Resolve README.md conflict and continue rebase

.idea/.gitignore

@@ -0,0 +1,3 @@
+# 默认忽略的文件
+/shelf/
+/workspace.xml

.idea/SpecDETR.iml

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="mmcv2" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PackageRequirementsSettings">
+    <option name="requirementsPath" value="" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="GOOGLE" />
+    <option name="myDocStringFormat" value="Google" />
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,42 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="22">
+            <item index="0" class="java.lang.String" itemvalue="imagecorruptions" />
+            <item index="1" class="java.lang.String" itemvalue="interrogate" />
+            <item index="2" class="java.lang.String" itemvalue="mmtrack" />
+            <item index="3" class="java.lang.String" itemvalue="isort" />
+            <item index="4" class="java.lang.String" itemvalue="kwarray" />
+            <item index="5" class="java.lang.String" itemvalue="asynctest" />
+            <item index="6" class="java.lang.String" itemvalue="onnx" />
+            <item index="7" class="java.lang.String" itemvalue="xdoctest" />
+            <item index="8" class="java.lang.String" itemvalue="codecov" />
+            <item index="9" class="java.lang.String" itemvalue="flake8" />
+            <item index="10" class="java.lang.String" itemvalue="ubelt" />
+            <item index="11" class="java.lang.String" itemvalue="fairscale" />
+            <item index="12" class="java.lang.String" itemvalue="pytest" />
+            <item index="13" class="java.lang.String" itemvalue="emoji" />
+            <item index="14" class="java.lang.String" itemvalue="lightning" />
+            <item index="15" class="java.lang.String" itemvalue="hydra-core" />
+            <item index="16" class="java.lang.String" itemvalue="memory_profiler" />
+            <item index="17" class="java.lang.String" itemvalue="mmpose" />
+            <item index="18" class="java.lang.String" itemvalue="mmrazor" />
+            <item index="19" class="java.lang.String" itemvalue="parameterized" />
+            <item index="20" class="java.lang.String" itemvalue="mmcls" />
+            <item index="21" class="java.lang.String" itemvalue="mmrotate" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="pkl2json._" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="mmcv2" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/SpecDETR.iml" filepath="$PROJECT_DIR$/.idea/SpecDETR.iml" />
+    </modules>
+  </component>
+</project>

MANIFEST.in

@@ -0,0 +1,6 @@
+include requirements/*.txt
+include mmdet/VERSION
+include mmdet/.mim/model-index.yml
+include mmdet/.mim/demo/*/*
+recursive-include mmdet/.mim/configs *.py *.yml
+recursive-include mmdet/.mim/tools *.sh *.py

benchmark.py

@@ -0,0 +1,133 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import argparse
+import os
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+from mmengine import MMLogger
+from mmengine.config import Config, DictAction
+from mmengine.dist import init_dist
+from mmengine.registry import init_default_scope
+from mmengine.utils import mkdir_or_exist
+
+from mmdet.utils.benchmark import (DataLoaderBenchmark, DatasetBenchmark,
+                                   InferenceBenchmark)
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='MMDet benchmark')
+    parser.add_argument('--config',default='./configs/specdetr_sb-2s-100e_hsi.py',help='test config file path')
+    parser.add_argument('--checkpoint',default='./work_dirs/SpecDETR/SpecDETR_100e.pth', help='checkpoint file')
+    parser.add_argument(
+        '--task',
+        choices=['inference', 'dataloader', 'dataset'],
+        default='inference',
+        help='Which task do you want to go to benchmark')
+    parser.add_argument(
+        '--repeat-num',
+        type=int,
+        default=1,
+        help='number of repeat times of measurement for averaging the results')
+    parser.add_argument(
+        '--max-iter', type=int, default=2000, help='num of max iter')
+    parser.add_argument(
+        '--log-interval', type=int, default=50, help='interval of logging')
+    parser.add_argument(
+        '--num-warmup', type=int, default=5, help='Number of warmup')
+    parser.add_argument(
+        '--fuse-conv-bn',
+        action='store_true',
+        help='Whether to fuse conv and bn, this will slightly increase'
+        'the inference speed')
+    parser.add_argument(
+        '--dataset-type',
+        choices=['train', 'val', 'test'],
+        default='test',
+        help='Benchmark dataset type. only supports train, val and test')
+    parser.add_argument(
+        '--work-dir',
+        help='the directory to save the file containing '
+        'benchmark metrics')
+    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(
+        '--launcher',
+        choices=['none', 'pytorch', 'slurm', 'mpi'],
+        default='none',
+        help='job launcher')
+    parser.add_argument('--local_rank', type=int, default=0)
+    args = parser.parse_args()
+    if 'LOCAL_RANK' not in os.environ:
+        os.environ['LOCAL_RANK'] = str(args.local_rank)
+    return args
+
+
+def inference_benchmark(args, cfg, distributed, logger):
+    benchmark = InferenceBenchmark(
+        cfg,
+        args.checkpoint,
+        distributed,
+        args.fuse_conv_bn,
+        args.max_iter,
+        args.log_interval,
+        args.num_warmup,
+        logger=logger)
+    return benchmark
+
+
+def dataloader_benchmark(args, cfg, distributed, logger):
+    benchmark = DataLoaderBenchmark(
+        cfg,
+        distributed,
+        args.dataset_type,
+        args.max_iter,
+        args.log_interval,
+        args.num_warmup,
+        logger=logger)
+    return benchmark
+
+
+def dataset_benchmark(args, cfg, distributed, logger):
+    benchmark = DatasetBenchmark(
+        cfg,
+        args.dataset_type,
+        args.max_iter,
+        args.log_interval,
+        args.num_warmup,
+        logger=logger)
+    return benchmark
+
+
+def main():
+    args = parse_args()
+    cfg = Config.fromfile(args.config)
+    if args.cfg_options is not None:
+        cfg.merge_from_dict(args.cfg_options)
+
+    init_default_scope(cfg.get('default_scope', 'mmdet'))
+
+    distributed = False
+    if args.launcher != 'none':
+        init_dist(args.launcher, **cfg.get('env_cfg', {}).get('dist_cfg', {}))
+        distributed = True
+
+    log_file = None
+    if args.work_dir:
+        log_file = os.path.join(args.work_dir, 'benchmark.log')
+        mkdir_or_exist(args.work_dir)
+
+    logger = MMLogger.get_instance(
+        'mmdet', log_file=log_file, log_level='INFO')
+
+    benchmark = eval(f'{args.task}_benchmark')(args, cfg, distributed, logger)
+    benchmark.run(args.repeat_num)
+
+
+if __name__ == '__main__':
+    main()

