_dit.py index e7e1474f17..1804afdf82 100644 --- a/tests/models/dit/test_modeling_dit.py +++ b/tests/models/dit/test_modeling_dit.py @@ -25,7 +25,7 @@ if is_torch_available(): from transformers import AutoModelForImageClassification if is_vision_available(): - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor @require_torch @@ -33,7 +33,7 @@ if is_vision_available(): class DiTIntegrationTest(unittest.TestCase): @slow def test_for_image_classification(self): - feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/dit-base-finetuned-rvlcdip") + image_processor = AutoImageProcessor.from_pretrained("microsoft/dit-base-finetuned-rvlcdip") model = AutoModelForImageClassification.from_pretrained("microsoft/dit-base-finetuned-rvlcdip") model.to(torch_device) @@ -43,7 +43,7 @@ class DiTIntegrationTest(unittest.TestCase): image = dataset["train"][0]["image"].convert("RGB") - inputs = feature_extractor(image, return_tensors="pt").to(torch_device) + inputs = image_processor(image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/dpt/test_modeling_dpt.py b/tests/models/dpt/test_modeling_dpt.py index 76790ee795..31e6cf221d 100644 --- a/tests/models/dpt/test_modeling_dpt.py +++ b/tests/models/dpt/test_modeling_dpt.py @@ -39,7 +39,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import DPTFeatureExtractor + from transformers import DPTImageProcessor class DPTModelTester: @@ -293,11 +293,11 @@ def prepare_img(): @slow class DPTModelIntegrationTest(unittest.TestCase): def test_inference_depth_estimation(self): - feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-large") + image_processor = DPTImageProcessor.from_pretrained("Intel/dpt-large") model = DPTForDepthEstimation.from_pretrained("Intel/dpt-large").to(torch_device) image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -315,11 +315,11 @@ class DPTModelIntegrationTest(unittest.TestCase): self.assertTrue(torch.allclose(outputs.predicted_depth[0, :3, :3], expected_slice, atol=1e-4)) def test_inference_semantic_segmentation(self): - feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-large-ade") + image_processor = DPTImageProcessor.from_pretrained("Intel/dpt-large-ade") model = DPTForSemanticSegmentation.from_pretrained("Intel/dpt-large-ade").to(torch_device) image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -336,11 +336,11 @@ class DPTModelIntegrationTest(unittest.TestCase): self.assertTrue(torch.allclose(outputs.logits[0, 0, :3, :3], expected_slice, atol=1e-4)) def test_post_processing_semantic_segmentation(self): - feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-large-ade") + image_processor = DPTImageProcessor.from_pretrained("Intel/dpt-large-ade") model = DPTForSemanticSegmentation.from_pretrained("Intel/dpt-large-ade").to(torch_device) image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -348,10 +348,10 @@ class DPTModelIntegrationTest(unittest.TestCase): outputs.logits = outputs.logits.detach().cpu() - segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(500, 300)]) + segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(500, 300)]) expected_shape = torch.Size((500, 300)) self.assertEqual(segmentation[0].shape, expected_shape) - segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs) + segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs) expected_shape = torch.Size((480, 480)) self.assertEqual(segmentation[0].shape, expected_shape) diff --git a/tests/models/dpt/test_modeling_dpt_hybrid.py b/tests/models/dpt/test_modeling_dpt_hybrid.py index 6d4a75c80d..68d600f33f 100644 --- a/tests/models/dpt/test_modeling_dpt_hybrid.py +++ b/tests/models/dpt/test_modeling_dpt_hybrid.py @@ -39,7 +39,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import DPTFeatureExtractor + from transformers import DPTImageProcessor class DPTModelTester: @@ -314,11 +314,11 @@ def prepare_img(): @slow class DPTModelIntegrationTest(unittest.TestCase): def test_inference_depth_estimation(self): - feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-hybrid-midas") + image_processor = DPTImageProcessor.from_pretrained("Intel/dpt-hybrid-midas") model = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to(torch_device) image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/efficientformer/test_modeling_efficientformer.py b/tests/models/efficientformer/test_modeling_efficientformer.py index 2d951e4e5b..2774a210da 100644 --- a/tests/models/efficientformer/test_modeling_efficientformer.py +++ b/tests/models/efficientformer/test_modeling_efficientformer.py @@ -444,7 +444,7 @@ def prepare_img(): @require_vision class EfficientFormerModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( EfficientFormerImageProcessor.from_pretrained("snap-research/efficientformer-l1-300") if is_vision_available() @@ -457,9 +457,9 @@ class EfficientFormerModelIntegrationTest(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -478,9 +478,9 @@ class EfficientFormerModelIntegrationTest(unittest.TestCase): "snap-research/efficientformer-l1-300" ).to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/glpn/test_modeling_glpn.py b/tests/models/glpn/test_modeling_glpn.py index bf279de9df..60e29b739f 100644 --- a/tests/models/glpn/test_modeling_glpn.py +++ b/tests/models/glpn/test_modeling_glpn.py @@ -37,7 +37,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import GLPNFeatureExtractor + from transformers import GLPNImageProcessor class GLPNConfigTester(ConfigTester): @@ -337,11 +337,11 @@ def prepare_img(): class GLPNModelIntegrationTest(unittest.TestCase): @slow def test_inference_depth_estimation(self): - feature_extractor = GLPNFeatureExtractor.from_pretrained(GLPN_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + image_processor = GLPNImageProcessor.from_pretrained(GLPN_PRETRAINED_MODEL_ARCHIVE_LIST[0]) model = GLPNForDepthEstimation.from_pretrained(GLPN_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/imagegpt/test_modeling_imagegpt.py b/tests/models/imagegpt/test_modeling_imagegpt.py index 27d83f3eb8..af08725ef1 100644 --- a/tests/models/imagegpt/test_modeling_imagegpt.py +++ b/tests/models/imagegpt/test_modeling_imagegpt.py @@ -49,7 +49,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import ImageGPTFeatureExtractor + from transformers import ImageGPTImageProcessor class ImageGPTModelTester: @@ -535,16 +535,16 @@ def prepare_img(): @require_vision class ImageGPTModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ImageGPTFeatureExtractor.from_pretrained("openai/imagegpt-small") if is_vision_available() else None + def default_image_processor(self): + return ImageGPTImageProcessor.from_pretrained("openai/imagegpt-small") if is_vision_available() else None @slow def test_inference_causal_lm_head(self): model = ImageGPTForCausalImageModeling.from_pretrained("openai/imagegpt-small").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/layoutlmv3/test_modeling_layoutlmv3.py b/tests/models/layoutlmv3/test_modeling_layoutlmv3.py index c458024f10..2c3aef9b93 100644 --- a/tests/models/layoutlmv3/test_modeling_layoutlmv3.py +++ b/tests/models/layoutlmv3/test_modeling_layoutlmv3.py @@ -45,7 +45,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import LayoutLMv3FeatureExtractor + from transformers import LayoutLMv3ImageProcessor class LayoutLMv3ModelTester: @@ -382,16 +382,16 @@ def prepare_img(): @require_torch class LayoutLMv3ModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return LayoutLMv3FeatureExtractor(apply_ocr=False) if is_vision_available() else None + def default_image_processor(self): + return LayoutLMv3ImageProcessor(apply_ocr=False) if is_vision_available() else None @slow def test_inference_no_head(self): model = LayoutLMv3Model.from_pretrained("microsoft/layoutlmv3-base").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values.to(torch_device) + pixel_values = image_processor(images=image, return_tensors="pt").pixel_values.to(torch_device) input_ids = torch.tensor([[1, 2]]) bbox = torch.tensor([[1, 2, 3, 4], [5, 6, 7, 8]]).unsqueeze(0) diff --git a/tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py b/tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py index 1bdb3e2648..3a6f34185b 100644 --- a/tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py +++ b/tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py @@ -51,7 +51,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import LayoutLMv3FeatureExtractor + from transformers import LayoutLMv3ImageProcessor class TFLayoutLMv3ModelTester: @@ -482,16 +482,16 @@ def prepare_img(): @require_tf class TFLayoutLMv3ModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return LayoutLMv3FeatureExtractor(apply_ocr=False) if is_vision_available() else None + def default_image_processor(self): + return LayoutLMv3ImageProcessor(apply_ocr=False) if is_vision_available() else None @slow def test_inference_no_head(self): model = TFLayoutLMv3Model.from_pretrained("microsoft/layoutlmv3-base") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - pixel_values = feature_extractor(images=image, return_tensors="tf").pixel_values + pixel_values = image_processor(images=image, return_tensors="tf").pixel_values input_ids = tf.constant([[1, 2]]) bbox = tf.expand_dims(tf.constant([[1, 2, 3, 4], [5, 6, 7, 8]]), axis=0) diff --git a/tests/models/layoutxlm/test_processor_layoutxlm.py b/tests/models/layoutxlm/test_processor_layoutxlm.py index 5d74bacfa0..57c349b26b 100644 --- a/tests/models/layoutxlm/test_processor_layoutxlm.py +++ b/tests/models/layoutxlm/test_processor_layoutxlm.py @@ -36,7 +36,7 @@ from transformers.utils import FEATURE_EXTRACTOR_NAME, cached_property, is_pytes if is_pytesseract_available(): from PIL import Image - from transformers import LayoutLMv2FeatureExtractor, LayoutXLMProcessor + from transformers import LayoutLMv2ImageProcessor, LayoutXLMProcessor @require_pytesseract @@ -47,7 +47,7 @@ class LayoutXLMProcessorTest(unittest.TestCase): rust_tokenizer_class = LayoutXLMTokenizerFast def setUp(self): - feature_extractor_map = { + image_processor_map = { "do_resize": True, "size": 224, "apply_ocr": True, @@ -56,7 +56,7 @@ class LayoutXLMProcessorTest(unittest.TestCase): self.tmpdirname = tempfile.mkdtemp() self.feature_extraction_file = os.path.join(self.tmpdirname, FEATURE_EXTRACTOR_NAME) with open(self.feature_extraction_file, "w", encoding="utf-8") as fp: - fp.write(json.dumps(feature_extractor_map) + "\n") + fp.write(json.dumps(image_processor_map) + "\n") # taken from `test_tokenization_layoutxlm.LayoutXLMTokenizationTest.test_save_pretrained` self.tokenizer_pretrained_name = "hf-internal-testing/tiny-random-layoutxlm" @@ -70,8 +70,8 @@ class LayoutXLMProcessorTest(unittest.TestCase): def get_tokenizers(self, **kwargs) -> List[PreTrainedTokenizerBase]: return [self.get_tokenizer(**kwargs), self.get_rust_tokenizer(**kwargs)] - def get_feature_extractor(self, **kwargs): - return LayoutLMv2FeatureExtractor.from_pretrained(self.tmpdirname, **kwargs) + def get_image_processor(self, **kwargs): + return LayoutLMv2ImageProcessor.from_pretrained(self.tmpdirname, **kwargs) def tearDown(self): shutil.rmtree(self.tmpdirname) @@ -88,10 +88,10 @@ class LayoutXLMProcessorTest(unittest.TestCase): return image_inputs def test_save_load_pretrained_default(self): - feature_extractor = self.get_feature_extractor() + image_processor = self.get_image_processor() tokenizers = self.get_tokenizers() for tokenizer in tokenizers: - processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer) + processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer) processor.save_pretrained(self.tmpdirname) processor = LayoutXLMProcessor.from_pretrained(self.tmpdirname) @@ -99,16 +99,16 @@ class LayoutXLMProcessorTest(unittest.TestCase): self.assertEqual(processor.tokenizer.get_vocab(), tokenizer.get_vocab()) self.assertIsInstance(processor.tokenizer, (LayoutXLMTokenizer, LayoutXLMTokenizerFast)) - self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor.to_json_string()) - self.assertIsInstance(processor.feature_extractor, LayoutLMv2FeatureExtractor) + self.assertEqual(processor.image_processor.to_json_string(), image_processor.to_json_string()) + self.assertIsInstance(processor.image_processor, LayoutLMv2ImageProcessor) def test_save_load_pretrained_additional_features(self): - processor = LayoutXLMProcessor(feature_extractor=self.get_feature_extractor(), tokenizer=self.get_tokenizer()) + processor = LayoutXLMProcessor(image_processor=self.get_image_processor(), tokenizer=self.get_tokenizer()) processor.save_pretrained(self.tmpdirname) # slow tokenizer tokenizer_add_kwargs = self.get_tokenizer(bos_token="(BOS)", eos_token="(EOS)") - feature_extractor_add_kwargs = self.get_feature_extractor(do_resize=False, size=30) + image_processor_add_kwargs = self.get_image_processor(do_resize=False, size=30) processor = LayoutXLMProcessor.from_pretrained( self.tmpdirname, @@ -122,12 +122,12 @@ class LayoutXLMProcessorTest(unittest.TestCase): self.assertEqual(processor.tokenizer.get_vocab(), tokenizer_add_kwargs.get_vocab()) self.assertIsInstance(processor.tokenizer, LayoutXLMTokenizer) - self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor_add_kwargs.to_json_string()) - self.assertIsInstance(processor.feature_extractor, LayoutLMv2FeatureExtractor) + self.assertEqual(processor.image_processor.to_json_string(), image_processor_add_kwargs.to_json_string()) + self.assertIsInstance(processor.image_processor, LayoutLMv2ImageProcessor) # fast tokenizer tokenizer_add_kwargs = self.get_rust_tokenizer(bos_token="(BOS)", eos_token="(EOS)") - feature_extractor_add_kwargs = self.get_feature_extractor(do_resize=False, size=30) + image_processor_add_kwargs = self.get_image_processor(do_resize=False, size=30) processor = LayoutXLMProcessor.from_pretrained( self.tmpdirname, use_xlm=True, bos_token="(BOS)", eos_token="(EOS)", do_resize=False, size=30 @@ -136,14 +136,14 @@ class LayoutXLMProcessorTest(unittest.TestCase): self.assertEqual(processor.tokenizer.get_vocab(), tokenizer_add_kwargs.get_vocab()) self.assertIsInstance(processor.tokenizer, LayoutXLMTokenizerFast) - self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor_add_kwargs.to_json_string()) - self.assertIsInstance(processor.feature_extractor, LayoutLMv2FeatureExtractor) + self.assertEqual(processor.image_processor.to_json_string(), image_processor_add_kwargs.to_json_string()) + self.assertIsInstance(processor.image_processor, LayoutLMv2ImageProcessor) def test_model_input_names(self): - feature_extractor = self.get_feature_extractor() + image_processor = self.get_image_processor() tokenizer = self.get_tokenizer() - processor = LayoutXLMProcessor(tokenizer=tokenizer, feature_extractor=feature_extractor) + processor = LayoutXLMProcessor(tokenizer=tokenizer, image_processor=image_processor) input_str = "lower newer" image_input = self.prepare_image_inputs() @@ -215,15 +215,15 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase): def test_processor_case_1(self): # case 1: document image classification (training, inference) + token classification (inference), apply_ocr = True - feature_extractor = LayoutLMv2FeatureExtractor() + image_processor = LayoutLMv2ImageProcessor() tokenizers = self.get_tokenizers images = self.get_images for tokenizer in tokenizers: - processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer) + processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer) # not batched - input_feat_extract = feature_extractor(images[0], return_tensors="pt") + input_feat_extract = image_processor(images[0], return_tensors="pt") input_processor = processor(images[0], return_tensors="pt") # verify keys @@ -245,7 +245,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase): self.assertSequenceEqual(decoding, expected_decoding) # batched - input_feat_extract = feature_extractor(images, return_tensors="pt") + input_feat_extract = image_processor(images, return_tensors="pt") input_processor = processor(images, padding=True, return_tensors="pt") # verify keys @@ -270,12 +270,12 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase): def test_processor_case_2(self): # case 2: document image classification (training, inference) + token classification (inference), apply_ocr=False - feature_extractor = LayoutLMv2FeatureExtractor(apply_ocr=False) + image_processor = LayoutLMv2ImageProcessor(apply_ocr=False) tokenizers = self.get_tokenizers images = self.get_images for tokenizer in tokenizers: - processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer) + processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer) # not batched words = ["hello", "world"] @@ -324,12 +324,12 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase): def test_processor_case_3(self): # case 3: token classification (training), apply_ocr=False - feature_extractor = LayoutLMv2FeatureExtractor(apply_ocr=False) + image_processor = LayoutLMv2ImageProcessor(apply_ocr=False) tokenizers = self.get_tokenizers images = self.get_images for tokenizer in tokenizers: - processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer) + processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer) # not batched words = ["weirdly", "world"] @@ -389,12 +389,12 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase): def test_processor_case_4(self): # case 4: visual question answering (inference), apply_ocr=True - feature_extractor = LayoutLMv2FeatureExtractor() + image_processor = LayoutLMv2ImageProcessor() tokenizers = self.get_tokenizers images = self.get_images for tokenizer in tokenizers: - processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer) + processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer) # not batched question = "What's his name?" @@ -440,12 +440,12 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase): def test_processor_case_5(self): # case 5: visual question answering (inference), apply_ocr=False - feature_extractor = LayoutLMv2FeatureExtractor(apply_ocr=False) + image_processor = LayoutLMv2ImageProcessor(apply_ocr=False) tokenizers = self.get_tokenizers images = self.get_images for tokenizer in tokenizers: - processor = LayoutXLMProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer) + processor = LayoutXLMProcessor(image_processor=image_processor, tokenizer=tokenizer) # not batched question = "What's his name?" diff --git