[Feature] Register torchvision transforms into mmcls

[Ezra-Yu]

Motivation

Register torchvision transforms into mmcls

Modification

0. Add stochastic depth decay rule in resnet refer to [Enhance] Add stochastic depth decay rule in resnet #1363
1. Register torchvision transforms into mmcls;
2. update transform NumpyToPIL and PILToNumpy;

Use cases

1. Use some vision Augs Surrounded by NumpyToPIL and 'PILToNumpy (Recommendation)

Surrounded by dict(type='NumpyToPIL', to_rgb=True), and dict(type='PILToNumpy', to_bgr=True),

train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='NumpyToPIL', to_rgb=True),     # from BGR in cv2 to RGB  in PIL
    dict(type='torchvision/RandomResizedCrop',size=176),
    dict(type='PILToNumpy', to_bgr=True),     # from RGB  in PIL to BGR in cv2
    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
    dict(type='PackInputs'),
]

data_preprocessor = dict(
    num_classes=1000,
    mean=[123.675, 116.28, 103.53],
    std=[58.395, 57.12, 57.375],
    to_rgb=True,                          # from BGR in cv2 to RGB  in PIL
)

2. Use vision Augs and ToTensor&Normalize

Make sure have coverted to RGB-Numpy format; dict(type='NumpyToPIL', to_rgb=True)

train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='NumpyToPIL', to_rgb=True),       # from BGR in cv2 to RGB  in PIL
    dict(
        type='torchvision/RandomResizedCrop',
        size=176,
        interpolation=2),
    dict(type='torchvision/RandomHorizontalFlip', p=0.5),
    dict(
        type='torchvision/TrivialAugmentWide',
        interpolation=2),
    dict(type='torchvision/PILToTensor'),
    dict(type='torchvision/ConvertImageDtype', dtype=torch.float),
    dict(      
        type='torchvision/Normalize',  
        mean=(0.485, 0.456, 0.406),
        std=(0.229, 0.224, 0.225),
    ),
    dict(type='torchvision/RandomErasing', p=0.1),
    dict(type='PackInputs'),
]

data_preprocessor = dict(num_classes=1000, mean=None, std=None, to_rgb=False)  # Normalize in dataset pipeline

3. USe Augs but no ToTensor&Normalize

train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='NumpyToPIL', to_rgb=True),   # from BGR in cv2 to RGB  in PIL
    dict(type='torchvision/RandomResizedCrop', size=176, interpolation=2),
    dict(type='torchvision/RandomHorizontalFlip', p=0.5),
    dict(type='torchvision/TrivialAugmentWide', interpolation=2),
    dict(type='PackInputs'),
]

# here the Normalize params is for the RGB fromat
data_preprocessor = dict(
    num_classes=1000,
    mean=[123.675, 116.28, 103.53],
    std=[58.395, 57.12, 57.375],
    to_rgb=False,
)

Checklist

Before PR:

• Pre-commit or other linting tools are used to fix the potential lint issues.
• Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
• The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
• The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

• If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects, like MMDet or MMSeg.
• CLA has been signed and all committers have signed the CLA in this PR.

[codecov]

Codecov Report

Patch coverage has no change and project coverage change: +0.85 🎉

Comparison is base (c9a0cb0) 84.37% compared to head (6663729) 85.22%.

❗ Current head 6663729 differs from pull request most recent head e9f53be. Consider uploading reports for the commit e9f53be to get more accurate results

Additional details and impacted files

@@            Coverage Diff             @@
##              dev    #1265      +/-   ##
==========================================
+ Coverage   84.37%   85.22%   +0.85%     
==========================================
  Files         142      229      +87     
  Lines        9925    17311    +7386     
  Branches     1621     2715    +1094     
==========================================
+ Hits         8374    14753    +6379     
- Misses       1277     2056     +779     
- Partials      274      502     +228     

Flag	Coverage Δ
unittests	85.22% <ø> (+0.85%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

see 371 files with indirect coverage changes

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report in Codecov by Sentry.
📢 Do you have feedback about the report comment? Let us know in this issue.