[CI] Add mypy and mdformat

.pre-commit-config.yaml

@@ -1,7 +1,4 @@
 
-default_language_version:
-  ruby: 2.7.1
-
 exclude: ^tests/data/
 repos:
   - repo: https://github.com/PyCQA/flake8
@@ -33,6 +30,15 @@ repos:
     rev: v2.1.0
     hooks:
       - id: codespell
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.14
+    hooks:
+      - id: mdformat
+        args: ["--number"]
+        additional_dependencies:
+          - mdformat-gfm
+          - mdformat_frontmatter
+          - linkify-it-py
   - repo: https://github.com/myint/docformatter
     rev: v1.3.1
     hooks:
@@ -53,3 +59,12 @@ repos:
     -   id: check-algo-readme
     -   id: check-copyright
         args: [ "mmrazor", "tests", "tools"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.812
+    hooks:
+      - id: mypy
+        exclude: |-
+          (?x)(
+              ^test
+              | ^docs
+          )

README_zh-CN.md

@@ -85,12 +85,11 @@ MMRazor v0.3.1 版本已经在 2022.5.4 发布。
 
 ## 基准测试和模型库
 
-测试结果可以在 [模型库](docs/en/model_zoo.md) 中找到。
+测试结果可以在 [模型库](docs/en/model_zoo.md) 中找到.
 
 已经支持的算法：
 
-<details open>
-<summary>Neural Architecture Search</summary>
+Neural Architecture Search
 
 - [x] [DARTS(ICLR'2019)](configs/nas/darts)
 
@@ -98,24 +97,16 @@ MMRazor v0.3.1 版本已经在 2022.5.4 发布。
 
 - [x] [SPOS(ECCV'2020)](configs/nas/spos)
 
-</details>
-
-<details open>
-<summary>Pruning</summary>
+Pruning
 
 - [x] [AutoSlim(NeurIPS'2019)](/configs/pruning/autoslim)
 
-</details>
-
-<details open>
-<summary>Knowledge Distillation</summary>
+Knowledge Distillation
 
 - [x] [CWD(ICCV'2021)](/configs/distill/cwd)
 
 - [x] [WSLD(ICLR'2021)](/configs/distill/wsld)
 
-</details>
-
 ## 安装
 
 MMRazor 依赖 [PyTorch](https://pytorch.org/) 和 [MMCV](https://github.com/open-mmlab/mmcv)。
@@ -124,7 +115,7 @@ MMRazor 依赖 [PyTorch](https://pytorch.org/) 和 [MMCV](https://github.com/ope
 
 ## 快速入门
 
-请参考 [train.md](/docs/en/train.md) 和 [test.md](/docs/en/test.md) 学习 MMRazor 的基本使用。 我们也提供了一些进阶教程:
+请参考 [get_started.md](/docs/en/get_started.md) 学习 MMRazor 的基本使用。 我们也提供了一些进阶教程:
 
 - [overview](/docs/en/tutorials/Tutorial_1_overview.md)
 - [learn about configs](/docs/en/tutorials/Tutorial_2_learn_about_configs.md)

configs/_base_/datasets/mmcls/cifar100_bs16.py

@@ -1,36 +0,0 @@
-# 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/_base_/datasets/mmcls/cifar10_bs16.py

@@ -1,35 +0,0 @@
-# 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/_base_/datasets/mmcls/cifar10_bs96_cutout.py

@@ -1,36 +0,0 @@
-# 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='Cutout', shape=16, pad_val=0, prob=1.0),
-    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=96,
-    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/_base_/datasets/mmcls/imagenet_bs128_colorjittor.py

@@ -1,41 +0,0 @@
-# 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),
-    dict(type='ColorJitter', brightness=0.4, contrast=0.4, saturation=0.4),
-    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='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=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=1, metric='accuracy')

configs/_base_/datasets/mmcls/imagenet_bs256_autoslim.py

@@ -1,45 +0,0 @@
-# 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,
-        scale=(0.25, 1.0),
-        backend='pillow'),
-    dict(type='ColorJitter', brightness=0.4, contrast=0.4, saturation=0.4),
-    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='LoadImageFromFile'),
-    dict(type='Resize', size=(256, -1), backend='pillow'),
-    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=256,
-    workers_per_gpu=4,
-    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=1, metric='accuracy')

configs/_base_/datasets/mmcls/imagenet_bs32.py

@@ -1,40 +0,0 @@
-# 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),
-    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=32,
-    workers_per_gpu=2,
-    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=1, metric='accuracy')

configs/_base_/datasets/mmcls/imagenet_bs32_pil_resize.py

@@ -1,40 +0,0 @@
-# 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'),
-    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), backend='pillow'),
-    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=32,
-    workers_per_gpu=2,
-    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=1, metric='accuracy')

configs/_base_/datasets/mmcls/imagenet_bs64.py

@@ -1,40 +0,0 @@
-# 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),
-    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=64,
-    workers_per_gpu=2,
-    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=1, metric='accuracy')

configs/_base_/datasets/mmcls/imagenet_bs64_autoaug.py

@@ -1,43 +0,0 @@
-_base_ = ['./pipelines/auto_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),
-    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
-    dict(type='AutoAugment', policies={{_base_.auto_increasing_policies}}),
-    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=64,
-    workers_per_gpu=2,
-    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=1, metric='accuracy')

configs/_base_/datasets/mmcls/imagenet_bs64_pil_resize.py

@@ -1,40 +0,0 @@
-# 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'),
-    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), backend='pillow'),
-    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=64,
-    workers_per_gpu=2,
-    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=1, metric='accuracy')

configs/_base_/datasets/mmcls/imagenet_bs64_pil_resize_autoaug.py

@@ -1,45 +0,0 @@
-_base_ = [
-    'pipelines/auto_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'),
-    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
-    dict(type='AutoAugment', policies={{_base_.policy_imagenet}}),
-    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), backend='pillow'),
-    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=64,
-    workers_per_gpu=2,
-    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=1, metric='accuracy')

configs/_base_/datasets/mmcls/imagenet_bs64_swin_224.py

@@ -1,71 +0,0 @@
-_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=(256, -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=64,
-    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/_base_/datasets/mmcls/imagenet_bs64_swin_384.py

