Removal of deprecated vision methods and specify deprecation versions (#24570)

* Removal of deprecated methods and specify versions * Fix tests
2023-06-29 15:09:51 +01:00
parent 77db28dc52
commit b324557aac
32 changed files with 144 additions and 760 deletions
--- a/docs/source/en/model_doc/conditional_detr.md
+++ b/docs/source/en/model_doc/conditional_detr.md
@@ -43,7 +43,6 @@ This model was contributed by [DepuMeng](https://huggingface.co/DepuMeng). The o

 [[autodoc]] ConditionalDetrImageProcessor
    - preprocess
-    - pad_and_create_pixel_mask
    - post_process_object_detection
    - post_process_instance_segmentation
    - post_process_semantic_segmentation
@@ -53,7 +52,6 @@ This model was contributed by [DepuMeng](https://huggingface.co/DepuMeng). The o

 [[autodoc]] ConditionalDetrFeatureExtractor
    - __call__
-    - pad_and_create_pixel_mask
    - post_process_object_detection
    - post_process_instance_segmentation
    - post_process_semantic_segmentation
--- a/docs/source/en/model_doc/deformable_detr.md
+++ b/docs/source/en/model_doc/deformable_detr.md
@@ -52,14 +52,12 @@ If you're interested in submitting a resource to be included here, please feel f

 [[autodoc]] DeformableDetrImageProcessor
    - preprocess
-    - pad_and_create_pixel_mask
    - post_process_object_detection

 ## DeformableDetrFeatureExtractor

 [[autodoc]] DeformableDetrFeatureExtractor
    - __call__
-    - pad_and_create_pixel_mask
    - post_process_object_detection

 ## DeformableDetrConfig
--- a/docs/source/en/model_doc/detr.md
+++ b/docs/source/en/model_doc/detr.md
@@ -190,7 +190,6 @@ If you're interested in submitting a resource to be included here, please feel f

 [[autodoc]] DetrFeatureExtractor
    - __call__
-    - pad_and_create_pixel_mask
    - post_process_object_detection
    - post_process_semantic_segmentation
    - post_process_instance_segmentation
--- a/docs/source/en/preprocessing.md
+++ b/docs/source/en/preprocessing.md
@@ -62,8 +62,8 @@ Then pass your text to the tokenizer:
 ```py
 >>> encoded_input = tokenizer("Do not meddle in the affairs of wizards, for they are subtle and quick to anger.")
 >>> print(encoded_input)
-{'input_ids': [101, 2079, 2025, 19960, 10362, 1999, 1996, 3821, 1997, 16657, 1010, 2005, 2027, 2024, 11259, 1998, 4248, 2000, 4963, 1012, 102], 
- 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
+{'input_ids': [101, 2079, 2025, 19960, 10362, 1999, 1996, 3821, 1997, 16657, 1010, 2005, 2027, 2024, 11259, 1998, 4248, 2000, 4963, 1012, 102],
+ 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}
 ```

@@ -93,14 +93,14 @@ If there are several sentences you want to preprocess, pass them as a list to th
 ... ]
 >>> encoded_inputs = tokenizer(batch_sentences)
 >>> print(encoded_inputs)
-{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102], 
-               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102], 
-               [101, 1327, 1164, 5450, 23434, 136, 102]], 
- 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0], 
-                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
-                    [0, 0, 0, 0, 0, 0, 0]], 
- 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1], 
-                    [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 
+{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102],
+               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
+               [101, 1327, 1164, 5450, 23434, 136, 102]],
+ 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0],
+                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
+                    [0, 0, 0, 0, 0, 0, 0]],
+ 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1],
+                    [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                    [1, 1, 1, 1, 1, 1, 1]]}
 ```

@@ -118,14 +118,14 @@ Set the `padding` parameter to `True` to pad the shorter sequences in the batch
 ... ]
 >>> encoded_input = tokenizer(batch_sentences, padding=True)
 >>> print(encoded_input)
-{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0], 
-               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102], 
-               [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]], 
- 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
-                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
-                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 
- 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0], 
-                    [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 
+{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0],
+               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
+               [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]],
+ 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
+                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
+                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]],
+ 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
+                    [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                    [1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0]]}
 ```