configs/_base_/datasets/cityscapes_detection.py

@@ -0,0 +1,84 @@
+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/segmentation/cityscapes/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/segmentation/',
+#          'data/': 's3://openmmlab/datasets/segmentation/'
+#      }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomResize',
+        scale=[(2048, 800), (2048, 1024)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/instancesonly_filtered_gtFine_train.json',
+            data_prefix=dict(img='leftImg8bit/train/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline,
+            backend_args=backend_args)))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instancesonly_filtered_gtFine_val.json',
+        data_prefix=dict(img='leftImg8bit/val/'),
+        test_mode=True,
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_val.json',
+    metric='bbox',
+    backend_args=backend_args)
+
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes_instance.py

@@ -0,0 +1,113 @@
+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/segmentation/cityscapes/'
+
+# Method 2: Use backend_args, file_client_args in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/segmentation/',
+#          'data/': 's3://openmmlab/datasets/segmentation/'
+#      }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='RandomResize',
+        scale=[(2048, 800), (2048, 1024)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/instancesonly_filtered_gtFine_train.json',
+            data_prefix=dict(img='leftImg8bit/train/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline,
+            backend_args=backend_args)))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instancesonly_filtered_gtFine_val.json',
+        data_prefix=dict(img='leftImg8bit/val/'),
+        test_mode=True,
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+test_dataloader = val_dataloader
+
+val_evaluator = [
+    dict(
+        type='CocoMetric',
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_val.json',
+        metric=['bbox', 'segm'],
+        backend_args=backend_args),
+    dict(
+        type='CityScapesMetric',
+        seg_prefix=data_root + 'gtFine/val',
+        outfile_prefix='./work_dirs/cityscapes_metric/instance',
+        backend_args=backend_args)
+]
+
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file='annotations/instancesonly_filtered_gtFine_test.json',
+#         data_prefix=dict(img='leftImg8bit/test/'),
+#         test_mode=True,
+#         filter_cfg=dict(filter_empty_gt=True, min_size=32),
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#         type='CityScapesMetric',
+#         format_only=True,
+#         outfile_prefix='./work_dirs/cityscapes_metric/test')

configs/_base_/datasets/coco_detection.py

@@ -0,0 +1,95 @@
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric='bbox',
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoMetric',
+#     metric='bbox',
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_detection/test')

configs/_base_/datasets/coco_instance.py

@@ -0,0 +1,95 @@
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoMetric',
+#     metric=['bbox', 'segm'],
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_instance/test')

configs/_base_/datasets/coco_instance_semantic.py

@@ -0,0 +1,78 @@
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(
+        type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(
+        type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/', seg='stuffthingmaps/train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/coco_panoptic.py

@@ -0,0 +1,94 @@
+# dataset settings
+dataset_type = 'CocoPanopticDataset'
+# data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadPanopticAnnotations', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='LoadPanopticAnnotations', backend_args=backend_args),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/panoptic_train2017.json',
+        data_prefix=dict(
+            img='train2017/', seg='annotations/panoptic_train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/panoptic_val2017.json',
+        data_prefix=dict(img='val2017/', seg='annotations/panoptic_val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoPanopticMetric',
+    ann_file=data_root + 'annotations/panoptic_val2017.json',
+    seg_prefix=data_root + 'annotations/panoptic_val2017/',
+    backend_args=backend_args)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=1,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file='annotations/panoptic_image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoPanopticMetric',
+#     format_only=True,
+#     ann_file=data_root + 'annotations/panoptic_image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_panoptic/test')