@@ -1,43 +0,0 @@
-# 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=384,
-        backend='pillow',
-        interpolation='bicubic'),
-    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=384, backend='pillow', interpolation='bicubic'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='ImageToTensor', keys=['img']),
-    dict(type='Collect', keys=['img'])
-]
-data = dict(
-    samples_per_gpu=64,
-    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/_base_/datasets/mmdet/cityscapes_detection.py

@@ -1,56 +0,0 @@
-# dataset settings
-dataset_type = 'CityscapesDataset'
-data_root = 'data/cityscapes/'
-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='LoadAnnotations', with_bbox=True),
-    dict(
-        type='Resize', img_scale=[(2048, 800), (2048, 1024)], keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 1024),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=1,
-    workers_per_gpu=2,
-    train=dict(
-        type='RepeatDataset',
-        times=8,
-        dataset=dict(
-            type=dataset_type,
-            ann_file=data_root +
-            'annotations/instancesonly_filtered_gtFine_train.json',
-            img_prefix=data_root + 'leftImg8bit/train/',
-            pipeline=train_pipeline)),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root +
-        'annotations/instancesonly_filtered_gtFine_val.json',
-        img_prefix=data_root + 'leftImg8bit/val/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root +
-        'annotations/instancesonly_filtered_gtFine_test.json',
-        img_prefix=data_root + 'leftImg8bit/test/',
-        pipeline=test_pipeline))
-evaluation = dict(interval=1, metric='bbox')

configs/_base_/datasets/mmdet/cityscapes_instance.py

@@ -1,56 +0,0 @@
-# dataset settings
-dataset_type = 'CityscapesDataset'
-data_root = 'data/cityscapes/'
-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='LoadAnnotations', with_bbox=True, with_mask=True),
-    dict(
-        type='Resize', img_scale=[(2048, 800), (2048, 1024)], keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 1024),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=1,
-    workers_per_gpu=2,
-    train=dict(
-        type='RepeatDataset',
-        times=8,
-        dataset=dict(
-            type=dataset_type,
-            ann_file=data_root +
-            'annotations/instancesonly_filtered_gtFine_train.json',
-            img_prefix=data_root + 'leftImg8bit/train/',
-            pipeline=train_pipeline)),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root +
-        'annotations/instancesonly_filtered_gtFine_val.json',
-        img_prefix=data_root + 'leftImg8bit/val/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root +
-        'annotations/instancesonly_filtered_gtFine_test.json',
-        img_prefix=data_root + 'leftImg8bit/test/',
-        pipeline=test_pipeline))
-evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/mmdet/coco_detection.py

@@ -1,49 +0,0 @@
-# dataset settings
-dataset_type = 'CocoDataset'
-data_root = 'data/coco/'
-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='LoadAnnotations', with_bbox=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1333, 800),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_train2017.json',
-        img_prefix=data_root + 'train2017/',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline))
-evaluation = dict(interval=1, metric='bbox')

configs/_base_/datasets/mmdet/coco_instance.py

@@ -1,49 +0,0 @@
-# dataset settings
-dataset_type = 'CocoDataset'
-data_root = 'data/coco/'
-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='LoadAnnotations', with_bbox=True, with_mask=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1333, 800),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_train2017.json',
-        img_prefix=data_root + 'train2017/',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline))
-evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/mmdet/coco_instance_semantic.py

@@ -1,54 +0,0 @@
-# dataset settings
-dataset_type = 'CocoDataset'
-data_root = 'data/coco/'
-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='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='SegRescale', scale_factor=1 / 8),
-    dict(type='DefaultFormatBundle'),
-    dict(
-        type='Collect',
-        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1333, 800),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip', flip_ratio=0.5),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_train2017.json',
-        img_prefix=data_root + 'train2017/',
-        seg_prefix=data_root + 'stuffthingmaps/train2017/',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline))
-evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/mmdet/coco_panoptic.py

@@ -1,59 +0,0 @@
-# dataset settings
-dataset_type = 'CocoPanopticDataset'
-data_root = 'data/coco/'
-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='LoadPanopticAnnotations',
-        with_bbox=True,
-        with_mask=True,
-        with_seg=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='SegRescale', scale_factor=1 / 4),
-    dict(type='DefaultFormatBundle'),
-    dict(
-        type='Collect',
-        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1333, 800),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/panoptic_train2017.json',
-        img_prefix=data_root + 'train2017/',
-        seg_prefix=data_root + 'annotations/panoptic_train2017/',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/panoptic_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        seg_prefix=data_root + 'annotations/panoptic_val2017/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/panoptic_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        seg_prefix=data_root + 'annotations/panoptic_val2017/',
-        pipeline=test_pipeline))
-evaluation = dict(interval=1, metric=['PQ'])

configs/_base_/datasets/mmdet/deepfashion.py

@@ -1,53 +0,0 @@
-# dataset settings
-dataset_type = 'DeepFashionDataset'
-data_root = 'data/DeepFashion/In-shop/'
-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='LoadAnnotations', with_bbox=True, with_mask=True),
-    dict(type='Resize', img_scale=(750, 1101), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(750, 1101),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    imgs_per_gpu=2,
-    workers_per_gpu=1,
-    train=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/DeepFashion_segmentation_query.json',
-        img_prefix=data_root + 'Img/',
-        pipeline=train_pipeline,
-        data_root=data_root),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/DeepFashion_segmentation_query.json',
-        img_prefix=data_root + 'Img/',
-        pipeline=test_pipeline,
-        data_root=data_root),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root +
-        'annotations/DeepFashion_segmentation_gallery.json',
-        img_prefix=data_root + 'Img/',
-        pipeline=test_pipeline,
-        data_root=data_root))
-evaluation = dict(interval=5, metric=['bbox', 'segm'])

configs/_base_/datasets/mmdet/lvis_v0.5_instance.py

@@ -1,24 +0,0 @@
-# dataset settings
-_base_ = 'coco_instance.py'
-dataset_type = 'LVISV05Dataset'
-data_root = 'data/lvis_v0.5/'
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        _delete_=True,
-        type='ClassBalancedDataset',
-        oversample_thr=1e-3,
-        dataset=dict(
-            type=dataset_type,
-            ann_file=data_root + 'annotations/lvis_v0.5_train.json',
-            img_prefix=data_root + 'train2017/')),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/lvis_v0.5_val.json',
-        img_prefix=data_root + 'val2017/'),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/lvis_v0.5_val.json',
-        img_prefix=data_root + 'val2017/'))
-evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/mmdet/lvis_v1_instance.py

