[Feature] Add MMClassification

.github/workflows/build_unit_test.yaml

@@ -26,7 +26,7 @@ jobs:
       run: |
           pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html
           pip install mmcv-full==1.4.7 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.9.0/index.html
-          pip install nevergrad mmdet mmsegmentation
+          pip install nevergrad mmcls mmdet mmsegmentation protobuf==3.20
           pip install -e .
     - name: Run unittests and generate coverage report
       run: |

configs/mmcls/_base_/datasets/cifar100_bs16.py

@@ -0,0 +1,36 @@
+# dataset settings
+dataset_type = 'CIFAR100'
+img_norm_cfg = dict(
+    mean=[129.304, 124.070, 112.434],
+    std=[68.170, 65.392, 70.418],
+    to_rgb=False)
+train_pipeline = [
+    dict(type='RandomCrop', size=32, padding=4),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+test_pipeline = [
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+data = dict(
+    samples_per_gpu=16,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/cifar100',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/cifar100',
+        pipeline=test_pipeline,
+        test_mode=True),
+    test=dict(
+        type=dataset_type,
+        data_prefix='data/cifar100',
+        pipeline=test_pipeline,
+        test_mode=True))

configs/mmcls/_base_/datasets/cifar10_bs16.py

@@ -0,0 +1,35 @@
+# dataset settings
+dataset_type = 'CIFAR10'
+img_norm_cfg = dict(
+    mean=[125.307, 122.961, 113.8575],
+    std=[51.5865, 50.847, 51.255],
+    to_rgb=False)
+train_pipeline = [
+    dict(type='RandomCrop', size=32, padding=4),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+test_pipeline = [
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+data = dict(
+    samples_per_gpu=16,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type, data_prefix='data/cifar10',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/cifar10',
+        pipeline=test_pipeline,
+        test_mode=True),
+    test=dict(
+        type=dataset_type,
+        data_prefix='data/cifar10',
+        pipeline=test_pipeline,
+        test_mode=True))

configs/mmcls/_base_/datasets/cub_bs8_384.py

@@ -0,0 +1,54 @@
+# dataset settings
+dataset_type = 'CUB'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', size=510),
+    dict(type='RandomCrop', size=384),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', size=510),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data_root = 'data/CUB_200_2011/'
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'images.txt',
+        image_class_labels_file=data_root + 'image_class_labels.txt',
+        train_test_split_file=data_root + 'train_test_split.txt',
+        data_prefix=data_root + 'images',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'images.txt',
+        image_class_labels_file=data_root + 'image_class_labels.txt',
+        train_test_split_file=data_root + 'train_test_split.txt',
+        data_prefix=data_root + 'images',
+        test_mode=True,
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'images.txt',
+        image_class_labels_file=data_root + 'image_class_labels.txt',
+        train_test_split_file=data_root + 'train_test_split.txt',
+        data_prefix=data_root + 'images',
+        test_mode=True,
+        pipeline=test_pipeline))
+
+evaluation = dict(
+    interval=1, metric='accuracy',
+    save_best='auto')  # save the checkpoint with highest accuracy

configs/mmcls/_base_/datasets/cub_bs8_448.py

@@ -0,0 +1,54 @@
+# dataset settings
+dataset_type = 'CUB'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', size=600),
+    dict(type='RandomCrop', size=448),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', size=600),
+    dict(type='CenterCrop', crop_size=448),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data_root = 'data/CUB_200_2011/'
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'images.txt',
+        image_class_labels_file=data_root + 'image_class_labels.txt',
+        train_test_split_file=data_root + 'train_test_split.txt',
+        data_prefix=data_root + 'images',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'images.txt',
+        image_class_labels_file=data_root + 'image_class_labels.txt',
+        train_test_split_file=data_root + 'train_test_split.txt',
+        data_prefix=data_root + 'images',
+        test_mode=True,
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'images.txt',
+        image_class_labels_file=data_root + 'image_class_labels.txt',
+        train_test_split_file=data_root + 'train_test_split.txt',
+        data_prefix=data_root + 'images',
+        test_mode=True,
+        pipeline=test_pipeline))
+
+evaluation = dict(
+    interval=1, metric='accuracy',
+    save_best='auto')  # save the checkpoint with highest accuracy

configs/mmcls/_base_/datasets/imagenet21k_bs128.py

@@ -0,0 +1,43 @@
+# dataset settings
+dataset_type = 'ImageNet21k'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', size=224),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', size=(256, -1)),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+data = dict(
+    samples_per_gpu=128,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet21k/train',
+        pipeline=train_pipeline,
+        recursion_subdir=True),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet21k/val',
+        ann_file='data/imagenet21k/meta/val.txt',
+        pipeline=test_pipeline,
+        recursion_subdir=True),
+    test=dict(
+        # replace `data/val` with `data/test` for standard test
+        type=dataset_type,
+        data_prefix='data/imagenet21k/val',
+        ann_file='data/imagenet21k/meta/val.txt',
+        pipeline=test_pipeline,
+        recursion_subdir=True))
+evaluation = dict(interval=1, metric='accuracy')

configs/mmcls/_base_/datasets/imagenet_bs128_poolformer_medium_224.py

@@ -0,0 +1,71 @@
+_base_ = ['./pipelines/rand_aug.py']
+
+# dataset settings
+dataset_type = 'ImageNet'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        size=224,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(
+        type='RandAugment',
+        policies={{_base_.rand_increasing_policies}},
+        num_policies=2,
+        total_level=10,
+        magnitude_level=9,
+        magnitude_std=0.5,
+        hparams=dict(
+            pad_val=[round(x) for x in img_norm_cfg['mean'][::-1]],
+            interpolation='bicubic')),
+    dict(
+        type='RandomErasing',
+        erase_prob=0.25,
+        mode='rand',
+        min_area_ratio=0.02,
+        max_area_ratio=1 / 3,
+        fill_color=img_norm_cfg['mean'][::-1],
+        fill_std=img_norm_cfg['std'][::-1]),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='Resize',
+        size=(236, -1),
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+data = dict(
+    samples_per_gpu=128,
+    workers_per_gpu=8,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        # replace `data/val` with `data/test` for standard test
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline))
+
+evaluation = dict(interval=10, metric='accuracy')

configs/mmcls/_base_/datasets/imagenet_bs128_poolformer_small_224.py

@@ -0,0 +1,71 @@
+_base_ = ['./pipelines/rand_aug.py']
+
+# dataset settings
+dataset_type = 'ImageNet'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        size=224,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(
+        type='RandAugment',
+        policies={{_base_.rand_increasing_policies}},
+        num_policies=2,
+        total_level=10,
+        magnitude_level=9,
+        magnitude_std=0.5,
+        hparams=dict(
+            pad_val=[round(x) for x in img_norm_cfg['mean'][::-1]],
+            interpolation='bicubic')),
+    dict(
+        type='RandomErasing',
+        erase_prob=0.25,
+        mode='rand',
+        min_area_ratio=0.02,
+        max_area_ratio=1 / 3,
+        fill_color=img_norm_cfg['mean'][::-1],
+        fill_std=img_norm_cfg['std'][::-1]),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='Resize',
+        size=(248, -1),
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+data = dict(
+    samples_per_gpu=128,
+    workers_per_gpu=8,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        # replace `data/val` with `data/test` for standard test
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline))
+
+evaluation = dict(interval=10, metric='accuracy')