configs/_base_/datasets/deepfashion.py

@@ -0,0 +1,95 @@
+# dataset settings
+dataset_type = 'DeepFashionDataset'
+data_root = 'data/DeepFashion/In-shop/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', scale=(750, 1101), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(750, 1101), keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=2,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='Anno/segmentation/DeepFashion_segmentation_train.json',
+            data_prefix=dict(img='Img/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline,
+            backend_args=backend_args)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='Anno/segmentation/DeepFashion_segmentation_query.json',
+        data_prefix=dict(img='Img/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='Anno/segmentation/DeepFashion_segmentation_gallery.json',
+        data_prefix=dict(img='Img/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root +
+    'Anno/segmentation/DeepFashion_segmentation_query.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root +
+    'Anno/segmentation/DeepFashion_segmentation_gallery.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=backend_args)

configs/_base_/datasets/hsi_detection.py

@@ -0,0 +1,96 @@
+# dataset settings
+dataset_type = 'HSIDataset'
+data_root = '/media/ubuntu/data/HTD_dataset/SPOD_30b_8c/'
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+
+normalized_basis =3000
+backend_args = None
+train_pipeline = [
+    dict(type='LoadHyperspectralImageFromFiles', to_float32 =True, normalized_basis=normalized_basis),
+    dict(type='LoadAnnotations', with_bbox=True),
+    # dict(type='Resize', scale=(512, 512), keep_ratio=True),
+    dict(type='HSIResize', scale_factor=1, keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs',meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction','scale_factor'))
+]
+test_pipeline = [
+    dict(type='LoadHyperspectralImageFromFiles', to_float32 =True, normalized_basis=normalized_basis),
+    # dict(type='Resize', scale=(512, 512), keep_ratio=True),
+    dict(type='HSIResize', scale_factor=1, keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/test.json',
+        data_prefix=dict(img='test/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/test.json',
+    metric=['bbox','proposal_fast'],
+    classwise = True,
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoMetric',
+#     metric='bbox',
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_detection/test')

configs/_base_/datasets/objects365v1_detection.py

@@ -0,0 +1,74 @@
+# dataset settings
+dataset_type = 'Objects365V1Dataset'
+data_root = 'data/Objects365/Obj365_v1/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/objects365_val.json',
+        data_prefix=dict(img='val/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/objects365_val.json',
+    metric='bbox',
+    sort_categories=True,
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/objects365v2_detection.py

@@ -0,0 +1,73 @@
+# dataset settings
+dataset_type = 'Objects365V2Dataset'
+data_root = 'data/Objects365/Obj365_v2/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/zhiyuan_objv2_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/zhiyuan_objv2_val.json',
+        data_prefix=dict(img='val/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/zhiyuan_objv2_val.json',
+    metric='bbox',
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/openimages_detection.py

@@ -0,0 +1,81 @@
+# dataset settings
+dataset_type = 'OpenImagesDataset'
+data_root = 'data/OpenImages/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1024, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1024, 800), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='LoadAnnotations', with_bbox=True),
+    # TODO: find a better way to collect image_level_labels
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'instances', 'image_level_labels'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=0,  # workers_per_gpu > 0 may occur out of memory
+    persistent_workers=False,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/oidv6-train-annotations-bbox.csv',
+        data_prefix=dict(img='OpenImages/train/'),
+        label_file='annotations/class-descriptions-boxable.csv',
+        hierarchy_file='annotations/bbox_labels_600_hierarchy.json',
+        meta_file='annotations/train-image-metas.pkl',
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=0,
+    persistent_workers=False,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/validation-annotations-bbox.csv',
+        data_prefix=dict(img='OpenImages/validation/'),
+        label_file='annotations/class-descriptions-boxable.csv',
+        hierarchy_file='annotations/bbox_labels_600_hierarchy.json',
+        meta_file='annotations/validation-image-metas.pkl',
+        image_level_ann_file='annotations/validation-'
+        'annotations-human-imagelabels-boxable.csv',
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='OpenImagesMetric',
+    iou_thrs=0.5,
+    ioa_thrs=0.5,
+    use_group_of=True,
+    get_supercategory=True)
+test_evaluator = val_evaluator