@@ -1,24 +0,0 @@
-# dataset settings
-_base_ = 'coco_instance.py'
-dataset_type = 'LVISV1Dataset'
-data_root = 'data/lvis_v1/'
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        _delete_=True,
-        type='ClassBalancedDataset',
-        oversample_thr=1e-3,
-        dataset=dict(
-            type=dataset_type,
-            ann_file=data_root + 'annotations/lvis_v1_train.json',
-            img_prefix=data_root)),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/lvis_v1_val.json',
-        img_prefix=data_root),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/lvis_v1_val.json',
-        img_prefix=data_root))
-evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/mmdet/voc0712.py

@@ -1,55 +0,0 @@
-# dataset settings
-dataset_type = 'VOCDataset'
-data_root = 'data/VOCdevkit/'
-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='LoadAnnotations', with_bbox=True),
-    dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1000, 600),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type='RepeatDataset',
-        times=3,
-        dataset=dict(
-            type=dataset_type,
-            ann_file=[
-                data_root + 'VOC2007/ImageSets/Main/trainval.txt',
-                data_root + 'VOC2012/ImageSets/Main/trainval.txt'
-            ],
-            img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
-            pipeline=train_pipeline)),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
-        img_prefix=data_root + 'VOC2007/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
-        img_prefix=data_root + 'VOC2007/',
-        pipeline=test_pipeline))
-evaluation = dict(interval=1, metric='mAP')

configs/_base_/datasets/mmdet/wider_face.py

@@ -1,63 +0,0 @@
-# dataset settings
-dataset_type = 'WIDERFaceDataset'
-data_root = 'data/WIDERFace/'
-img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
-train_pipeline = [
-    dict(type='LoadImageFromFile', to_float32=True),
-    dict(type='LoadAnnotations', with_bbox=True),
-    dict(
-        type='PhotoMetricDistortion',
-        brightness_delta=32,
-        contrast_range=(0.5, 1.5),
-        saturation_range=(0.5, 1.5),
-        hue_delta=18),
-    dict(
-        type='Expand',
-        mean=img_norm_cfg['mean'],
-        to_rgb=img_norm_cfg['to_rgb'],
-        ratio_range=(1, 4)),
-    dict(
-        type='MinIoURandomCrop',
-        min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
-        min_crop_size=0.3),
-    dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(300, 300),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=False),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=60,
-    workers_per_gpu=2,
-    train=dict(
-        type='RepeatDataset',
-        times=2,
-        dataset=dict(
-            type=dataset_type,
-            ann_file=data_root + 'train.txt',
-            img_prefix=data_root + 'WIDER_train/',
-            min_size=17,
-            pipeline=train_pipeline)),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'val.txt',
-        img_prefix=data_root + 'WIDER_val/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'val.txt',
-        img_prefix=data_root + 'WIDER_val/',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/ade20k.py

@@ -1,54 +0,0 @@
-# dataset settings
-dataset_type = 'ADE20KDataset'
-data_root = 'data/ade/ADEChallengeData2016'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-crop_size = (512, 512)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations', reduce_zero_label=True),
-    dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 512),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/training',
-        ann_dir='annotations/training',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/chase_db1.py

@@ -1,59 +0,0 @@
-# dataset settings
-dataset_type = 'ChaseDB1Dataset'
-data_root = 'data/CHASE_DB1'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-img_scale = (960, 999)
-crop_size = (128, 128)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=img_scale,
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img'])
-        ])
-]
-
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type='RepeatDataset',
-        times=40000,
-        dataset=dict(
-            type=dataset_type,
-            data_root=data_root,
-            img_dir='images/training',
-            ann_dir='annotations/training',
-            pipeline=train_pipeline)),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/cityscapes.py

@@ -1,54 +0,0 @@
-# dataset settings
-dataset_type = 'CityscapesDataset'
-data_root = 'data/cityscapes/'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-crop_size = (512, 1024)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 1024),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='leftImg8bit/train',
-        ann_dir='gtFine/train',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='leftImg8bit/val',
-        ann_dir='gtFine/val',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='leftImg8bit/val',
-        ann_dir='gtFine/val',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/cityscapes_1024x1024.py

@@ -1,35 +0,0 @@
-_base_ = './cityscapes.py'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-crop_size = (1024, 1024)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 1024),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    train=dict(pipeline=train_pipeline),
-    val=dict(pipeline=test_pipeline),
-    test=dict(pipeline=test_pipeline))

configs/_base_/datasets/mmseg/cityscapes_769x769.py

@@ -1,35 +0,0 @@
-_base_ = './cityscapes.py'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-crop_size = (769, 769)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2049, 1025),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    train=dict(pipeline=train_pipeline),
-    val=dict(pipeline=test_pipeline),
-    test=dict(pipeline=test_pipeline))

configs/_base_/datasets/mmseg/cityscapes_832x832.py

@@ -1,35 +0,0 @@
-_base_ = './cityscapes.py'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-crop_size = (832, 832)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 1024),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    train=dict(pipeline=train_pipeline),
-    val=dict(pipeline=test_pipeline),
-    test=dict(pipeline=test_pipeline))

configs/_base_/datasets/mmseg/coco-stuff10k.py

@@ -1,57 +0,0 @@
-# dataset settings
-dataset_type = 'COCOStuffDataset'
-data_root = 'data/coco_stuff10k'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-crop_size = (512, 512)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations', reduce_zero_label=True),
-    dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 512),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        reduce_zero_label=True,
-        img_dir='images/train2014',
-        ann_dir='annotations/train2014',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        reduce_zero_label=True,
-        img_dir='images/test2014',
-        ann_dir='annotations/test2014',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        reduce_zero_label=True,
-        img_dir='images/test2014',
-        ann_dir='annotations/test2014',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/coco-stuff164k.py

