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

Fix code sample in preprocess (#20561)

Browse Source 
* change to image_processor

* apply review
This commit is contained in:
Steven Liu
2022-12-05 11:49:43 -08:00
committed by GitHub
parent 73ec12eafb
commit 7d1c1c5b21
1 changed files with 5 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
docs/source/en/preprocessing.mdx
View File

@@ -361,11 +361,11 @@ For computer vision tasks, it is common to add some type of data augmentation to
```py ```py
>>> from torchvision.transforms import Compose, Normalize, RandomResizedCrop, ColorJitter, ToTensor >>> 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)
>>> size = ( >>> size = (
... feature_extractor.size["shortest_edge"] ... image_processor.size["shortest_edge"]
... if "shortest_edge" in feature_extractor.size ... if "shortest_edge" in image_processor.size
... else (feature_extractor.size["height"], feature_extractor.size["width"]) ... else (image_processor.size["height"], image_processor.size["width"])
... ) ... )
>>> _transforms = Compose([RandomResizedCrop(size), ColorJitter(brightness=0.5, hue=0.5), ToTensor(), normalize]) >>> _transforms = Compose([RandomResizedCrop(size), ColorJitter(brightness=0.5, hue=0.5), ToTensor(), normalize])
``` ```
@@ -387,32 +387,7 @@ For computer vision tasks, it is common to add some type of data augmentation to
4. Now when you access the image, you'll notice the image processor has added `pixel_values`. You can pass your processed dataset to the model now! 4. Now when you access the image, you'll notice the image processor has added `pixel_values`. You can pass your processed dataset to the model now!
```py ```py
>>> dataset[0]["image"] >>> dataset[0].keys()
{'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=384x512 at 0x7F1A7B0630D0>,
'label': 6,
'pixel_values': tensor([[[ 0.0353, 0.0745, 0.1216, ..., -0.9922, -0.9922, -0.9922],
[-0.0196, 0.0667, 0.1294, ..., -0.9765, -0.9843, -0.9922],
[ 0.0196, 0.0824, 0.1137, ..., -0.9765, -0.9686, -0.8667],
...,
[ 0.0275, 0.0745, 0.0510, ..., -0.1137, -0.1216, -0.0824],
[ 0.0667, 0.0824, 0.0667, ..., -0.0588, -0.0745, -0.0980],
[ 0.0353, 0.0353, 0.0431, ..., -0.0039, -0.0039, -0.0588]],
[[ 0.2078, 0.2471, 0.2863, ..., -0.9451, -0.9373, -0.9451],
[ 0.1608, 0.2471, 0.3098, ..., -0.9373, -0.9451, -0.9373],
[ 0.2078, 0.2706, 0.3020, ..., -0.9608, -0.9373, -0.8275],
...,
[-0.0353, 0.0118, -0.0039, ..., -0.2392, -0.2471, -0.2078],
[ 0.0196, 0.0353, 0.0196, ..., -0.1843, -0.2000, -0.2235],
[-0.0118, -0.0039, -0.0039, ..., -0.0980, -0.0980, -0.1529]],
[[ 0.3961, 0.4431, 0.4980, ..., -0.9216, -0.9137, -0.9216],
[ 0.3569, 0.4510, 0.5216, ..., -0.9059, -0.9137, -0.9137],
[ 0.4118, 0.4745, 0.5216, ..., -0.9137, -0.8902, -0.7804],
...,
[-0.2314, -0.1922, -0.2078, ..., -0.4196, -0.4275, -0.3882],
[-0.1843, -0.1686, -0.2000, ..., -0.3647, -0.3804, -0.4039],
[-0.1922, -0.1922, -0.1922, ..., -0.2941, -0.2863, -0.3412]]])}
``` ```
Here is what the image looks like after the transforms are applied. The image has been randomly cropped and it's color properties are different. Here is what the image looks like after the transforms are applied. The image has been randomly cropped and it's color properties are different.