a/tests/models/levit/test_modeling_levit.py b/tests/models/levit/test_modeling_levit.py index d4e803ed4d..4f78527514 100644 --- a/tests/models/levit/test_modeling_levit.py +++ b/tests/models/levit/test_modeling_levit.py @@ -46,7 +46,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import LevitFeatureExtractor + from transformers import LevitImageProcessor class LevitConfigTester(ConfigTester): @@ -409,8 +409,8 @@ def prepare_img(): @require_vision class LevitModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return LevitFeatureExtractor.from_pretrained(LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + def default_image_processor(self): + return LevitImageProcessor.from_pretrained(LEVIT_PRETRAINED_MODEL_ARCHIVE_LIST[0]) @slow def test_inference_image_classification_head(self): @@ -418,9 +418,9 @@ class LevitModelIntegrationTest(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/mask2former/test_image_processing_mask2former.py b/tests/models/mask2former/test_image_processing_mask2former.py index 9f76f678f3..c750edd2e2 100644 --- a/tests/models/mask2former/test_image_processing_mask2former.py +++ b/tests/models/mask2former/test_image_processing_mask2former.py @@ -545,9 +545,9 @@ class Mask2FormerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te self.assertEqual(segmentation[0].shape, target_sizes[0]) def test_post_process_instance_segmentation(self): - feature_extractor = self.image_processing_class(num_labels=self.image_processor_tester.num_classes) + image_processor = self.image_processing_class(num_labels=self.image_processor_tester.num_classes) outputs = self.image_processor_tester.get_fake_mask2former_outputs() - segmentation = feature_extractor.post_process_instance_segmentation(outputs, threshold=0) + segmentation = image_processor.post_process_instance_segmentation(outputs, threshold=0) self.assertTrue(len(segmentation) == self.image_processor_tester.batch_size) for el in segmentation: @@ -556,7 +556,7 @@ class Mask2FormerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Te self.assertEqual(type(el["segments_info"]), list) self.assertEqual(el["segmentation"].shape, (384, 384)) - segmentation = feature_extractor.post_process_instance_segmentation( + segmentation = image_processor.post_process_instance_segmentation( outputs, threshold=0, return_binary_maps=True ) diff --git a/tests/models/mask2former/test_modeling_mask2former.py b/tests/models/mask2former/test_modeling_mask2former.py index 8d7cd52f0f..7ec44c0713 100644 --- a/tests/models/mask2former/test_modeling_mask2former.py +++ b/tests/models/mask2former/test_modeling_mask2former.py @@ -325,14 +325,14 @@ class Mask2FormerModelIntegrationTest(unittest.TestCase): return "facebook/mask2former-swin-small-coco-instance" @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return Mask2FormerImageProcessor.from_pretrained(self.model_checkpoints) if is_vision_available() else None def test_inference_no_head(self): model = Mask2FormerModel.from_pretrained(self.model_checkpoints).to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(image, return_tensors="pt").to(torch_device) + inputs = image_processor(image, return_tensors="pt").to(torch_device) inputs_shape = inputs["pixel_values"].shape # check size is divisible by 32 self.assertTrue((inputs_shape[-1] % 32) == 0 and (inputs_shape[-2] % 32) == 0) @@ -371,9 +371,9 @@ class Mask2FormerModelIntegrationTest(unittest.TestCase): def test_inference_universal_segmentation_head(self): model = Mask2FormerForUniversalSegmentation.from_pretrained(self.model_checkpoints).to(torch_device).eval() - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(image, return_tensors="pt").to(torch_device) + inputs = image_processor(image, return_tensors="pt").to(torch_device) inputs_shape = inputs["pixel_values"].shape # check size is divisible by 32 self.assertTrue((inputs_shape[-1] % 32) == 0 and (inputs_shape[-2] % 32) == 0) @@ -408,9 +408,9 @@ class Mask2FormerModelIntegrationTest(unittest.TestCase): def test_with_segmentation_maps_and_loss(self): model = Mask2FormerForUniversalSegmentation.from_pretrained(self.model_checkpoints).to(torch_device).eval() - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor - inputs = feature_extractor( + inputs = image_processor( [np.zeros((3, 800, 1333)), np.zeros((3, 800, 1333))], segmentation_maps=[np.zeros((384, 384)).astype(np.float32), np.zeros((384, 384)).astype(np.float32)], return_tensors="pt", diff --git a/tests/models/maskformer/test_image_processing_maskformer.py b/tests/models/maskformer/test_image_processing_maskformer.py index 128d232d4c..3fff1022c1 100644 --- a/tests/models/maskformer/test_image_processing_maskformer.py +++ b/tests/models/maskformer/test_image_processing_maskformer.py @@ -574,9 +574,9 @@ class MaskFormerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Tes self.assertEqual(segmentation[0].shape, target_sizes[0]) def test_post_process_instance_segmentation(self): - feature_extractor = self.image_processing_class(num_labels=self.image_processor_tester.num_classes) + image_processor = self.image_processing_class(num_labels=self.image_processor_tester.num_classes) outputs = self.image_processor_tester.get_fake_maskformer_outputs() - segmentation = feature_extractor.post_process_instance_segmentation(outputs, threshold=0) + segmentation = image_processor.post_process_instance_segmentation(outputs, threshold=0) self.assertTrue(len(segmentation) == self.image_processor_tester.batch_size) for el in segmentation: @@ -587,7 +587,7 @@ class MaskFormerImageProcessingTest(ImageProcessingSavingTestMixin, unittest.Tes el["segmentation"].shape, (self.image_processor_tester.height, self.image_processor_tester.width) ) - segmentation = feature_extractor.post_process_instance_segmentation( + segmentation = image_processor.post_process_instance_segmentation( outputs, threshold=0, return_binary_maps=True ) diff --git a/tests/models/maskformer/test_modeling_maskformer.py b/tests/models/maskformer/test_modeling_maskformer.py index 65ce4aa7f0..81c720a0b5 100644 --- a/tests/models/maskformer/test_modeling_maskformer.py +++ b/tests/models/maskformer/test_modeling_maskformer.py @@ -35,7 +35,7 @@ if is_torch_available(): from transformers import MaskFormerForInstanceSegmentation, MaskFormerModel if is_vision_available(): - from transformers import MaskFormerFeatureExtractor + from transformers import MaskFormerImageProcessor if is_vision_available(): from PIL import Image @@ -326,18 +326,18 @@ def prepare_img(): @slow class MaskFormerModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-small-coco") + MaskFormerImageProcessor.from_pretrained("facebook/maskformer-swin-small-coco") if is_vision_available() else None ) def test_inference_no_head(self): model = MaskFormerModel.from_pretrained("facebook/maskformer-swin-small-coco").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(image, return_tensors="pt").to(torch_device) + inputs = image_processor(image, return_tensors="pt").to(torch_device) inputs_shape = inputs["pixel_values"].shape # check size is divisible by 32 self.assertTrue((inputs_shape[-1] % 32) == 0 and (inputs_shape[-2] % 32) == 0) @@ -380,9 +380,9 @@ class MaskFormerModelIntegrationTest(unittest.TestCase): .to(torch_device) .eval() ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(image, return_tensors="pt").to(torch_device) + inputs = image_processor(image, return_tensors="pt").to(torch_device) inputs_shape = inputs["pixel_values"].shape # check size is divisible by 32 self.assertTrue((inputs_shape[-1] % 32) == 0 and (inputs_shape[-2] % 32) == 0) @@ -424,9 +424,9 @@ class MaskFormerModelIntegrationTest(unittest.TestCase): .to(torch_device) .eval() ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(image, return_tensors="pt").to(torch_device) + inputs = image_processor(image, return_tensors="pt").to(torch_device) inputs_shape = inputs["pixel_values"].shape # check size is divisible by 32 self.assertTrue((inputs_shape[-1] % 32) == 0 and (inputs_shape[-2] % 32) == 0) @@ -460,9 +460,9 @@ class MaskFormerModelIntegrationTest(unittest.TestCase): .to(torch_device) .eval() ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor - inputs = feature_extractor( + inputs = image_processor( [np.zeros((3, 800, 1333)), np.zeros((3, 800, 1333))], segmentation_maps=[np.zeros((384, 384)).astype(np.float32), np.zeros((384, 384)).astype(np.float32)], return_tensors="pt", diff --git a/tests/models/mgp_str/test_processor_mgp_str.py b/tests/models/mgp_str/test_processor_mgp_str.py index 387d13fad1..4cffc344a3 100644 --- a/tests/models/mgp_str/test_processor_mgp_str.py +++ b/tests/models/mgp_str/test_processor_mgp_str.py @@ -64,7 +64,7 @@ class MgpstrProcessorTest(unittest.TestCase): image_processor_map = { "do_normalize": False, "do_resize": True, - "feature_extractor_type": "ViTFeatureExtractor", + "image_processor_type": "ViTImageProcessor", "resample": 3, "size": {"height": 32, "width": 128}, } diff --git a/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py b/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py index 0129143ec7..8c24935800 100644 --- a/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py +++ b/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py @@ -37,7 +37,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import MobileNetV1FeatureExtractor + from transformers import MobileNetV1ImageProcessor class MobileNetV1ConfigTester(ConfigTester): @@ -240,20 +240,18 @@ def prepare_img(): @require_vision class MobileNetV1ModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - MobileNetV1FeatureExtractor.from_pretrained("google/mobilenet_v1_1.0_224") - if is_vision_available() - else None + MobileNetV1ImageProcessor.from_pretrained("google/mobilenet_v1_1.0_224") if is_vision_available() else None ) @slow def test_inference_image_classification_head(self): model = MobileNetV1ForImageClassification.from_pretrained("google/mobilenet_v1_1.0_224").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py b/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py index e3768d0ee0..06b2bd9d3f 100644 --- a/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py +++ b/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py @@ -37,7 +37,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import MobileNetV2FeatureExtractor + from transformers import MobileNetV2ImageProcessor class MobileNetV2ConfigTester(ConfigTester): @@ -295,20 +295,18 @@ def prepare_img(): @require_vision class MobileNetV2ModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - MobileNetV2FeatureExtractor.from_pretrained("google/mobilenet_v2_1.0_224") - if is_vision_available() - else None + MobileNetV2ImageProcessor.from_pretrained("google/mobilenet_v2_1.0_224") if is_vision_available() else None ) @slow def test_inference_image_classification_head(self): model = MobileNetV2ForImageClassification.from_pretrained("google/mobilenet_v2_1.0_224").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -327,10 +325,10 @@ class MobileNetV2ModelIntegrationTest(unittest.TestCase): model = MobileNetV2ForSemanticSegmentation.from_pretrained("google/deeplabv3_mobilenet_v2_1.0_513") model = model.to(torch_device) - feature_extractor = MobileNetV2FeatureExtractor.from_pretrained("google/deeplabv3_mobilenet_v2_1.0_513") + image_processor = MobileNetV2ImageProcessor.from_pretrained("google/deeplabv3_mobilenet_v2_1.0_513") image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/mobilevit/test_modeling_mobilevit.py b/tests/models/mobilevit/test_modeling_mobilevit.py index e9029cd085..c0ad5a7744 100644 --- a/tests/models/mobilevit/test_modeling_mobilevit.py +++ b/tests/models/mobilevit/test_modeling_mobilevit.py @@ -37,7 +37,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import MobileViTFeatureExtractor + from transformers import MobileViTImageProcessor class MobileViTConfigTester(ConfigTester): @@ -298,16 +298,16 @@ def prepare_img(): @require_vision class MobileViTModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return MobileViTFeatureExtractor.from_pretrained("apple/mobilevit-xx-small") if is_vision_available() else None + def default_image_processor(self): + return MobileViTImageProcessor.from_pretrained("apple/mobilevit-xx-small") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = MobileViTForImageClassification.from_pretrained("apple/mobilevit-xx-small").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -326,10 +326,10 @@ class MobileViTModelIntegrationTest(unittest.TestCase): model = MobileViTForSemanticSegmentation.from_pretrained("apple/deeplabv3-mobilevit-xx-small") model = model.to(torch_device) - feature_extractor = MobileViTFeatureExtractor.from_pretrained("apple/deeplabv3-mobilevit-xx-small") + image_processor = MobileViTImageProcessor.from_pretrained("apple/deeplabv3-mobilevit-xx-small") image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -356,10 +356,10 @@ class MobileViTModelIntegrationTest(unittest.TestCase): model = MobileViTForSemanticSegmentation.from_pretrained("apple/deeplabv3-mobilevit-xx-small") model = model.to(torch_device) - feature_extractor = MobileViTFeatureExtractor.from_pretrained("apple/deeplabv3-mobilevit-xx-small") + image_processor = MobileViTImageProcessor.from_pretrained("apple/deeplabv3-mobilevit-xx-small") image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -367,10 +367,10 @@ class MobileViTModelIntegrationTest(unittest.TestCase): outputs.logits = outputs.logits.detach().cpu() - segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(50, 60)]) + segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(50, 60)]) expected_shape = torch.Size((50, 60)) self.assertEqual(segmentation[0].shape, expected_shape) - segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs) + segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs) expected_shape = torch.Size((32, 32)) self.assertEqual(segmentation[0].shape, expected_shape) diff --git a/tests/models/mobilevit/test_modeling_tf_mobilevit.py b/tests/models/mobilevit/test_modeling_tf_mobilevit.py index c635feae8f..4a3c4484d2 100644 --- a/tests/models/mobilevit/test_modeling_tf_mobilevit.py +++ b/tests/models/mobilevit/test_modeling_tf_mobilevit.py @@ -40,7 +40,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import MobileViTFeatureExtractor + from transformers import MobileViTImageProcessor class TFMobileViTConfigTester(ConfigTester): @@ -381,9 +381,9 @@ class TFMobileViTModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head(self): model = TFMobileViTForImageClassification.from_pretrained("apple/mobilevit-xx-small") - feature_extractor = MobileViTFeatureExtractor.from_pretrained("apple/mobilevit-xx-small") + image_processor = MobileViTImageProcessor.from_pretrained("apple/mobilevit-xx-small") image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(**inputs, training=False) @@ -401,10 +401,10 @@ class TFMobileViTModelIntegrationTest(unittest.TestCase): # `from_pt` will be removed model = TFMobileViTForSemanticSegmentation.from_pretrained("apple/deeplabv3-mobilevit-xx-small") - feature_extractor = MobileViTFeatureExtractor.from_pretrained("apple/deeplabv3-mobilevit-xx-small") + image_processor = MobileViTImageProcessor.from_pretrained("apple/deeplabv3-mobilevit-xx-small") image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(inputs.pixel_values, training=False) diff --git a/tests/models/nat/test_modeling_nat.py b/tests/models/nat/test_modeling_nat.py index cd4f0bf964..a27b087ce5 100644 --- a/tests/models/nat/test_modeling_nat.py +++ b/tests/models/nat/test_modeling_nat.py @@ -364,16 +364,16 @@ class NatModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @require_torch class NatModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return AutoImageProcessor.from_pretrained("shi-labs/nat-mini-in1k-224") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = NatForImageClassification.from_pretrained("shi-labs/nat-mini-in1k-224").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png") - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/perceiver/test_modeling_perceiver.py b/tests/models/perceiver/test_modeling_perceiver.py index c4a32b1647..64ad560d7d 100644 --- a/tests/models/perceiver/test_modeling_perceiver.py +++ b/tests/models/perceiver/test_modeling_perceiver.py @@ -61,7 +61,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import PerceiverFeatureExtractor + from transformers import PerceiverImageProcessor class PerceiverModelTester: @@ -899,13 +899,13 @@ class PerceiverModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_classification(self): - feature_extractor = PerceiverFeatureExtractor() + image_processor = PerceiverImageProcessor() model = PerceiverForImageClassificationLearned.from_pretrained("deepmind/vision-perceiver-learned") model.to(torch_device) # prepare inputs image = prepare_img() - inputs = feature_extractor(image, return_tensors="pt").pixel_values.to(torch_device) + inputs = image_processor(image, return_tensors="pt").pixel_values.to(torch_device) input_mask = None # forward pass @@ -923,13 +923,13 @@ class PerceiverModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_classification_fourier(self): - feature_extractor = PerceiverFeatureExtractor() + image_processor = PerceiverImageProcessor() model = PerceiverForImageClassificationFourier.from_pretrained("deepmind/vision-perceiver-fourier") model.to(torch_device) # prepare inputs image = prepare_img() - inputs = feature_extractor(image, return_tensors="pt").pixel_values.to(torch_device) + inputs = image_processor(image, return_tensors="pt").pixel_values.to(torch_device) input_mask = None # forward pass @@ -947,13 +947,13 @@ class PerceiverModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_classification_conv(self): - feature_extractor = PerceiverFeatureExtractor() + image_processor = PerceiverImageProcessor() model = PerceiverForImageClassificationConvProcessing.from_pretrained("deepmind/vision-perceiver-conv") model.to(torch_device) # prepare inputs image = prepare_img() - inputs = feature_extractor(image, return_tensors="pt").pixel_values.to(torch_device) + inputs = image_processor(image, return_tensors="pt").pixel_values.to(torch_device) input_mask = None # forward pass diff --git a/tests/models/poolformer/test_modeling_poolformer.py b/tests/models/poolformer/test_modeling_poolformer.py