@@ -1,54 +0,0 @@
-# dataset settings
-dataset_type = 'COCOStuffDataset'
-data_root = 'data/coco_stuff164k'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-crop_size = (512, 512)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 512),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/train2017',
-        ann_dir='annotations/train2017',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/val2017',
-        ann_dir='annotations/val2017',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/val2017',
-        ann_dir='annotations/val2017',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/drive.py

@@ -1,59 +0,0 @@
-# dataset settings
-dataset_type = 'DRIVEDataset'
-data_root = 'data/DRIVE'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-img_scale = (584, 565)
-crop_size = (64, 64)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=img_scale,
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img'])
-        ])
-]
-
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type='RepeatDataset',
-        times=40000,
-        dataset=dict(
-            type=dataset_type,
-            data_root=data_root,
-            img_dir='images/training',
-            ann_dir='annotations/training',
-            pipeline=train_pipeline)),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/hrf.py

@@ -1,59 +0,0 @@
-# dataset settings
-dataset_type = 'HRFDataset'
-data_root = 'data/HRF'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-img_scale = (2336, 3504)
-crop_size = (256, 256)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=img_scale,
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img'])
-        ])
-]
-
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type='RepeatDataset',
-        times=40000,
-        dataset=dict(
-            type=dataset_type,
-            data_root=data_root,
-            img_dir='images/training',
-            ann_dir='annotations/training',
-            pipeline=train_pipeline)),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/pascal_context.py

@@ -1,60 +0,0 @@
-# dataset settings
-dataset_type = 'PascalContextDataset'
-data_root = 'data/VOCdevkit/VOC2010/'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-
-img_scale = (520, 520)
-crop_size = (480, 480)
-
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=img_scale,
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClassContext',
-        split='ImageSets/SegmentationContext/train.txt',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClassContext',
-        split='ImageSets/SegmentationContext/val.txt',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClassContext',
-        split='ImageSets/SegmentationContext/val.txt',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/pascal_context_59.py

@@ -1,60 +0,0 @@
-# dataset settings
-dataset_type = 'PascalContextDataset59'
-data_root = 'data/VOCdevkit/VOC2010/'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-
-img_scale = (520, 520)
-crop_size = (480, 480)
-
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations', reduce_zero_label=True),
-    dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=img_scale,
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClassContext',
-        split='ImageSets/SegmentationContext/train.txt',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClassContext',
-        split='ImageSets/SegmentationContext/val.txt',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClassContext',
-        split='ImageSets/SegmentationContext/val.txt',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/pascal_voc12.py

@@ -1,57 +0,0 @@
-# dataset settings
-dataset_type = 'PascalVOCDataset'
-data_root = 'data/VOCdevkit/VOC2012'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-crop_size = (512, 512)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 512),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClass',
-        split='ImageSets/Segmentation/train.txt',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClass',
-        split='ImageSets/Segmentation/val.txt',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='JPEGImages',
-        ann_dir='SegmentationClass',
-        split='ImageSets/Segmentation/val.txt',
-        pipeline=test_pipeline))

configs/_base_/datasets/mmseg/pascal_voc12_aug.py

@@ -1,9 +0,0 @@
-_base_ = './pascal_voc12.py'
-# dataset settings
-data = dict(
-    train=dict(
-        ann_dir=['SegmentationClass', 'SegmentationClassAug'],
-        split=[
-            'ImageSets/Segmentation/train.txt',
-            'ImageSets/Segmentation/aug.txt'
-        ]))

configs/_base_/datasets/mmseg/stare.py

@@ -1,59 +0,0 @@
-# dataset settings
-dataset_type = 'STAREDataset'
-data_root = 'data/STARE'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-img_scale = (605, 700)
-crop_size = (128, 128)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations'),
-    dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
-    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
-    dict(type='RandomFlip', prob=0.5),
-    dict(type='PhotoMetricDistortion'),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=img_scale,
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img'])
-        ])
-]
-
-data = dict(
-    samples_per_gpu=4,
-    workers_per_gpu=4,
-    train=dict(
-        type='RepeatDataset',
-        times=40000,
-        dataset=dict(
-            type=dataset_type,
-            data_root=data_root,
-            img_dir='images/training',
-            ann_dir='annotations/training',
-            pipeline=train_pipeline)),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        img_dir='images/validation',
-        ann_dir='annotations/validation',
-        pipeline=test_pipeline))

configs/_base_/mmcls_runtime.py

@@ -1,16 +0,0 @@
-# checkpoint saving
-checkpoint_config = dict(interval=1)
-# yapf:disable
-log_config = dict(
-    interval=100,
-    hooks=[
-        dict(type='TextLoggerHook'),
-        # dict(type='TensorboardLoggerHook')
-    ])
-# yapf:enable
-
-dist_params = dict(backend='nccl')
-log_level = 'INFO'
-load_from = None
-resume_from = None
-workflow = [('train', 1)]

configs/_base_/mmdet_runtime.py

@@ -1,16 +0,0 @@
-checkpoint_config = dict(interval=1)
-# yapf:disable
-log_config = dict(
-    interval=50,
-    hooks=[
-        dict(type='TextLoggerHook'),
-        # dict(type='TensorboardLoggerHook')
-    ])
-# yapf:enable
-custom_hooks = [dict(type='NumClassCheckHook')]
-
-dist_params = dict(backend='nccl')
-log_level = 'INFO'
-load_from = None
-resume_from = None
-workflow = [('train', 1)]

configs/_base_/mmseg_runtime.py

@@ -1,14 +0,0 @@
-# yapf:disable
-log_config = dict(
-    interval=50,
-    hooks=[
-        dict(type='TextLoggerHook', by_epoch=False),
-        # dict(type='TensorboardLoggerHook')
-    ])
-# yapf:enable
-dist_params = dict(backend='nccl')
-log_level = 'INFO'
-load_from = None
-resume_from = None
-workflow = [('train', 1)]
-cudnn_benchmark = True

configs/_base_/schedules/mmcls/cifar10_bs128.py

@@ -1,6 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(policy='step', step=[100, 150])
-runner = dict(type='EpochBasedRunner', max_epochs=200)