@@ -145,14 +145,14 @@ Set the `truncation` parameter to `True` to truncate a sequence to the maximum l
 ... ]
 >>> encoded_input = tokenizer(batch_sentences, padding=True, truncation=True)
 >>> print(encoded_input)
-{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0], 
-               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102], 
-               [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]], 
- 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
-                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
-                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 
- 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0], 
-                    [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 
+{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0],
+               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
+               [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]],
+ 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
+                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
+                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]],
+ 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
+                    [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                    [1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0]]}
 ```

@@ -181,10 +181,10 @@ Set the `return_tensors` parameter to either `pt` for PyTorch, or `tf` for Tenso
 >>> print(encoded_input)
 {'input_ids': tensor([[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0],
                      [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
-                      [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]]), 
+                      [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]]),
 'token_type_ids': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
                           [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
-                           [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]), 
+                           [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]),
 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
                           [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                           [1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0]])}
@@ -203,11 +203,11 @@ Set the `return_tensors` parameter to either `pt` for PyTorch, or `tf` for Tenso
 array([[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0],
       [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
       [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]],
-      dtype=int32)>, 
+      dtype=int32)>,
 'token_type_ids': <tf.Tensor: shape=(2, 9), dtype=int32, numpy=
 array([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
       [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
-       [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], dtype=int32)>, 
+       [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], dtype=int32)>,
 'attention_mask': <tf.Tensor: shape=(2, 9), dtype=int32, numpy=
 array([[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
       [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
@@ -244,7 +244,7 @@ This returns three items:
 * `path` points to the location of the audio file.
 * `sampling_rate` refers to how many data points in the speech signal are measured per second.

-For this tutorial, you'll use the [Wav2Vec2](https://huggingface.co/facebook/wav2vec2-base) model. Take a look at the model card, and you'll learn Wav2Vec2 is pretrained on 16kHz sampled speech audio. It is important your audio data's sampling rate matches the sampling rate of the dataset used to pretrain the model. If your data's sampling rate isn't the same, then you need to resample your data. 
+For this tutorial, you'll use the [Wav2Vec2](https://huggingface.co/facebook/wav2vec2-base) model. Take a look at the model card, and you'll learn Wav2Vec2 is pretrained on 16kHz sampled speech audio. It is important your audio data's sampling rate matches the sampling rate of the dataset used to pretrain the model. If your data's sampling rate isn't the same, then you need to resample your data.

 1. Use 🤗 Datasets' [`~datasets.Dataset.cast_column`] method to upsample the sampling rate to 16kHz:

@@ -449,13 +449,13 @@ or segmentation maps.
 ### Pad

 In some cases, for instance, when fine-tuning [DETR](./model_doc/detr), the model applies scale augmentation at training
-time. This may cause images to be different sizes in a batch. You can use [`DetrImageProcessor.pad_and_create_pixel_mask`]
+time. This may cause images to be different sizes in a batch. You can use [`DetrImageProcessor.pad`]
 from [`DetrImageProcessor`] and define a custom `collate_fn` to batch images together.

 ```py
 >>> def collate_fn(batch):
 ...     pixel_values = [item["pixel_values"] for item in batch]
-...     encoding = image_processor.pad_and_create_pixel_mask(pixel_values, return_tensors="pt")
+...     encoding = image_processor.pad(pixel_values, return_tensors="pt")
 ...     labels = [item["labels"] for item in batch]
 ...     batch = {}
 ...     batch["pixel_values"] = encoding["pixel_values"]
--- a/docs/source/en/tasks/object_detection.md
+++ b/docs/source/en/tasks/object_detection.md
@@ -305,7 +305,7 @@ to indicate which pixels are real (1) and which are padding (0).
 ```py
 >>> def collate_fn(batch):
 ...     pixel_values = [item["pixel_values"] for item in batch]
-...     encoding = image_processor.pad_and_create_pixel_mask(pixel_values, return_tensors="pt")
+...     encoding = image_processor.pad(pixel_values, return_tensors="pt")
 ...     labels = [item["labels"] for item in batch]
 ...     batch = {}
 ...     batch["pixel_values"] = encoding["pixel_values"]