configs/_base_/datasets/semi_coco_detection.py

@@ -0,0 +1,178 @@
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+color_space = [
+    [dict(type='ColorTransform')],
+    [dict(type='AutoContrast')],
+    [dict(type='Equalize')],
+    [dict(type='Sharpness')],
+    [dict(type='Posterize')],
+    [dict(type='Solarize')],
+    [dict(type='Color')],
+    [dict(type='Contrast')],
+    [dict(type='Brightness')],
+]
+
+geometric = [
+    [dict(type='Rotate')],
+    [dict(type='ShearX')],
+    [dict(type='ShearY')],
+    [dict(type='TranslateX')],
+    [dict(type='TranslateY')],
+]
+
+scale = [(1333, 400), (1333, 1200)]
+
+branch_field = ['sup', 'unsup_teacher', 'unsup_student']
+# pipeline used to augment labeled data,
+# which will be sent to student model for supervised training.
+sup_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='RandomResize', scale=scale, keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='RandAugment', aug_space=color_space, aug_num=1),
+    dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
+    dict(
+        type='MultiBranch',
+        branch_field=branch_field,
+        sup=dict(type='PackDetInputs'))
+]
+
+# pipeline used to augment unlabeled data weakly,
+# which will be sent to teacher model for predicting pseudo instances.
+weak_pipeline = [
+    dict(type='RandomResize', scale=scale, keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'flip', 'flip_direction',
+                   'homography_matrix')),
+]
+
+# pipeline used to augment unlabeled data strongly,
+# which will be sent to student model for unsupervised training.
+strong_pipeline = [
+    dict(type='RandomResize', scale=scale, keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(
+        type='RandomOrder',
+        transforms=[
+            dict(type='RandAugment', aug_space=color_space, aug_num=1),
+            dict(type='RandAugment', aug_space=geometric, aug_num=1),
+        ]),
+    dict(type='RandomErasing', n_patches=(1, 5), ratio=(0, 0.2)),
+    dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'flip', 'flip_direction',
+                   'homography_matrix')),
+]
+
+# pipeline used to augment unlabeled data into different views
+unsup_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadEmptyAnnotations'),
+    dict(
+        type='MultiBranch',
+        branch_field=branch_field,
+        unsup_teacher=weak_pipeline,
+        unsup_student=strong_pipeline,
+    )
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+batch_size = 5
+num_workers = 5
+# There are two common semi-supervised learning settings on the coco dataset：
+# (1) Divide the train2017 into labeled and unlabeled datasets
+# by a fixed percentage, such as 1%, 2%, 5% and 10%.
+# The format of labeled_ann_file and unlabeled_ann_file are
+# instances_train2017.{fold}@{percent}.json, and
+# instances_train2017.{fold}@{percent}-unlabeled.json
+# `fold` is used for cross-validation, and `percent` represents
+# the proportion of labeled data in the train2017.
+# (2) Choose the train2017 as the labeled dataset
+# and unlabeled2017 as the unlabeled dataset.
+# The labeled_ann_file and unlabeled_ann_file are
+# instances_train2017.json and image_info_unlabeled2017.json
+# We use this configuration by default.
+labeled_dataset = dict(
+    type=dataset_type,
+    data_root=data_root,
+    ann_file='annotations/instances_train2017.json',
+    data_prefix=dict(img='train2017/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=sup_pipeline,
+    backend_args=backend_args)
+
+unlabeled_dataset = dict(
+    type=dataset_type,
+    data_root=data_root,
+    ann_file='annotations/instances_unlabeled2017.json',
+    data_prefix=dict(img='unlabeled2017/'),
+    filter_cfg=dict(filter_empty_gt=False),
+    pipeline=unsup_pipeline,
+    backend_args=backend_args)
+
+train_dataloader = dict(
+    batch_size=batch_size,
+    num_workers=num_workers,
+    persistent_workers=True,
+    sampler=dict(
+        type='GroupMultiSourceSampler',
+        batch_size=batch_size,
+        source_ratio=[1, 4]),
+    dataset=dict(
+        type='ConcatDataset', datasets=[labeled_dataset, unlabeled_dataset]))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric='bbox',
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator

configs/_base_/datasets/voc0712.py

@@ -0,0 +1,92 @@
+# dataset settings
+dataset_type = 'VOCDataset'
+data_root = 'data/VOCdevkit/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically Infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/segmentation/VOCdevkit/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/segmentation/',
+#         'data/': 's3://openmmlab/datasets/segmentation/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1000, 600), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1000, 600), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=3,
+        dataset=dict(
+            type='ConcatDataset',
+            # VOCDataset will add different `dataset_type` in dataset.metainfo,
+            # which will get error if using ConcatDataset. Adding
+            # `ignore_keys` can avoid this error.
+            ignore_keys=['dataset_type'],
+            datasets=[
+                dict(
+                    type=dataset_type,
+                    data_root=data_root,
+                    ann_file='VOC2007/ImageSets/Main/trainval.txt',
+                    data_prefix=dict(sub_data_root='VOC2007/'),
+                    filter_cfg=dict(
+                        filter_empty_gt=True, min_size=32, bbox_min_size=32),
+                    pipeline=train_pipeline,
+                    backend_args=backend_args),
+                dict(
+                    type=dataset_type,
+                    data_root=data_root,
+                    ann_file='VOC2012/ImageSets/Main/trainval.txt',
+                    data_prefix=dict(sub_data_root='VOC2012/'),
+                    filter_cfg=dict(
+                        filter_empty_gt=True, min_size=32, bbox_min_size=32),
+                    pipeline=train_pipeline,
+                    backend_args=backend_args)
+            ])))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='VOC2007/ImageSets/Main/test.txt',
+        data_prefix=dict(sub_data_root='VOC2007/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+# Pascal VOC2007 uses `11points` as default evaluate mode, while PASCAL
+# VOC2012 defaults to use 'area'.
+val_evaluator = dict(type='VOCMetric', metric='mAP', eval_mode='11points')
+test_evaluator = val_evaluator