configs/_base_/schedules/mmcls/imagenet_bs1024_adamw_swin.py

@@ -1,30 +0,0 @@
-paramwise_cfg = dict(
-    norm_decay_mult=0.0,
-    bias_decay_mult=0.0,
-    custom_keys={
-        '.absolute_pos_embed': dict(decay_mult=0.0),
-        '.relative_position_bias_table': dict(decay_mult=0.0)
-    })
-
-# for batch in each gpu is 128, 8 gpu
-# lr = 5e-4 * 128 * 8 / 512 = 0.001
-optimizer = dict(
-    type='AdamW',
-    lr=5e-4 * 128 * 8 / 512,
-    weight_decay=0.05,
-    eps=1e-8,
-    betas=(0.9, 0.999),
-    paramwise_cfg=paramwise_cfg)
-optimizer_config = dict(grad_clip=dict(max_norm=5.0))
-
-# learning policy
-lr_config = dict(
-    policy='CosineAnnealing',
-    by_epoch=False,
-    min_lr_ratio=1e-2,
-    warmup='linear',
-    warmup_ratio=1e-3,
-    warmup_iters=20 * 1252,
-    warmup_by_epoch=False)
-
-runner = dict(type='EpochBasedRunner', max_epochs=300)

configs/_base_/schedules/mmcls/imagenet_bs1024_linearlr_bn_nowd.py

@@ -1,17 +0,0 @@
-# optimizer
-optimizer = dict(
-    type='SGD',
-    lr=0.5,
-    momentum=0.9,
-    weight_decay=0.00004,
-    paramwise_cfg=dict(norm_decay_mult=0))
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(
-    policy='poly',
-    min_lr=0,
-    by_epoch=False,
-    warmup='constant',
-    warmup_iters=5000,
-)
-runner = dict(type='EpochBasedRunner', max_epochs=300)

configs/_base_/schedules/mmcls/imagenet_bs1024_spos.py

@@ -1,12 +0,0 @@
-# optimizer
-paramwise_cfg = dict(bias_decay_mult=0.0, norm_decay_mult=0.0)
-optimizer = dict(
-    type='SGD',
-    lr=0.5,
-    momentum=0.9,
-    weight_decay=4e-5,
-    paramwise_cfg=paramwise_cfg)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(policy='poly', power=1.0, min_lr=0.0, by_epoch=False)
-runner = dict(type='IterBasedRunner', max_iters=300000)

configs/_base_/schedules/mmcls/imagenet_bs2048.py

@@ -1,12 +0,0 @@
-# optimizer
-optimizer = dict(
-    type='SGD', lr=0.8, momentum=0.9, weight_decay=0.0001, nesterov=True)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(
-    policy='step',
-    warmup='linear',
-    warmup_iters=2500,
-    warmup_ratio=0.25,
-    step=[30, 60, 90])
-runner = dict(type='EpochBasedRunner', max_epochs=100)

configs/_base_/schedules/mmcls/imagenet_bs2048_AdamW.py

@@ -1,20 +0,0 @@
-# optimizer
-# In ClassyVision, the lr is set to 0.003 for bs4096.
-# In this implementation(bs2048), lr = 0.003 / 4096 * (32bs * 64gpus) = 0.0015
-optimizer = dict(type='AdamW', lr=0.0015, weight_decay=0.3)
-optimizer_config = dict(grad_clip=dict(max_norm=1.0))
-
-# specific to vit pretrain
-paramwise_cfg = dict(
-    custom_keys={
-        '.backbone.cls_token': dict(decay_mult=0.0),
-        '.backbone.pos_embed': dict(decay_mult=0.0)
-    })
-# learning policy
-lr_config = dict(
-    policy='CosineAnnealing',
-    min_lr=0,
-    warmup='linear',
-    warmup_iters=10000,
-    warmup_ratio=1e-4)
-runner = dict(type='EpochBasedRunner', max_epochs=300)

configs/_base_/schedules/mmcls/imagenet_bs2048_autoslim.py

@@ -1,16 +0,0 @@
-# optimizer
-paramwise_cfg = dict(
-    bias_decay_mult=0.0, norm_decay_mult=0.0, dwconv_decay_mult=0.0)
-optimizer = dict(
-    type='SGD',
-    lr=0.5,
-    momentum=0.9,
-    nesterov=True,
-    weight_decay=0.0001,
-    paramwise_cfg=paramwise_cfg)
-
-optimizer_config = None
-
-# learning policy
-lr_config = dict(policy='poly', power=1.0, min_lr=0.0, by_epoch=False)
-runner = dict(type='EpochBasedRunner', max_epochs=300)

configs/_base_/schedules/mmcls/imagenet_bs2048_coslr.py

@@ -1,12 +0,0 @@
-# optimizer
-optimizer = dict(
-    type='SGD', lr=0.8, momentum=0.9, weight_decay=0.0001, nesterov=True)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(
-    policy='CosineAnnealing',
-    min_lr=0,
-    warmup='linear',
-    warmup_iters=2500,
-    warmup_ratio=0.25)
-runner = dict(type='EpochBasedRunner', max_epochs=100)

configs/_base_/schedules/mmcls/imagenet_bs256.py

@@ -1,6 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(policy='step', step=[30, 60, 90])
-runner = dict(type='EpochBasedRunner', max_epochs=100)

configs/_base_/schedules/mmcls/imagenet_bs256_140e.py

@@ -1,6 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(policy='step', step=[40, 80, 120])
-runner = dict(type='EpochBasedRunner', max_epochs=140)

configs/_base_/schedules/mmcls/imagenet_bs256_200e_coslr_warmup.py

@@ -1,11 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(
-    policy='CosineAnnealing',
-    min_lr=0,
-    warmup='linear',
-    warmup_iters=25025,
-    warmup_ratio=0.25)
-runner = dict(type='EpochBasedRunner', max_epochs=200)

configs/_base_/schedules/mmcls/imagenet_bs256_coslr.py

@@ -1,6 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(policy='CosineAnnealing', min_lr=0)
-runner = dict(type='EpochBasedRunner', max_epochs=100)

