SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Update doc examples feature extractor -> image processor (#20501)

Browse Source 
* Update doc example feature extractor -> image processor

* Apply suggestions from code review
This commit is contained in:
amyeroberts
2022-11-30 14:50:55 +00:00
committed by GitHub
parent afad0c18d9
commit 17a7b49bda
84 changed files with 497 additions and 458 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
docs/source/en/tasks/image_classification.mdx
View File

@@ -91,26 +91,26 @@ Now you can convert the label id to a label name:
## Preprocess
The next step is to load a ViT feature extractor to process the image into a tensor:
The next step is to load a ViT image processor to process the image into a 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")
```
Apply some image transformations to the images to make the model more robust against overfitting. Here you'll use torchvision's [`transforms`](https://pytorch.org/vision/stable/transforms.html) module, but you can also use any image library you like.
Apply some image transformations to the images to make the model more robust against overfitting. Here you'll use torchvision's [`transforms`](https://pytorch.org/vision/stable/transforms.html) module, but you can also use any image library you like.
Crop a random part of the image, resize it, and normalize it with the image mean and standard deviation:
```py
>>> from torchvision.transforms import RandomResizedCrop, Compose, Normalize, 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)
>>> size = (
... feature_extractor.size["shortest_edge"]
... if "shortest_edge" in feature_extractor.size
... else (feature_extractor.size["height"], feature_extractor.size["width"])
... image_processor.size["shortest_edge"]
... if "shortest_edge" in image_processor.size
... else (image_processor.size["height"], image_processor.size["width"])
... )
>>> _transforms = Compose([RandomResizedCrop(size), ToTensor(), normalize])
```
@@ -213,7 +213,7 @@ At this point, only three steps remain:
... data_collator=data_collator,
... train_dataset=food["train"],
... eval_dataset=food["test"],
... tokenizer=feature_extractor,
... tokenizer=image_processor,
... compute_metrics=compute_metrics,
... )
@@ -266,14 +266,14 @@ You can also manually replicate the results of the `pipeline` if you'd like:
<frameworkcontent>
<pt>
Load a feature extractor to preprocess the image and return the `input` as PyTorch tensors:
Load an image processor to preprocess the image and return the `input` as PyTorch tensors:
```py
>>> from transformers import AutoFeatureExtractor
>>> from transformers import AutoImageProcessor
>>> import torch
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("my_awesome_food_model")
>>> inputs = feature_extractor(image, return_tensors="pt")
>>> image_processor = AutoImageProcessor.from_pretrained("my_awesome_food_model")
>>> inputs = image_processor(image, return_tensors="pt")
```
Pass your inputs to the model and return the logits: