add new config sample and check scripts (#2216)

* add new config sample and check scripts

* context managere to prevent import

* refactor backbone, add caffe

* add fast rcnn

* all basci config done

* rm coco_proposal

* add scratch, wider_face, voc

* add reppoints

* delete device id, auto resume

* add libra_rcnn, ms_rcnn, nas_fpn

* add hrnet, fcos

* add free_anchor, gn, grid_rcnn, guided_anchoring, gcnet, ghm, gn+ws

* finished all, but some need refactor and unified logic

* fixed albu

* update ReseNet101

* reduce ResNet101, add norm_cfg, 4conv1fc

* refactor caffe backbone

* merge act_cfg, dcn from master

* rename 2fc head, add 4conv1fc head

* delete 4con1fc model

* rename components -> _base_

* flatten _base_

* refactor _base_ structure

* refactor config structure

* reduce _base/models

* rename all config

* add _coco inside configs

* fixed _coco in files

* fixed albu in test

* migrate to new sys

* fixed test

* fixed test

* rm cascade, fast_rcnn

* rm cascade, fast_rcnn from _base_

* fixed fcos_center

* rename from rule

* collopse third party model

* fixed test

* fixed some minor bug

* rename gn-neck_head -> gn-neck+head

README.md

@@ -76,7 +76,7 @@ Other features
 - [x] [DCNv2](configs/dcn/README.md)
 - [x] [Group Normalization](configs/gn/README.md)
 - [x] [Weight Standardization](configs/gn+ws/README.md)
-- [x] [OHEM](configs/faster_rcnn_ohem_r50_fpn_1x.py)
+- [x] [OHEM](configs/faster_rcnn_ohem_r50_fpn_1x_coco.py)
 - [x] Soft-NMS
 - [x] [Generalized Attention](configs/empirical_attention/README.md)
 - [x] [GCNet](configs/gcnet/README.md)

configs/_base_/datasets/cityscapes_detection.py

@@ -0,0 +1,55 @@
+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(
+    imgs_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/cityscapes_instance.py

@@ -0,0 +1,16 @@
+_base_ = './cityscapes_detection.py'
+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']),
+]
+data = dict(train=dict(dataset=dict(pipeline=train_pipeline)))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/coco_detection.py

@@ -0,0 +1,48 @@
+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(
+    imgs_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/coco_instance.py

@@ -0,0 +1,15 @@
+_base_ = 'coco_detection.py'
+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']),
+]
+data = dict(train=dict(pipeline=train_pipeline))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/coco_instance_semantic.py

@@ -0,0 +1,40 @@
+_base_ = 'coco_detection.py'
+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(
+    train=dict(
+        seg_prefix=data_root + 'stuffthingmaps/train2017/',
+        pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))
+evaluation = dict(metric=['bbox', 'segm'])

configs/_base_/datasets/voc0712.py

@@ -0,0 +1,55 @@
+# 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(
+    imgs_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/wider_face.py

@@ -0,0 +1,63 @@
+# 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(
+    imgs_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_/default_runtime.py

@@ -0,0 +1,14 @@
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    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)]