configs/_base_/schedules/mmcls/imagenet_bs256_epochstep.py

@@ -1,6 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.045, momentum=0.9, weight_decay=0.00004)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(policy='step', gamma=0.98, step=1)
-runner = dict(type='EpochBasedRunner', max_epochs=300)

configs/_base_/schedules/mmcls/imagenet_bs4096_AdamW.py

@@ -1,18 +0,0 @@
-# optimizer
-optimizer = dict(type='AdamW', lr=0.003, weight_decay=0.3)
-optimizer_config = dict(grad_clip=dict(max_norm=1.0))
-
-# specific to vit pretrain
-paramwise_cfg = dict(
-    custom_keys={
-        '.backbone.cls_token': dict(decay_mult=0.0),
-        '.backbone.pos_embed': dict(decay_mult=0.0)
-    })
-# learning policy
-lr_config = dict(
-    policy='CosineAnnealing',
-    min_lr=0,
-    warmup='linear',
-    warmup_iters=10000,
-    warmup_ratio=1e-4)
-runner = dict(type='EpochBasedRunner', max_epochs=300)

configs/_base_/schedules/mmdet/schedule_1x.py

@@ -1,11 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(
-    policy='step',
-    warmup='linear',
-    warmup_iters=500,
-    warmup_ratio=0.001,
-    step=[8, 11])
-runner = dict(type='EpochBasedRunner', max_epochs=12)

configs/_base_/schedules/mmdet/schedule_2x.py

@@ -1,11 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
-optimizer_config = dict(grad_clip=None)
-# learning policy
-lr_config = dict(
-    policy='step',
-    warmup='linear',
-    warmup_iters=500,
-    warmup_ratio=0.001,
-    step=[16, 22])
-runner = dict(type='EpochBasedRunner', max_epochs=24)

configs/_base_/schedules/mmseg/schedule_160k.py

@@ -1,9 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
-optimizer_config = dict()
-# learning policy
-lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
-# runtime settings
-runner = dict(type='IterBasedRunner', max_iters=160000)
-checkpoint_config = dict(by_epoch=False, interval=16000)
-evaluation = dict(interval=16000, metric='mIoU', pre_eval=True)

configs/_base_/schedules/mmseg/schedule_20k.py

@@ -1,9 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
-optimizer_config = dict()
-# learning policy
-lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
-# runtime settings
-runner = dict(type='IterBasedRunner', max_iters=20000)
-checkpoint_config = dict(by_epoch=False, interval=2000)
-evaluation = dict(interval=2000, metric='mIoU', pre_eval=True)

configs/_base_/schedules/mmseg/schedule_320k.py

@@ -1,9 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
-optimizer_config = dict()
-# learning policy
-lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
-# runtime settings
-runner = dict(type='IterBasedRunner', max_iters=320000)
-checkpoint_config = dict(by_epoch=False, interval=32000)
-evaluation = dict(interval=32000, metric='mIoU')

configs/_base_/schedules/mmseg/schedule_40k.py

@@ -1,9 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
-optimizer_config = dict()
-# learning policy
-lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
-# runtime settings
-runner = dict(type='IterBasedRunner', max_iters=40000)
-checkpoint_config = dict(by_epoch=False, interval=4000)
-evaluation = dict(interval=4000, metric='mIoU', pre_eval=True)

configs/_base_/schedules/mmseg/schedule_80k.py

@@ -1,9 +0,0 @@
-# optimizer
-optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
-optimizer_config = dict()
-# learning policy
-lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
-# runtime settings
-runner = dict(type='IterBasedRunner', max_iters=80000)
-checkpoint_config = dict(by_epoch=False, interval=8000)
-evaluation = dict(interval=8000, metric='mIoU', pre_eval=True)

configs/detnas_supernet_shufflenetv2_coco_1x_2.0_example.py

@@ -62,7 +62,7 @@ test_evaluator = val_evaluator
 # training schedule for 1x
 train_cfg = dict(by_epoch=True, max_epochs=12)
 val_cfg = dict(interval=1)
-test_cfg = dict()
+test_cfg = dict()  # type: ignore
 
 # learning rate
 param_scheduler = [

configs/distill/cwd/README.md

@@ -14,9 +14,9 @@ Knowledge distillation (KD) has been proven to be a simple and effective tool fo
 
 ### Segmentation
 
-| Location |  Dataset   |                                                             Teacher                                                              |                                                            Student                                                             | mIoU  | mIoU(T) | mIou(S) |    Config    | Download                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
-| :------: | :--------: | :------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------: | :---: | :-----: | :-----: | :----------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-|  logits  | cityscapes | [pspnet_r101](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py) | [pspnet_r18](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes.py) | 75.54 |  79.76  |  74.87  | [config](<>) | [teacher](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth) \|[model](https://download.openmmlab.com/mmrazor/v0.1/distill/cwd/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k_mIoU-75.54_20211222-3a26ee1c.pth) \| [log](https://download.openmmlab.com/mmrazor/v0.1/distill/cwd/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k_20211212_205711.log.json) |
+| Location |  Dataset   |                                                             Teacher                                                              |                                                            Student                                                             | mIoU  | mIoU(T) | mIou(S) |    Config    | Download                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| :------: | :--------: | :------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------: | :---: | :-----: | :-----: | :----------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+|  logits  | cityscapes | [pspnet_r101](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py) | [pspnet_r18](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r18-d8_512x1024_80k_cityscapes.py) | 75.54 |  79.76  |  74.87  | [config](<>) | [teacher](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth) \|[model](https://download.openmmlab.com/mmrazor/v0.1/distill/cwd/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k_mIoU-75.54_20211222-3a26ee1c.pth) \| [log](https://download.openmmlab.com/mmrazor/v0.1/distill/cwd/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k/cwd_cls_head_pspnet_r101_d8_pspnet_r18_d8_512x1024_cityscapes_80k_20211212_205711.log.json?) |
 