index e741b9650d..99667d6f1b 100644 --- a/tests/models/poolformer/test_modeling_poolformer.py +++ b/tests/models/poolformer/test_modeling_poolformer.py @@ -37,7 +37,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import PoolFormerFeatureExtractor + from transformers import PoolFormerImageProcessor class PoolFormerConfigTester(ConfigTester): @@ -237,10 +237,10 @@ def prepare_img(): class PoolFormerModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_classification_head(self): - feature_extractor = PoolFormerFeatureExtractor() + image_processor = PoolFormerImageProcessor() model = PoolFormerForImageClassification.from_pretrained("sail/poolformer_s12").to(torch_device) - inputs = feature_extractor(images=prepare_img(), return_tensors="pt").to(torch_device) + inputs = image_processor(images=prepare_img(), return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/regnet/test_modeling_flax_regnet.py b/tests/models/regnet/test_modeling_flax_regnet.py index e9788ab09d..911d595c56 100644 --- a/tests/models/regnet/test_modeling_flax_regnet.py +++ b/tests/models/regnet/test_modeling_flax_regnet.py @@ -33,7 +33,7 @@ if is_flax_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class FlaxRegNetModelTester(unittest.TestCase): @@ -215,16 +215,16 @@ def prepare_img(): @require_flax class FlaxRegNetModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return AutoFeatureExtractor.from_pretrained("facebook/regnet-y-040") if is_vision_available() else None + def default_image_processor(self): + return AutoImageProcessor.from_pretrained("facebook/regnet-y-040") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = FlaxRegNetForImageClassification.from_pretrained("facebook/regnet-y-040") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="np") + inputs = image_processor(images=image, return_tensors="np") outputs = model(**inputs) diff --git a/tests/models/regnet/test_modeling_regnet.py b/tests/models/regnet/test_modeling_regnet.py index e7c33699fd..debd8271b5 100644 --- a/tests/models/regnet/test_modeling_regnet.py +++ b/tests/models/regnet/test_modeling_regnet.py @@ -38,7 +38,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class RegNetModelTester: @@ -248,9 +248,9 @@ def prepare_img(): @require_vision class RegNetModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - AutoFeatureExtractor.from_pretrained(REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + AutoImageProcessor.from_pretrained(REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) if is_vision_available() else None ) @@ -259,9 +259,9 @@ class RegNetModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head(self): model = RegNetForImageClassification.from_pretrained(REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/regnet/test_modeling_tf_regnet.py b/tests/models/regnet/test_modeling_tf_regnet.py index 4536458c54..a2f2bf92ef 100644 --- a/tests/models/regnet/test_modeling_tf_regnet.py +++ b/tests/models/regnet/test_modeling_tf_regnet.py @@ -38,7 +38,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class TFRegNetModelTester: @@ -267,9 +267,9 @@ def prepare_img(): @require_vision class RegNetModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - AutoFeatureExtractor.from_pretrained(TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + AutoImageProcessor.from_pretrained(TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) if is_vision_available() else None ) @@ -278,9 +278,9 @@ class RegNetModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head(self): model = TFRegNetForImageClassification.from_pretrained(TF_REGNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(**inputs, training=False) diff --git a/tests/models/resnet/test_modeling_flax_resnet.py b/tests/models/resnet/test_modeling_flax_resnet.py index ee56cfe113..e9566e2e2f 100644 --- a/tests/models/resnet/test_modeling_flax_resnet.py +++ b/tests/models/resnet/test_modeling_flax_resnet.py @@ -32,7 +32,7 @@ if is_flax_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class FlaxResNetModelTester(unittest.TestCase): @@ -206,16 +206,16 @@ def prepare_img(): @require_flax class FlaxResNetModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return AutoFeatureExtractor.from_pretrained("microsoft/resnet-50") if is_vision_available() else None + def default_image_processor(self): + return AutoImageProcessor.from_pretrained("microsoft/resnet-50") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = FlaxResNetForImageClassification.from_pretrained("microsoft/resnet-50") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="np") + inputs = image_processor(images=image, return_tensors="np") outputs = model(**inputs) diff --git a/tests/models/resnet/test_modeling_resnet.py b/tests/models/resnet/test_modeling_resnet.py index fe7a1a0458..4cfa18d6bc 100644 --- a/tests/models/resnet/test_modeling_resnet.py +++ b/tests/models/resnet/test_modeling_resnet.py @@ -39,7 +39,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class ResNetModelTester: @@ -301,9 +301,9 @@ def prepare_img(): @require_vision class ResNetModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - AutoFeatureExtractor.from_pretrained(RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + AutoImageProcessor.from_pretrained(RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) if is_vision_available() else None ) @@ -312,9 +312,9 @@ class ResNetModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head(self): model = ResNetForImageClassification.from_pretrained(RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/resnet/test_modeling_tf_resnet.py b/tests/models/resnet/test_modeling_tf_resnet.py index e6f8d121c2..827fc807df 100644 --- a/tests/models/resnet/test_modeling_tf_resnet.py +++ b/tests/models/resnet/test_modeling_tf_resnet.py @@ -41,7 +41,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class TFResNetModelTester: @@ -229,9 +229,9 @@ def prepare_img(): @require_vision class TFResNetModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - AutoFeatureExtractor.from_pretrained(TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + AutoImageProcessor.from_pretrained(TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) if is_vision_available() else None ) @@ -240,9 +240,9 @@ class TFResNetModelIntegrationTest(unittest.TestCase): def test_inference_image_classification_head(self): model = TFResNetForImageClassification.from_pretrained(TF_RESNET_PRETRAINED_MODEL_ARCHIVE_LIST[0]) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(**inputs) diff --git a/tests/models/segformer/test_modeling_segformer.py b/tests/models/segformer/test_modeling_segformer.py index c357fee5ae..03706ca96e 100644 --- a/tests/models/segformer/test_modeling_segformer.py +++ b/tests/models/segformer/test_modeling_segformer.py @@ -42,7 +42,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import SegformerFeatureExtractor + from transformers import SegformerImageProcessor class SegformerConfigTester(ConfigTester): @@ -365,7 +365,7 @@ class SegformerModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_segmentation_ade(self): # only resize + normalize - feature_extractor = SegformerFeatureExtractor( + image_processor = SegformerImageProcessor( image_scale=(512, 512), keep_ratio=False, align=False, do_random_crop=False ) model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512").to( @@ -373,7 +373,7 @@ class SegformerModelIntegrationTest(unittest.TestCase): ) image = prepare_img() - encoded_inputs = feature_extractor(images=image, return_tensors="pt") + encoded_inputs = image_processor(images=image, return_tensors="pt") pixel_values = encoded_inputs.pixel_values.to(torch_device) with torch.no_grad(): @@ -394,7 +394,7 @@ class SegformerModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_segmentation_city(self): # only resize + normalize - feature_extractor = SegformerFeatureExtractor( + image_processor = SegformerImageProcessor( image_scale=(512, 512), keep_ratio=False, align=False, do_random_crop=False ) model = SegformerForSemanticSegmentation.from_pretrained( @@ -402,7 +402,7 @@ class SegformerModelIntegrationTest(unittest.TestCase): ).to(torch_device) image = prepare_img() - encoded_inputs = feature_extractor(images=image, return_tensors="pt") + encoded_inputs = image_processor(images=image, return_tensors="pt") pixel_values = encoded_inputs.pixel_values.to(torch_device) with torch.no_grad(): @@ -423,7 +423,7 @@ class SegformerModelIntegrationTest(unittest.TestCase): @slow def test_post_processing_semantic_segmentation(self): # only resize + normalize - feature_extractor = SegformerFeatureExtractor( + image_processor = SegformerImageProcessor( image_scale=(512, 512), keep_ratio=False, align=False, do_random_crop=False ) model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512").to( @@ -431,7 +431,7 @@ class SegformerModelIntegrationTest(unittest.TestCase): ) image = prepare_img() - encoded_inputs = feature_extractor(images=image, return_tensors="pt") + encoded_inputs = image_processor(images=image, return_tensors="pt") pixel_values = encoded_inputs.pixel_values.to(torch_device) with torch.no_grad(): @@ -439,10 +439,10 @@ class SegformerModelIntegrationTest(unittest.TestCase): outputs.logits = outputs.logits.detach().cpu() - segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(500, 300)]) + segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[(500, 300)]) expected_shape = torch.Size((500, 300)) self.assertEqual(segmentation[0].shape, expected_shape) - segmentation = feature_extractor.post_process_semantic_segmentation(outputs=outputs) + segmentation = image_processor.post_process_semantic_segmentation(outputs=outputs) expected_shape = torch.Size((128, 128)) self.assertEqual(segmentation[0].shape, expected_shape) diff --git a/tests/models/segformer/test_modeling_tf_segformer.py b/tests/models/segformer/test_modeling_tf_segformer.py index b381a2e890..b4dc657b79 100644 --- a/tests/models/segformer/test_modeling_tf_segformer.py +++ b/tests/models/segformer/test_modeling_tf_segformer.py @@ -39,7 +39,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import SegformerFeatureExtractor + from transformers import SegformerImageProcessor class TFSegformerConfigTester(ConfigTester): @@ -454,13 +454,13 @@ class TFSegformerModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_segmentation_ade(self): # only resize + normalize - feature_extractor = SegformerFeatureExtractor( + image_processor = SegformerImageProcessor( image_scale=(512, 512), keep_ratio=False, align=False, do_random_crop=False ) model = TFSegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512") image = prepare_img() - encoded_inputs = feature_extractor(images=image, return_tensors="tf") + encoded_inputs = image_processor(images=image, return_tensors="tf") pixel_values = encoded_inputs.pixel_values outputs = model(pixel_values, training=False) @@ -480,7 +480,7 @@ class TFSegformerModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_segmentation_city(self): # only resize + normalize - feature_extractor = SegformerFeatureExtractor( + image_processor = SegformerImageProcessor( image_scale=(512, 512), keep_ratio=False, align=False, do_random_crop=False ) model = TFSegformerForSemanticSegmentation.from_pretrained( @@ -488,7 +488,7 @@ class TFSegformerModelIntegrationTest(unittest.TestCase): ) image = prepare_img() - encoded_inputs = feature_extractor(images=image, return_tensors="tf") + encoded_inputs = image_processor(images=image, return_tensors="tf") pixel_values = encoded_inputs.pixel_values outputs = model(pixel_values, training=False) diff --git a/tests/models/swiftformer/test_modeling_swiftformer.py b/tests/models/swiftformer/test_modeling_swiftformer.py index 159d5ec0fa..e524719d23 100644 --- a/tests/models/swiftformer/test_modeling_swiftformer.py +++ b/tests/models/swiftformer/test_modeling_swiftformer.py @@ -283,16 +283,16 @@ def prepare_img(): @require_vision class SwiftFormerModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ViTImageProcessor.from_pretrained("MBZUAI/swiftformer-xs") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = SwiftFormerForImageClassification.from_pretrained("MBZUAI/swiftformer-xs").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/swin/test_modeling_swin.py b/tests/models/swin/test_modeling_swin.py index 9dcb1bfdc6..383f0fe867 100644 --- a/tests/models/swin/test_modeling_swin.py +++ b/tests/models/swin/test_modeling_swin.py @@ -39,7 +39,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class SwinModelTester: @@ -482,9 +482,9 @@ class SwinModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @require_torch class SwinModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - AutoFeatureExtractor.from_pretrained("microsoft/swin-tiny-patch4-window7-224") + AutoImageProcessor.from_pretrained("microsoft/swin-tiny-patch4-window7-224") if is_vision_available() else None ) @@ -492,10 +492,10 @@ class SwinModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_classification_head(self): model = SwinForImageClassification.from_pretrained("microsoft/swin-tiny-patch4-window7-224").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png") - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/swin/test_modeling_tf_swin.py b/tests/models/swin/test_modeling_tf_swin.py index de271fb38a..597643936f 100644 --- a/tests/models/swin/test_modeling_tf_swin.py +++ b/tests/models/swin/test_modeling_tf_swin.py @@ -45,7 +45,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class TFSwinModelTester: @@ -382,9 +382,9 @@ class TFSwinModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.TestCase @require_tf class TFSwinModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - AutoFeatureExtractor.from_pretrained("microsoft/swin-tiny-patch4-window7-224") + AutoImageProcessor.from_pretrained("microsoft/swin-tiny-patch4-window7-224") if is_vision_available() else None ) @@ -392,10 +392,10 @@ class TFSwinModelIntegrationTest(unittest.TestCase): @slow def test_inference_image_classification_head(self): model = TFSwinForImageClassification.from_pretrained("microsoft/swin-tiny-patch4-window7-224") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png") - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(inputs) diff --git a/tests/models/swinv2/test_modeling_swinv2.py b/tests/models/swinv2/test_modeling_swinv2.py index b0ceaff2ed..5a771b2c4b 100644 --- a/tests/models/swinv2/test_modeling_swinv2.py +++ b/tests/models/swinv2/test_modeling_swinv2.py @@ -36,7 +36,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class Swinv2ModelTester: @@ -412,9 +412,9 @@ class Swinv2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): @require_torch class Swinv2ModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( - AutoFeatureExtractor.from_pretrained("microsoft/swinv2-tiny-patch4-window8-256") + AutoImageProcessor.from_pretrained("microsoft/swinv2-tiny-patch4-window8-256") if is_vision_available() else None ) @@ -424,10 +424,10 @@ class Swinv2ModelIntegrationTest(unittest.TestCase): model = Swinv2ForImageClassification.from_pretrained("microsoft/swinv2-tiny-patch4-window8-256").to( torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png") - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/table_transformer/test_modeling_table_transformer.py b/tests/models/table_transformer/test_modeling_table_transformer.py index 0dafb55e5a..2d42e29906 100644 --- a/tests/models/table_transformer/test_modeling_table_transformer.py +++ b/tests/models/table_transformer/test_modeling_table_transformer.py @@ -39,7 +39,7 @@ if is_timm_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class TableTransformerModelTester: @@ -501,13 +501,13 @@ def prepare_img(): @slow class TableTransformerModelIntegrationTests(unittest.TestCase): def test_table_detection(self): - feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/table-transformer-detection") + image_processor = AutoImageProcessor.from_pretrained("microsoft/table-transformer-detection") model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-detection") model.to(torch_device) file_path = hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_pdf.png") image = Image.open(file_path).convert("RGB") - inputs = feature_extractor(image, return_tensors="pt").to(torch_device) + inputs = image_processor(image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/timesformer/test_modeling_timesformer.py b/tests/models/timesformer/test_modeling_timesformer.py index ff73fa208a..2783a65ced 100644 --- a/tests/models/timesformer/test_modeling_timesformer.py +++ b/tests/models/timesformer/test_modeling_timesformer.py @@ -45,7 +45,7 @@ if is_torch_available(): if is_vision_available(): - from transformers import VideoMAEFeatureExtractor + from transformers import VideoMAEImageProcessor class TimesformerModelTester: @@ -339,10 +339,10 @@ def prepare_video(): @require_vision class TimesformerModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): # logits were tested with a different mean and std, so we use the same here return ( - VideoMAEFeatureExtractor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5]) + VideoMAEImageProcessor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5]) if is_vision_available() else None ) @@ -353,9 +353,9 @@ class TimesformerModelIntegrationTest(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor video = prepare_video() - inputs = feature_extractor(video[:8], return_tensors="pt").to(torch_device) + inputs = image_processor(video[:8], return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/tvlt/test_modeling_tvlt.py b/tests/models/tvlt/test_modeling_tvlt.py index e1864e48dd..52af9b6f1b 100644 --- a/tests/models/tvlt/test_modeling_tvlt.py +++ b/tests/models/tvlt/test_modeling_tvlt.py @@ -564,7 +564,7 @@ def prepare_audio(num_samples=1): @require_vision class TvltModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_processors(self): # logits were tested with a different mean and std, so we use the same here return ( TvltImageProcessor() if is_vision_available() else None, @@ -574,7 +574,7 @@ class TvltModelIntegrationTest(unittest.TestCase): def test_inference_for_base_model(self): model = TvltModel.from_pretrained("ZinengTang/tvlt-base").to(torch_device) - image_processor, audio_feature_extractor = self.default_feature_extractor + image_processor, audio_feature_extractor = self.default_processors video = prepare_video() audio = prepare_audio() video_inputs = image_processor(video, return_tensors="pt").to(torch_device) @@ -596,7 +596,7 @@ class TvltModelIntegrationTest(unittest.TestCase): def test_inference_for_pretraining(self): model = TvltForPreTraining.from_pretrained("ZinengTang/tvlt-base").to(torch_device) - image_processor, audio_feature_extractor = self.default_feature_extractor + image_processor, audio_feature_extractor = self.default_processors video = prepare_video() video_mixed = prepare_video() audio = prepare_audio() diff --git a/tests/models/van/test_modeling_van.py b/tests/models/van/test_modeling_van.py index 49df30a828..1296e0a225 100644 --- a/tests/models/van/test_modeling_van.py +++ b/tests/models/van/test_modeling_van.py @@ -42,7 +42,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class VanModelTester: @@ -254,16 +254,16 @@ def prepare_img(): @require_vision class VanModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return AutoFeatureExtractor.from_pretrained(VAN_PRETRAINED_MODEL_ARCHIVE_LIST[0]) + def default_image_processor(self): + return AutoImageProcessor.from_pretrained(VAN_PRETRAINED_MODEL_ARCHIVE_LIST[0]) @slow def test_inference_image_classification_head(self): model = VanForImageClassification.from_pretrained(VAN_PRETRAINED_MODEL_ARCHIVE_LIST[0]).to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/videomae/test_modeling_videomae.py b/tests/models/videomae/test_modeling_videomae.py index 1070a4ee2a..424fc7d84a 100644 --- a/tests/models/videomae/test_modeling_videomae.py +++ b/tests/models/videomae/test_modeling_videomae.py @@ -46,7 +46,7 @@ if is_torch_available(): if is_vision_available(): - from transformers import VideoMAEFeatureExtractor + from transformers import VideoMAEImageProcessor class VideoMAEModelTester: @@ -359,10 +359,10 @@ def prepare_video(): @require_vision class VideoMAEModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): # logits were tested with a different mean and std, so we use the same here return ( - VideoMAEFeatureExtractor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5]) + VideoMAEImageProcessor(image_mean=[0.5, 0.5, 0.5], image_std=[0.5, 0.5, 0.5]) if is_vision_available() else None ) @@ -373,9 +373,9 @@ class VideoMAEModelIntegrationTest(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor video = prepare_video() - inputs = feature_extractor(video, return_tensors="pt").to(torch_device) + inputs = image_processor(video, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -393,9 +393,9 @@ class VideoMAEModelIntegrationTest(unittest.TestCase): def test_inference_for_pretraining(self): model = VideoMAEForPreTraining.from_pretrained("MCG-NJU/videomae-base-short").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor video = prepare_video() - inputs = feature_extractor(video, return_tensors="pt").to(torch_device) + inputs = image_processor(video, return_tensors="pt").to(torch_device) # add boolean mask, indicating which patches to mask local_path = hf_hub_download(repo_id="hf-internal-testing/bool-masked-pos", filename="bool_masked_pos.pt") diff --git a/tests/models/vision_encoder_decoder/test_modeling_flax_vision_encoder_decoder.py b/tests/models/vision_encoder_decoder/test_modeling_flax_vision_encoder_decoder.py index c4f84012c7..c6926e002a 100644 --- a/tests/models/vision_encoder_decoder/test_modeling_flax_vision_encoder_decoder.py +++ b/tests/models/vision_encoder_decoder/test_modeling_flax_vision_encoder_decoder.py @@ -48,7 +48,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import ViTFeatureExtractor + from transformers import ViTImageProcessor @require_flax @@ -462,12 +462,12 @@ class FlaxViT2GPT2ModelIntegrationTest(unittest.TestCase): def test_inference_coco_en(self): loc = "ydshieh/vit-gpt2-coco-en" - feature_extractor = ViTFeatureExtractor.from_pretrained(loc) + image_processor = ViTImageProcessor.from_pretrained(loc) tokenizer = AutoTokenizer.from_pretrained(loc) model = FlaxVisionEncoderDecoderModel.from_pretrained(loc) img = prepare_img() - pixel_values = feature_extractor(images=img, return_tensors="np").pixel_values + pixel_values = image_processor(images=img, return_tensors="np").pixel_values decoder_input_ids = np.array([[model.config.decoder_start_token_id]]) logits = model(pixel_values, decoder_input_ids)[0] diff --git a/tests/models/vision_encoder_decoder/test_modeling_tf_vision_encoder_decoder.py b/tests/models/vision_encoder_decoder/test_modeling_tf_vision_encoder_decoder.py index 7a29bbd221..e173e21a9b 100644 --- a/tests/models/vision_encoder_decoder/test_modeling_tf_vision_encoder_decoder.py +++ b/tests/models/vision_encoder_decoder/test_modeling_tf_vision_encoder_decoder.py @@ -45,7 +45,7 @@ if is_tf_available(): from transformers import ( AutoConfig, - AutoFeatureExtractor, + AutoImageProcessor, AutoTokenizer, TFAutoModel, TFAutoModelForCausalLM, @@ -64,7 +64,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import ViTFeatureExtractor + from transformers import ViTImageProcessor @require_tf @@ -828,11 +828,11 @@ class TFVisionEncoderDecoderModelSaveLoadTests(unittest.TestCase): load_weight_prefix = TFVisionEncoderDecoderModel.load_weight_prefix config = self.get_encoder_decoder_config() - feature_extractor = AutoFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k") + image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k") decoder_tokenizer = AutoTokenizer.from_pretrained("gpt2") img = prepare_img() - pixel_values = feature_extractor(images=img, return_tensors="tf").pixel_values + pixel_values = image_processor(images=img, return_tensors="tf").pixel_values decoder_input_ids = decoder_tokenizer("Linda Davis", return_tensors="tf").input_ids with tempfile.TemporaryDirectory() as tmp_dirname: @@ -893,13 +893,13 @@ class TFViT2GPT2ModelIntegrationTest(unittest.TestCase): def test_inference_coco_en(self): loc = "ydshieh/vit-gpt2-coco-en" - feature_extractor = ViTFeatureExtractor.from_pretrained(loc) + image_processor = ViTImageProcessor.from_pretrained(loc) tokenizer = AutoTokenizer.from_pretrained(loc) model = TFVisionEncoderDecoderModel.from_pretrained(loc) # We will verify our results on an image of cute cats img = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png") - pixel_values = feature_extractor(images=img, return_tensors="tf").pixel_values + pixel_values = image_processor(images=img, return_tensors="tf").pixel_values decoder_input_ids = tf.constant([[model.config.decoder_start_token_id]]) diff --git a/tests/models/vision_encoder_decoder/test_modeling_vision_encoder_decoder.py b/tests/models/vision_encoder_decoder/test_modeling_vision_encoder_decoder.py index 52b23195b1..8ef7ac4697 100644 --- a/tests/models/vision_encoder_decoder/test_modeling_vision_encoder_decoder.py +++ b/tests/models/vision_encoder_decoder/test_modeling_vision_encoder_decoder.py @@ -62,7 +62,7 @@ if is_vision_available(): import PIL from PIL import Image - from transformers import ViTFeatureExtractor + from transformers import ViTImageProcessor @require_torch @@ -749,7 +749,7 @@ class ViT2GPT2ModelIntegrationTest(unittest.TestCase): def test_inference_coco_en(self): loc = "ydshieh/vit-gpt2-coco-en" - feature_extractor = ViTFeatureExtractor.from_pretrained(loc) + image_processor = ViTImageProcessor.from_pretrained(loc) tokenizer = AutoTokenizer.from_pretrained(loc) model = VisionEncoderDecoderModel.from_pretrained(loc) model.to(torch_device) @@ -757,7 +757,7 @@ class ViT2GPT2ModelIntegrationTest(unittest.TestCase): # We will verify our results on an image of cute cats img = Image.open("./tests/fixtures/tests_samples/COCO/000000039769.png") - pixel_values = feature_extractor(images=img, return_tensors="pt").pixel_values.to(torch_device) + pixel_values = image_processor(images=img, return_tensors="pt").pixel_values.to(torch_device) decoder_input_ids = torch.tensor([[model.config.decoder_start_token_id]]).to(torch_device) diff --git a/tests/models/vision_text_dual_encoder/test_processor_vision_text_dual_encoder.py b/tests/models/vision_text_dual_encoder/test_processor_vision_text_dual_encoder.py index 30630256f9..7cd8b7645d 100644 --- a/tests/models/vision_text_dual_encoder/test_processor_vision_text_dual_encoder.py +++ b/tests/models/vision_text_dual_encoder/test_processor_vision_text_dual_encoder.py @@ -170,10 +170,10 @@ class VisionTextDualEncoderProcessorTest(unittest.TestCase): self.assertListEqual(decoded_tok, decoded_processor) def test_model_input_names(self): - feature_extractor = self.get_image_processor() + image_processor = self.get_image_processor() tokenizer = self.get_tokenizer() - processor = VisionTextDualEncoderProcessor(tokenizer=tokenizer, feature_extractor=feature_extractor) + processor = VisionTextDualEncoderProcessor(tokenizer=tokenizer, image_processor=image_processor) input_str = "lower newer" image_input = self.prepare_image_inputs() diff --git a/tests/models/vit/test_modeling_tf_vit.py b/tests/models/vit/test_modeling_tf_vit.py index 72ca1b19dc..53862da916 100644 --- a/tests/models/vit/test_modeling_tf_vit.py +++ b/tests/models/vit/test_modeling_tf_vit.py @@ -38,7 +38,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import ViTFeatureExtractor + from transformers import ViTImageProcessor class TFViTModelTester: @@ -228,16 +228,16 @@ def prepare_img(): @require_vision class TFViTModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224") if is_vision_available() else None + def default_image_processor(self): + return ViTImageProcessor.from_pretrained("google/vit-base-patch16-224") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = TFViTForImageClassification.from_pretrained("google/vit-base-patch16-224") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # forward pass outputs = model(**inputs) diff --git a/tests/models/vit/test_modeling_vit.py b/tests/models/vit/test_modeling_vit.py index d7ae3c162f..67c6e4acb1 100644 --- a/tests/models/vit/test_modeling_vit.py +++ b/tests/models/vit/test_modeling_vit.py @@ -45,7 +45,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import ViTFeatureExtractor + from transformers import ViTImageProcessor class ViTModelTester: @@ -264,16 +264,16 @@ def prepare_img(): @require_vision class ViTModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224") if is_vision_available() else None + def default_image_processor(self): + return ViTImageProcessor.from_pretrained("google/vit-base-patch16-224") if is_vision_available() else None @slow def test_inference_image_classification_head(self): model = ViTForImageClassification.from_pretrained("google/vit-base-patch16-224").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -295,9 +295,9 @@ class ViTModelIntegrationTest(unittest.TestCase): # to visualize self-attention on higher resolution images. model = ViTModel.from_pretrained("facebook/dino-vits8").to(torch_device) - feature_extractor = ViTFeatureExtractor.from_pretrained("facebook/dino-vits8", size=480) + image_processor = ViTImageProcessor.from_pretrained("facebook/dino-vits8", size=480) image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt") + inputs = image_processor(images=image, return_tensors="pt") pixel_values = inputs.pixel_values.to(torch_device) # forward pass @@ -322,10 +322,10 @@ class ViTModelIntegrationTest(unittest.TestCase): A small test to make sure that inference work in half precision without any problem. """ model = ViTModel.from_pretrained("facebook/dino-vits8", torch_dtype=torch.float16, device_map="auto") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt") + inputs = image_processor(images=image, return_tensors="pt") pixel_values = inputs.pixel_values.to(torch_device) # forward pass to make sure inference works in fp16 diff --git a/tests/models/vit_hybrid/test_modeling_vit_hybrid.py b/tests/models/vit_hybrid/test_modeling_vit_hybrid.py index 7fbe2f9dca..fc816750e7 100644 --- a/tests/models/vit_hybrid/test_modeling_vit_hybrid.py +++ b/tests/models/vit_hybrid/test_modeling_vit_hybrid.py @@ -243,7 +243,7 @@ def prepare_img(): @require_vision class ViTModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): + def default_image_processor(self): return ( ViTHybridImageProcessor.from_pretrained(VIT_HYBRID_PRETRAINED_MODEL_ARCHIVE_LIST[0]) if is_vision_available() @@ -256,9 +256,9 @@ class ViTModelIntegrationTest(unittest.TestCase): torch_device ) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -275,12 +275,12 @@ class ViTModelIntegrationTest(unittest.TestCase): @slow @require_accelerate def test_accelerate_inference(self): - feature_extractor = ViTHybridImageProcessor.from_pretrained("google/vit-hybrid-base-bit-384") + image_processor = ViTHybridImageProcessor.from_pretrained("google/vit-hybrid-base-bit-384") model = ViTHybridForImageClassification.from_pretrained("google/vit-hybrid-base-bit-384", device_map="auto") image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt") + inputs = image_processor(images=image, return_tensors="pt") outputs = model(**inputs) logits = outputs.logits # model predicts one of the 1000 ImageNet classes diff --git a/tests/models/vit_mae/test_modeling_tf_vit_mae.py b/tests/models/vit_mae/test_modeling_tf_vit_mae.py index 34e5a636d8..bc7d481f5f 100644 --- a/tests/models/vit_mae/test_modeling_tf_vit_mae.py +++ b/tests/models/vit_mae/test_modeling_tf_vit_mae.py @@ -46,7 +46,7 @@ if is_tf_available(): if is_vision_available(): from PIL import Image - from transformers import ViTFeatureExtractor + from transformers import ViTImageProcessor class TFViTMAEModelTester: @@ -424,8 +424,8 @@ def prepare_img(): @require_vision class TFViTMAEModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ViTFeatureExtractor.from_pretrained("facebook/vit-mae-base") if is_vision_available() else None + def default_image_processor(self): + return ViTImageProcessor.from_pretrained("facebook/vit-mae-base") if is_vision_available() else None @slow def test_inference_for_pretraining(self): @@ -434,9 +434,9 @@ class TFViTMAEModelIntegrationTest(unittest.TestCase): model = TFViTMAEForPreTraining.from_pretrained("facebook/vit-mae-base") - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="tf") + inputs = image_processor(images=image, return_tensors="tf") # prepare a noise vector that will be also used for testing the TF model # (this way we can ensure that the PT and TF models operate on the same inputs) diff --git a/tests/models/vit_mae/test_modeling_vit_mae.py b/tests/models/vit_mae/test_modeling_vit_mae.py index c58e2e9480..8b63cd6d75 100644 --- a/tests/models/vit_mae/test_modeling_vit_mae.py +++ b/tests/models/vit_mae/test_modeling_vit_mae.py @@ -42,7 +42,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import ViTFeatureExtractor + from transformers import ViTImageProcessor class ViTMAEModelTester: @@ -296,8 +296,8 @@ def prepare_img(): @require_vision class ViTMAEModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ViTFeatureExtractor.from_pretrained("facebook/vit-mae-base") if is_vision_available() else None + def default_image_processor(self): + return ViTImageProcessor.from_pretrained("facebook/vit-mae-base") if is_vision_available() else None @slow def test_inference_for_pretraining(self): @@ -306,9 +306,9 @@ class ViTMAEModelIntegrationTest(unittest.TestCase): model = ViTMAEForPreTraining.from_pretrained("facebook/vit-mae-base").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # prepare a noise vector that will be also used for testing the TF model # (this way we can ensure that the PT and TF models operate on the same inputs) diff --git a/tests/models/vit_msn/test_modeling_vit_msn.py b/tests/models/vit_msn/test_modeling_vit_msn.py index 966ec6c6d3..173dca0913 100644 --- a/tests/models/vit_msn/test_modeling_vit_msn.py +++ b/tests/models/vit_msn/test_modeling_vit_msn.py @@ -38,7 +38,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import ViTFeatureExtractor + from transformers import ViTImageProcessor class ViTMSNModelTester: @@ -220,17 +220,17 @@ def prepare_img(): @require_vision class ViTMSNModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return ViTFeatureExtractor.from_pretrained("facebook/vit-msn-small") if is_vision_available() else None + def default_image_processor(self): + return ViTImageProcessor.from_pretrained("facebook/vit-msn-small") if is_vision_available() else None @slow def test_inference_image_classification_head(self): torch.manual_seed(2) model = ViTMSNForImageClassification.from_pretrained("facebook/vit-msn-small").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): diff --git a/tests/models/yolos/test_modeling_yolos.py b/tests/models/yolos/test_modeling_yolos.py index 209849394b..7c49bb864e 100644 --- a/tests/models/yolos/test_modeling_yolos.py +++ b/tests/models/yolos/test_modeling_yolos.py @@ -38,7 +38,7 @@ if is_torch_available(): if is_vision_available(): from PIL import Image - from transformers import AutoFeatureExtractor + from transformers import AutoImageProcessor class YolosModelTester: @@ -345,16 +345,16 @@ def prepare_img(): @require_vision class YolosModelIntegrationTest(unittest.TestCase): @cached_property - def default_feature_extractor(self): - return AutoFeatureExtractor.from_pretrained("hustvl/yolos-small") if is_vision_available() else None + def default_image_processor(self): + return AutoImageProcessor.from_pretrained("hustvl/yolos-small") if is_vision_available() else None @slow def test_inference_object_detection_head(self): model = YolosForObjectDetection.from_pretrained("hustvl/yolos-small").to(torch_device) - feature_extractor = self.default_feature_extractor + image_processor = self.default_image_processor image = prepare_img() - inputs = feature_extractor(images=image, return_tensors="pt").to(torch_device) + inputs = image_processor(images=image, return_tensors="pt").to(torch_device) # forward pass with torch.no_grad(): @@ -375,7 +375,7 @@ class YolosModelIntegrationTest(unittest.TestCase): self.assertTrue(torch.allclose(outputs.pred_boxes[0, :3, :3], expected_slice_boxes, atol=1e-4)) # verify postprocessing - results = feature_extractor.post_process_object_detection( + results = image_processor.post_process_object_detection( outputs, threshold=0.3, target_sizes=[image.size[::-1]] )[0] expected_scores = torch.tensor([0.9994, 0.9790, 0.9964, 0.9972, 0.9861]).to(torch_device)