configs/_base_/datasets/wider_face.py

@@ -0,0 +1,73 @@
+# dataset settings
+dataset_type = 'WIDERFaceDataset'
+data_root = 'data/WIDERFace/'
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/cityscapes/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#          'data/': 's3://openmmlab/datasets/detection/'
+#      }))
+backend_args = None
+
+img_scale = (640, 640)  # VGA resolution
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=img_scale, keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='train.txt',
+        data_prefix=dict(img='WIDER_train'),
+        filter_cfg=dict(filter_empty_gt=True, bbox_min_size=17, min_size=32),
+        pipeline=train_pipeline))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='val.txt',
+        data_prefix=dict(img='WIDER_val'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    # TODO: support WiderFace-Evaluation for easy, medium, hard cases
+    type='VOCMetric',
+    metric='mAP',
+    eval_mode='11points')
+test_evaluator = val_evaluator

configs/_base_/default_runtime.py

@@ -0,0 +1,25 @@
+default_scope = 'mmdet'
+
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    # checkpoint=dict(type='CheckpointHook',interval=-1, by_epoch=True, save_best='auto'),
+    checkpoint=dict(type='CheckpointHook', interval=999999, by_epoch=True),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='DetVisualizationHook'))
+
+env_cfg = dict(
+    cudnn_benchmark=False,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'),
+)
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+
+log_level = 'INFO'
+load_from = None
+resume = False

configs/_base_/models/cascade-mask-rcnn_r50_fpn.py

@@ -0,0 +1,203 @@
+# model settings
+model = dict(
+    type='CascadeRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_mask=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        type='CascadeRoIHead',
+        num_stages=3,
+        stage_loss_weights=[1, 0.5, 0.25],
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=[
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ],
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=4,
+            in_channels=256,
+            conv_out_channels=256,
+            num_classes=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=[
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.5,
+                    neg_iou_thr=0.5,
+                    min_pos_iou=0.5,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.6,
+                    neg_iou_thr=0.6,
+                    min_pos_iou=0.6,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.7,
+                    neg_iou_thr=0.7,
+                    min_pos_iou=0.7,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                mask_size=28,
+                pos_weight=-1,
+                debug=False)
+        ]),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/cascade-rcnn_r50_fpn.py

@@ -0,0 +1,185 @@
+# model settings
+model = dict(
+    type='CascadeRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+    roi_head=dict(
+        type='CascadeRoIHead',
+        num_stages=3,
+        stage_loss_weights=[1, 0.5, 0.25],
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=[
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.05, 0.05, 0.1, 0.1]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+                               loss_weight=1.0)),
+            dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=80,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0., 0., 0., 0.],
+                    target_stds=[0.033, 0.033, 0.067, 0.067]),
+                reg_class_agnostic=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=1.0),
+                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+        ]),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=[
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.5,
+                    neg_iou_thr=0.5,
+                    min_pos_iou=0.5,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.6,
+                    neg_iou_thr=0.6,
+                    min_pos_iou=0.6,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False),
+            dict(
+                assigner=dict(
+                    type='MaxIoUAssigner',
+                    pos_iou_thr=0.7,
+                    neg_iou_thr=0.7,
+                    min_pos_iou=0.7,
+                    match_low_quality=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False)
+        ]),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/fast-rcnn_r50_fpn.py

@@ -0,0 +1,68 @@
+# model settings
+model = dict(
+    type='FastRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/faster-rcnn_r50-caffe-c4.py

@@ -0,0 +1,123 @@
+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='FasterRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        shared_head=dict(
+            type='ResLayer',
+            depth=50,
+            stage=3,
+            stride=2,
+            dilation=1,
+            style='caffe',
+            norm_cfg=norm_cfg,
+            norm_eval=True,
+            init_cfg=dict(
+                type='Pretrained',
+                checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=1024,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='BBoxHead',
+            with_avg_pool=True,
+            roi_feat_size=7,
+            in_channels=2048,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=6000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/faster-rcnn_r50-caffe-dc5.py

@@ -0,0 +1,111 @@
+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='FasterRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        strides=(1, 2, 2, 1),
+        dilations=(1, 1, 1, 2),
+        out_indices=(3, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=2048,
+        feat_channels=2048,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=2048,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=2048,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms=dict(type='nms', iou_threshold=0.7),
+            nms_pre=6000,
+            max_per_img=1000,
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))

configs/_base_/models/faster-rcnn_r50_fpn.py

@@ -0,0 +1,114 @@
+# model settings
+model = dict(
+    type='FasterRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)
+        # soft-nms is also supported for rcnn testing
+        # e.g., nms=dict(type='soft_nms', iou_threshold=0.5, min_score=0.05)
+    ))

configs/_base_/models/mask-rcnn_r50-caffe-c4.py

@@ -0,0 +1,132 @@
+# model settings
+norm_cfg = dict(type='BN', requires_grad=False)
+model = dict(
+    type='MaskRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_mask=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        shared_head=dict(
+            type='ResLayer',
+            depth=50,
+            stage=3,
+            stride=2,
+            dilation=1,
+            style='caffe',
+            norm_cfg=norm_cfg,
+            norm_eval=True),
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=1024,
+            featmap_strides=[16]),
+        bbox_head=dict(
+            type='BBoxHead',
+            with_avg_pool=True,
+            roi_feat_size=7,
+            in_channels=2048,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=None,
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=0,
+            in_channels=2048,
+            conv_out_channels=256,
+            num_classes=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=14,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=6000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            max_per_img=1000,
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/mask-rcnn_r50_fpn.py