 ### Detection
 

mmrazor/apis/__init__.py

@@ -1,4 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-from .mmcls import *  # noqa: F401,F403
-from .mmdet import *  # noqa: F401,F403
-from .mmseg import *  # noqa: F401,F403

mmrazor/apis/mmcls/__init__.py

@@ -1,4 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-from .inference import init_mmcls_model
-
-__all__ = ['init_mmcls_model']

mmrazor/apis/mmcls/inference.py

@@ -1,58 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import warnings
-from typing import Dict, Optional, Union
-
-import mmcv
-from mmcv.runner import load_checkpoint
-from torch import nn
-
-from mmrazor.models import build_algorithm
-
-
-def init_mmcls_model(config: Union[str, mmcv.Config],
-                     checkpoint: Optional[str] = None,
-                     device: str = 'cuda:0',
-                     cfg_options: Optional[Dict] = None) -> nn.Module:
-    """Initialize a mmcls model from config file.
-
-    Args:
-        config (str or :obj:`mmcv.Config`): Config file path or the config
-            object.
-        checkpoint (str, optional): Checkpoint path. If left as None, the model
-            will not load any weights.
-        cfg_options (dict): cfg_options to override some settings in the used
-            config.
-
-    Returns:
-        nn.Module: The constructed classifier.
-    """
-    if isinstance(config, str):
-        config = mmcv.Config.fromfile(config)
-    elif not isinstance(config, mmcv.Config):
-        raise TypeError('config must be a filename or Config object, '
-                        f'but got {type(config)}')
-    if cfg_options is not None:
-        config.merge_from_dict(cfg_options)
-
-    model_cfg = config.algorithm.architecture.model
-    model_cfg.pretrained = None
-    algorithm = build_algorithm(config.algorithm)
-    model = algorithm.architecture.model
-
-    if checkpoint is not None:
-        # Mapping the weights to GPU may cause unexpected video memory leak
-        # which refers to https://github.com/open-mmlab/mmdetection/pull/6405
-        checkpoint = load_checkpoint(algorithm, checkpoint, map_location='cpu')
-        if 'CLASSES' in checkpoint.get('meta', {}):
-            model.CLASSES = checkpoint['meta']['CLASSES']
-        else:
-            from mmcls.datasets import ImageNet
-            warnings.simplefilter('once')
-            warnings.warn('Class names are not saved in the checkpoint\'s '
-                          'meta data, use imagenet by default.')
-            model.CLASSES = ImageNet.CLASSES
-    model.cfg = config  # save the config in the model for convenience
-    model.to(device)
-    model.eval()
-
-    return model

mmrazor/apis/mmdet/__init__.py

@@ -1,10 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-try:
-    import mmdet
-except (ImportError, ModuleNotFoundError):
-    mmdet = None
-
-if mmdet is not None:
-    from .inference import init_mmdet_model
-
-    __all__ = ['init_mmdet_model']

mmrazor/apis/mmseg/__init__.py

@@ -1,10 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-try:
-    import mmseg
-except (ImportError, ModuleNotFoundError):
-    mmseg = None
-
-if mmseg:
-    from .inference import init_mmseg_model
-
-    __all__ = ['init_mmseg_model']

mmrazor/apis/mmseg/inference.py

@@ -1,46 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-from typing import Optional, Union
-
-import mmcv
-from mmcv.runner import load_checkpoint
-from torch import nn
-
-from mmrazor.models import build_algorithm
-
-
-def init_mmseg_model(config: Union[str, mmcv.Config],
-                     checkpoint: Optional[str] = None,
-                     device: str = 'cuda:0') -> nn.Module:
-    """Initialize a mmseg model from config file.
-
-    Args:
-        config (str or :obj:`mmcv.Config`): Config file path or the config
-            object.
-        checkpoint (str, optional): Checkpoint path. If left as None, the model
-            will not load any weights.
-        device (str, optional) CPU/CUDA device option. Default 'cuda:0'.
-            Use 'cpu' for loading model on CPU.
-    Returns:
-        nn.Module: The constructed segmentor.
-    """
-    if isinstance(config, str):
-        config = mmcv.Config.fromfile(config)
-    elif not isinstance(config, mmcv.Config):
-        raise TypeError('config must be a filename or Config object, '
-                        'but got {}'.format(type(config)))
-
-    model_cfg = config.algorithm.architecture.model
-    model_cfg.pretrained = None
-    model_cfg.train_cfg = None
-    algorithm = build_algorithm(config.algorithm)
-    model = algorithm.architecture.model
-
-    if checkpoint is not None:
-        checkpoint = load_checkpoint(model, checkpoint, map_location='cpu')
-        model.CLASSES = checkpoint['meta']['CLASSES']
-        model.PALETTE = checkpoint['meta']['PALETTE']
-    model.cfg = config  # save the config in the model for convenience
-    model.to(device)
-    model.eval()
-
-    return model

mmrazor/apis/utils.py

@@ -1,57 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import random
-
-import numpy as np
-import torch
-import torch.distributed as dist
-from mmcv.runner import get_dist_info
-
-
-def init_random_seed(seed=None, device='cuda'):
-    """Initialize random seed.
-
-    If the seed is not set, the seed will be automatically randomized,
-    and then broadcast to all processes to prevent some potential bugs.
-    Args:
-        seed (int, Optional): The seed. Default to None.
-        device (str): The device where the seed will be put on.
-            Default to 'cuda'.
-    Returns:
-        int: Seed to be used.
-    """
-    if seed is not None:
-        return seed
-
-    # Make sure all ranks share the same random seed to prevent
-    # some potential bugs. Please refer to
-    # https://github.com/open-mmlab/mmdetection/issues/6339
-    rank, world_size = get_dist_info()
-    seed = np.random.randint(2**31)
-    if world_size == 1:
-        return seed
-
-    if rank == 0:
-        random_num = torch.tensor(seed, dtype=torch.int32, device=device)
-    else:
-        random_num = torch.tensor(0, dtype=torch.int32, device=device)
-    dist.broadcast(random_num, src=0)
-    return random_num.item()
-
-
-def set_random_seed(seed: int, deterministic: bool = False) -> None:
-    """Set random seed.
-
-    Args:
-        seed (int): Seed to be used.
-        deterministic (bool): Whether to set the deterministic option for
-            CUDNN backend, i.e., set ``torch.backends.cudnn.deterministic``
-            to True and ``torch.backends.cudnn.benchmark`` to False.
-            Default: False.
-    """
-    random.seed(seed)
-    np.random.seed(seed)
-    torch.manual_seed(seed)
-    torch.cuda.manual_seed_all(seed)
-    if deterministic:
-        torch.backends.cudnn.deterministic = True
-        torch.backends.cudnn.benchmark = False

