From 7d1c1c5b212c0484ea6d6f30fdba0e0a0c45a25b Mon Sep 17 00:00:00 2001 From: Steven Liu <59462357+stevhliu@users.noreply.github.com> Date: Mon, 5 Dec 2022 11:49:43 -0800 Subject: [PATCH] Fix code sample in preprocess (#20561) * change to image_processor * apply review --- docs/source/en/preprocessing.mdx | 35 +++++--------------------------- 1 file changed, 5 insertions(+), 30 deletions(-) diff --git a/docs/source/en/preprocessing.mdx b/docs/source/en/preprocessing.mdx index 119055cf16..5283a9b17e 100644 --- a/docs/source/en/preprocessing.mdx +++ b/docs/source/en/preprocessing.mdx @@ -361,11 +361,11 @@ For computer vision tasks, it is common to add some type of data augmentation to ```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) >>> 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), 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! ```py ->>> dataset[0]["image"] -{'image': , - '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]]])} +>>> dataset[0].keys() ``` 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.