@@ -0,0 +1,127 @@
+# model settings
+model = dict(
+    type='MaskRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_mask=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=80,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=4,
+            in_channels=256,
+            conv_out_channels=256,
+            num_classes=80,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))

configs/_base_/models/retinanet_r50_fpn.py

@@ -0,0 +1,68 @@
+# model settings
+model = dict(
+    type='RetinaNet',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs='on_input',
+        num_outs=5),
+    bbox_head=dict(
+        type='RetinaHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            octave_base_scale=4,
+            scales_per_octave=3,
+            ratios=[0.5, 1.0, 2.0],
+            strides=[8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.4,
+            min_pos_iou=0,
+            ignore_iof_thr=-1),
+        sampler=dict(
+            type='PseudoSampler'),  # Focal loss should use PseudoSampler
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms', iou_threshold=0.5),
+        max_per_img=100))

configs/_base_/models/rpn_r50-caffe-c4.py

@@ -0,0 +1,64 @@
+# model settings
+model = dict(
+    type='RPN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.530, 116.280, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=3,
+        strides=(1, 2, 2),
+        dilations=(1, 1, 1),
+        out_indices=(2, ),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    neck=None,
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=1024,
+        feat_channels=1024,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[2, 4, 8, 16, 32],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[16]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=12000,
+            max_per_img=2000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0)))

configs/_base_/models/rpn_r50_fpn.py

@@ -0,0 +1,64 @@
+# model settings
+model = dict(
+    type='RPN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    # model training and testing settings
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0)))

configs/_base_/models/ssd300.py

@@ -0,0 +1,63 @@
+# model settings
+input_size = 300
+model = dict(
+    type='SingleStageDetector',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[1, 1, 1],
+        bgr_to_rgb=True,
+        pad_size_divisor=1),
+    backbone=dict(
+        type='SSDVGG',
+        depth=16,
+        with_last_pool=False,
+        ceil_mode=True,
+        out_indices=(3, 4),
+        out_feature_indices=(22, 34),
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://vgg16_caffe')),
+    neck=dict(
+        type='SSDNeck',
+        in_channels=(512, 1024),
+        out_channels=(512, 1024, 512, 256, 256, 256),
+        level_strides=(2, 2, 1, 1),
+        level_paddings=(1, 1, 0, 0),
+        l2_norm_scale=20),
+    bbox_head=dict(
+        type='SSDHead',
+        in_channels=(512, 1024, 512, 256, 256, 256),
+        num_classes=80,
+        anchor_generator=dict(
+            type='SSDAnchorGenerator',
+            scale_major=False,
+            input_size=input_size,
+            basesize_ratio_range=(0.15, 0.9),
+            strides=[8, 16, 32, 64, 100, 300],
+            ratios=[[2], [2, 3], [2, 3], [2, 3], [2], [2]]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[0.1, 0.1, 0.2, 0.2])),
+    # model training and testing settings
+    train_cfg=dict(
+        assigner=dict(
+            type='MaxIoUAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0.,
+            ignore_iof_thr=-1,
+            gt_max_assign_all=False),
+        sampler=dict(type='PseudoSampler'),
+        smoothl1_beta=1.,
+        allowed_border=-1,
+        pos_weight=-1,
+        neg_pos_ratio=3,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        nms=dict(type='nms', iou_threshold=0.45),
+        min_bbox_size=0,
+        score_thr=0.02,
+        max_per_img=200))
+cudnn_benchmark = True

configs/_base_/schedules/schedule_1x.py

@@ -0,0 +1,28 @@
+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=12,
+        by_epoch=True,
+        milestones=[8, 11],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=4)

configs/_base_/schedules/schedule_20e.py

@@ -0,0 +1,28 @@
+# training schedule for 20e
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=20, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=20,
+        by_epoch=True,
+        milestones=[16, 19],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=16)

configs/_base_/schedules/schedule_2x.py

@@ -0,0 +1,28 @@
+# training schedule for 2x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=24, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=24,
+        by_epoch=True,
+        milestones=[16, 22],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=16)

configs/backup/albu_example/README.md

@@ -0,0 +1,31 @@
+# Albu Example
+
+> [Albumentations: fast and flexible image augmentations](https://arxiv.org/abs/1809.06839)
+
+<!-- [OTHERS] -->
+
+## Abstract
+
+Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve output labels. In computer vision domain, image augmentations have become a common implicit regularization technique to combat overfitting in deep convolutional neural networks and are ubiquitously used to improve performance. While most deep learning frameworks implement basic image transformations, the list is typically limited to some variations and combinations of flipping, rotating, scaling, and cropping. Moreover, the image processing speed varies in existing tools for image augmentation. We present Albumentations, a fast and flexible library for image augmentations with many various image transform operations available, that is also an easy-to-use wrapper around other augmentation libraries. We provide examples of image augmentations for different computer vision tasks and show that Albumentations is faster than other commonly used image augmentation tools on the most of commonly used image transformations.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/40661020/143870703-74f3ea3f-ae23-4035-9856-746bc3f88464.png" height="400" />
+</div>
+
+## Results and Models
+
+| Backbone |  Style  | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP |                    Config                     |                                                                                                                                                        Download                                                                                                                                                         |
+| :------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :-------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|   R-50   | pytorch |   1x    |   4.4    |      16.6      |  38.0  |  34.5   | [config](mask-rcnn_r50_fpn_albu-1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208-ab203bcd.pth) \| [log](https://download.openmmlab.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208_225520.log.json) |
+
+## Citation
+
+```latex
+@article{2018arXiv180906839B,
+  author = {A. Buslaev, A. Parinov, E. Khvedchenya, V.~I. Iglovikov and A.~A. Kalinin},
+  title = "{Albumentations: fast and flexible image augmentations}",
+  journal = {ArXiv e-prints},
+  eprint = {1809.06839},
+  year = 2018
+}
+```