mmrazor/models/pruners/structure_pruning.py

@@ -30,8 +30,8 @@ NON_PASS = CONV + FC
 PASS = BN + GN
 NORM = BN + GN
 
-BACKWARD_PARSER_DICT = dict()
-MAKE_GROUP_PARSER_DICT = dict()
+BACKWARD_PARSER_DICT = dict()  # type: ignore
+MAKE_GROUP_PARSER_DICT = dict()  # type: ignore
 
 
 def register_parser(parser_dict, name=None, force=False):

tools/misc/get_flops.py

@@ -1,90 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-
-import numpy as np
-import torch
-from mmcv import Config, DictAction
-from mmcv.cnn.utils import get_model_complexity_info
-
-from mmrazor.models import build_algorithm
-
-
-def parse_args():
-    parser = argparse.ArgumentParser(description='Get model flops and params')
-    parser.add_argument('config', help='config file path')
-    parser.add_argument(
-        '--shape',
-        type=int,
-        nargs='+',
-        default=[224, 224],
-        help='input image size')
-    parser.add_argument(
-        '--cfg-options',
-        nargs='+',
-        action=DictAction,
-        help='override some settings in the used config, the key-value pair '
-        'in xxx=yyy format will be merged into config file. If the value to '
-        'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
-        'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
-        'Note that the quotation marks are necessary and that no white space '
-        'is allowed.')
-    parser.add_argument(
-        '--size-divisor',
-        type=int,
-        default=32,
-        help='Pad the input image, the minimum size that is divisible '
-        'by size_divisor, -1 means do not pad the image.')
-    args = parser.parse_args()
-    return args
-
-
-def main():
-    args = parse_args()
-
-    if len(args.shape) == 1:
-        h = w = args.shape[0]
-    elif len(args.shape) == 2:
-        h, w = args.shape
-    else:
-        raise ValueError('invalid input shape')
-    orig_shape = (3, h, w)
-    divisor = args.size_divisor
-    if divisor > 0:
-        h = int(np.ceil(h / divisor)) * divisor
-        w = int(np.ceil(w / divisor)) * divisor
-
-    input_shape = (3, h, w)
-
-    cfg = Config.fromfile(args.config)
-    if args.cfg_options is not None:
-        cfg.merge_from_dict(args.cfg_options)
-
-    algorithm = build_algorithm(cfg.algorithm)
-    if torch.cuda.is_available():
-        algorithm.cuda()
-    algorithm.eval()
-
-    if hasattr(algorithm.architecture, 'forward_dummy'):
-        algorithm.architecture.forward = algorithm.architecture.forward_dummy
-    else:
-        raise NotImplementedError(
-            'FLOPs counter is currently not currently supported with {}'.
-            format(algorithm.architecture.__class__.__name__))
-
-    flops, params = get_model_complexity_info(algorithm.architecture,
-                                              input_shape)
-    split_line = '=' * 30
-
-    if divisor > 0 and \
-            input_shape != orig_shape:
-        print(f'{split_line}\nUse size divisor set input shape '
-              f'from {orig_shape} to {input_shape}\n')
-    print(f'{split_line}\nInput shape: {input_shape}\n'
-          f'Flops: {flops}\nParams: {params}\n{split_line}')
-    print('!!!Please be cautious if you use the results in papers. '
-          'You may need to check if all ops are supported and verify that the '
-          'flops computation is correct.')
-
-
-if __name__ == '__main__':
-    main()

tools/model_converters/split_checkpoint.py

@@ -1,68 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import argparse
-import os.path as osp
-
-from mmcv import Config
-from mmcv.runner import load_checkpoint, save_checkpoint
-
-from mmrazor.models import build_algorithm
-from mmrazor.models.pruners.utils import SwitchableBatchNorm2d
-
-
-def parse_args():
-    parser = argparse.ArgumentParser(description='Split a slimmable trained'
-                                     'model checkpoint')
-    parser.add_argument('config', type=str, help='path of train config file')
-    parser.add_argument('checkpoint', type=str, help='checkpoint path')
-    parser.add_argument(
-        '--channel-cfgs',
-        nargs='+',
-        help='The path of the channel configs. '
-        'The order should be the same as that of train.')
-    parser.add_argument('--output-dir', type=str, default='')
-    args = parser.parse_args()
-
-    return args
-
-
-def convert_bn(module, bn_ind):
-
-    def traverse(module):
-        for name, child in module.named_children():
-            if isinstance(child, SwitchableBatchNorm2d):
-                setattr(module, name, child.bns[bn_ind])
-            else:
-                traverse(child)
-
-    traverse(module)
-
-
-def main():
-    args = parse_args()
-
-    cfg = Config.fromfile(args.config)
-    cfg.merge_from_dict(dict(algorithm=dict(channel_cfg=args.channel_cfgs)))
-
-    for i, channel_cfg in enumerate(args.channel_cfgs):
-        algorithm = build_algorithm(cfg.algorithm)
-        load_checkpoint(algorithm, args.checkpoint, map_location='cpu')
-        convert_bn(algorithm, i)
-        for module in algorithm.modules():
-            if hasattr(module, 'out_mask'):
-                del module.out_mask
-            if hasattr(module, 'in_mask'):
-                del module.in_mask
-        assert algorithm.with_pruner, \
-            'The algorithm should has attr pruner. Please check your ' \
-            'config file.'
-        algorithm.pruner.deploy_subnet(algorithm.architecture,
-                                       algorithm.channel_cfg[i])
-        filename = osp.join(args.output_dir, f'checkpoint_{i + 1}.pth')
-        save_checkpoint(algorithm, filename)
-
-    print(f'Successfully split the original checkpoint `{args.checkpoint}` to '
-          f'{len(args.channel_cfgs)} different checkpoints.')
-
-
-if __name__ == '__main__':
-    main()