Update _base_ code

detection/configs/_base_/datasets/cityscapes_detection.py

+# 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')

detection/configs/_base_/datasets/cityscapes_instance.py

+# 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'])

detection/configs/_base_/datasets/coco_panoptic.py

+# 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'])

detection/configs/_base_/datasets/deepfashion.py

+# 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'])

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

+# 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'])

detection/configs/_base_/datasets/lvis_v1_instance.py

+# dataset settings
+_base_ = 'coco_instance.py'
+dataset_type = 'LVISV1Dataset'
+data_root = 'data/lvis_v1/'
+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(
+        _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,
+            pipeline=train_pipeline)),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/lvis_v1_val.json',
+        img_prefix=data_root,
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/lvis_v1_minival.json',
+        img_prefix=data_root,
+        pipeline=test_pipeline))
+evaluation = dict(metric=['bbox'])

detection/configs/_base_/datasets/obj365_detection.py

+# dataset settings
+dataset_type = 'Objects365V2Dataset'
+data_root = 'data/Objects365/Obj365_v2/'
+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/zhiyuan_objv2_train.json',
+        img_prefix=data_root + 'train/',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/zhiyuan_objv2_val.json',
+        img_prefix=data_root + 'val/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/zhiyuan_objv2_val.json',
+        img_prefix=data_root + 'val/',
+        pipeline=test_pipeline))
+evaluation = dict(interval=1, metric='bbox')

detection/configs/_base_/datasets/openimages_detection.py

+# dataset settings
+dataset_type = 'OpenImagesDataset'
+data_root = 'data/OpenImages/'
+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, denorm_bbox=True),
+    dict(type='Resize', img_scale=(1024, 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=(1024, 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=1,  # workers_per_gpu > 0 may occur out of memory
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/oidv6-train-annotations-bbox.csv',
+        img_prefix=data_root + 'OpenImages/train/',
+        label_file=data_root + 'annotations/class-descriptions-boxable.csv',
+        hierarchy_file=data_root +
+                       'annotations/bbox_labels_600_hierarchy.json',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/validation-annotations-bbox.csv',
+        img_prefix=data_root + 'OpenImages/validation/',
+        label_file=data_root + 'annotations/class-descriptions-boxable.csv',
+        hierarchy_file=data_root +
+        'annotations/bbox_labels_600_hierarchy.json',
+        meta_file=data_root + 'annotations/validation-image-metas.pkl',
+        image_level_ann_file=data_root +
+        'annotations/validation-annotations-human-imagelabels-boxable.csv',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/validation-annotations-bbox.csv',
+        img_prefix=data_root + 'OpenImages/validation/',
+        label_file=data_root + 'annotations/class-descriptions-boxable.csv',
+        hierarchy_file=data_root +
+        'annotations/bbox_labels_600_hierarchy.json',
+        meta_file=data_root + 'annotations/validation-image-metas.pkl',
+        image_level_ann_file=data_root +
+        'annotations/validation-annotations-human-imagelabels-boxable.csv',
+        pipeline=test_pipeline))
+evaluation = dict(interval=1, metric='mAP')

detection/configs/_base_/datasets/voc0712.py

+# 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')

detection/configs/_base_/datasets/wider_face.py

+# 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))

detection/configs/_base_/schedules/schedule_20e.py

+# 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, 19])
+runner = dict(type='EpochBasedRunner', max_epochs=20)

detection/configs/_base_/schedules/schedule_2x.py

+# 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)

detection/configs/_base_/schedules/schedule_6x.py

+# 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=2000,
+    warmup_ratio=0.001,
+    step=[62, 68])
+runner = dict(type='EpochBasedRunner', max_epochs=72)