configs/backup/albu_example/mask-rcnn_r50_fpn_albu-1x_coco.py

@@ -0,0 +1,66 @@
+_base_ = '../mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py'
+
+albu_train_transforms = [
+    dict(
+        type='ShiftScaleRotate',
+        shift_limit=0.0625,
+        scale_limit=0.0,
+        rotate_limit=0,
+        interpolation=1,
+        p=0.5),
+    dict(
+        type='RandomBrightnessContrast',
+        brightness_limit=[0.1, 0.3],
+        contrast_limit=[0.1, 0.3],
+        p=0.2),
+    dict(
+        type='OneOf',
+        transforms=[
+            dict(
+                type='RGBShift',
+                r_shift_limit=10,
+                g_shift_limit=10,
+                b_shift_limit=10,
+                p=1.0),
+            dict(
+                type='HueSaturationValue',
+                hue_shift_limit=20,
+                sat_shift_limit=30,
+                val_shift_limit=20,
+                p=1.0)
+        ],
+        p=0.1),
+    dict(type='JpegCompression', quality_lower=85, quality_upper=95, p=0.2),
+    dict(type='ChannelShuffle', p=0.1),
+    dict(
+        type='OneOf',
+        transforms=[
+            dict(type='Blur', blur_limit=3, p=1.0),
+            dict(type='MedianBlur', blur_limit=3, p=1.0)
+        ],
+        p=0.1),
+]
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(
+        type='Albu',
+        transforms=albu_train_transforms,
+        bbox_params=dict(
+            type='BboxParams',
+            format='pascal_voc',
+            label_fields=['gt_bboxes_labels', 'gt_ignore_flags'],
+            min_visibility=0.0,
+            filter_lost_elements=True),
+        keymap={
+            'img': 'image',
+            'gt_masks': 'masks',
+            'gt_bboxes': 'bboxes'
+        },
+        skip_img_without_anno=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))

configs/backup/albu_example/metafile.yml

@@ -0,0 +1,17 @@
+Models:
+  - Name: mask-rcnn_r50_fpn_albu-1x_coco
+    In Collection: Mask R-CNN
+    Config: mask-rcnn_r50_fpn_albu-1x_coco.py
+    Metadata:
+      Training Memory (GB): 4.4
+      Epochs: 12
+    Results:
+      - Task: Object Detection
+        Dataset: COCO
+        Metrics:
+          box AP: 38.0
+      - Task: Instance Segmentation
+        Dataset: COCO
+        Metrics:
+          mask AP: 34.5
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208-ab203bcd.pth

configs/backup/atss/README.md

@@ -0,0 +1,31 @@
+# ATSS
+
+> [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://arxiv.org/abs/1912.02424)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve state-of-the-art detectors by a large margin to 50.7% AP without introducing any overhead.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/40661020/143870776-c81168f5-e8b2-44ee-978b-509e4372c5c9.png"/>
+</div>
+
+## Results and Models
+
+| Backbone |  Style  | Lr schd | Mem (GB) | Inf time (fps) | box AP |                Config                |                                                                                                                            Download                                                                                                                             |
+| :------: | :-----: | :-----: | :------: | :------------: | :----: | :----------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|   R-50   | pytorch |   1x    |   3.7    |      19.7      |  39.4  | [config](atss_r50_fpn_1x_coco.py)  | [model](https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209-985f7bd0.pth) \| [log](https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209_102539.log.json) |
+|  R-101   | pytorch |   1x    |   5.6    |      12.3      |  41.5  | [config](atss_r101_fpn_1x_coco.py) |   [model](https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r101_fpn_1x_coco/atss_r101_fpn_1x_20200825-dfcadd6f.pth) \| [log](https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r101_fpn_1x_coco/atss_r101_fpn_1x_20200825-dfcadd6f.log.json)   |
+
+## Citation
+
+```latex
+@article{zhang2019bridging,
+  title   =  {Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection},
+  author  =  {Zhang, Shifeng and Chi, Cheng and Yao, Yongqiang and Lei, Zhen and Li, Stan Z.},
+  journal =  {arXiv preprint arXiv:1912.02424},
+  year    =  {2019}
+}
+```

configs/backup/atss/atss_r101_fpn_1x_coco.py

@@ -0,0 +1,6 @@
+_base_ = './atss_r50_fpn_1x_coco.py'
+model = dict(
+    backbone=dict(
+        depth=101,
+        init_cfg=dict(type='Pretrained',
+                      checkpoint='torchvision://resnet101')))

configs/backup/atss/atss_r101_fpn_8xb8-amp-lsj-200e_coco.py

@@ -0,0 +1,7 @@
+_base_ = './atss_r50_fpn_8xb8-amp-lsj-200e_coco.py'
+
+model = dict(
+    backbone=dict(
+        depth=101,
+        init_cfg=dict(type='Pretrained',
+                      checkpoint='torchvision://resnet101')))

configs/backup/atss/atss_r18_fpn_8xb8-amp-lsj-200e_coco.py

@@ -0,0 +1,7 @@
+_base_ = './atss_r50_fpn_8xb8-amp-lsj-200e_coco.py'
+
+model = dict(
+    backbone=dict(
+        depth=18,
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18')),
+    neck=dict(in_channels=[64, 128, 256, 512]))

configs/backup/atss/atss_r50_fpn_1x_coco.py

@@ -0,0 +1,71 @@
+_base_ = [
+    '../_base_/datasets/coco_detection.py',
+    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    type='ATSS',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs='on_output',
+        num_outs=5),
+    bbox_head=dict(
+        type='ATSSHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            ratios=[1.0],
+            octave_base_scale=8,
+            scales_per_octave=1,
+            strides=[8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[0.1, 0.1, 0.2, 0.2]),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
+        loss_centerness=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
+    # training and testing settings
+    train_cfg=dict(
+        assigner=dict(type='ATSSAssigner', topk=9),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms', iou_threshold=0.6),
+        max_per_img=100))
+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001))

configs/backup/atss/atss_r50_fpn_8xb8-amp-lsj-200e_coco.py

@@ -0,0 +1,81 @@
+_base_ = '../common/lsj-200e_coco-detection.py'
+
+image_size = (1024, 1024)
+batch_augments = [dict(type='BatchFixedSizePad', size=image_size)]
+
+model = dict(
+    type='ATSS',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_size_divisor=32,
+        batch_augments=batch_augments),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs='on_output',
+        num_outs=5),
+    bbox_head=dict(
+        type='ATSSHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            ratios=[1.0],
+            octave_base_scale=8,
+            scales_per_octave=1,
+            strides=[8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[0.1, 0.1, 0.2, 0.2]),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
+        loss_centerness=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
+    # training and testing settings
+    train_cfg=dict(
+        assigner=dict(type='ATSSAssigner', topk=9),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms', iou_threshold=0.6),
+        max_per_img=100))
+
+train_dataloader = dict(batch_size=8, num_workers=4)
+
+# Enable automatic-mixed-precision training with AmpOptimWrapper.
+optim_wrapper = dict(
+    type='AmpOptimWrapper',
+    optimizer=dict(
+        type='SGD', lr=0.01 * 4, momentum=0.9, weight_decay=0.00004))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# USER SHOULD NOT CHANGE ITS VALUES.
+# base_batch_size = (8 GPUs) x (8 samples per GPU)
+auto_scale_lr = dict(base_batch_size=64)

configs/backup/atss/metafile.yml

@@ -0,0 +1,60 @@
+Collections:
+  - Name: ATSS
+    Metadata:
+      Training Data: COCO
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+      Training Resources: 8x V100 GPUs
+      Architecture:
+        - ATSS
+        - FPN
+        - ResNet
+    Paper:
+      URL: https://arxiv.org/abs/1912.02424
+      Title: 'Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection'
+    README: configs/atss/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmdetection/blob/v2.0.0/mmdet/models/detectors/atss.py#L6
+      Version: v2.0.0
+
+Models:
+  - Name: atss_r50_fpn_1x_coco
+    In Collection: ATSS
+    Config: configs/atss/atss_r50_fpn_1x_coco.py
+    Metadata:
+      Training Memory (GB): 3.7
+      inference time (ms/im):
+        - value: 50.76
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
+      Epochs: 12
+    Results:
+      - Task: Object Detection
+        Dataset: COCO
+        Metrics:
+          box AP: 39.4
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209-985f7bd0.pth
+
+  - Name: atss_r101_fpn_1x_coco
+    In Collection: ATSS
+    Config: configs/atss/atss_r101_fpn_1x_coco.py
+    Metadata:
+      Training Memory (GB): 5.6
+      inference time (ms/im):
+        - value: 81.3
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
+      Epochs: 12
+    Results:
+      - Task: Object Detection
+        Dataset: COCO
+        Metrics:
+          box AP: 41.5
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r101_fpn_1x_coco/atss_r101_fpn_1x_20200825-dfcadd6f.pth

configs/backup/autoassign/README.md

@@ -0,0 +1,35 @@
+# AutoAssign
+
+> [AutoAssign: Differentiable Label Assignment for Dense Object Detection](https://arxiv.org/abs/2007.03496)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledge and achieves appearance-aware through a fully differentiable weighting mechanism. During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions. To adapt to object appearances, Confidence Weighting is proposed to adjust the specific assign strategy of each instance. The two weighting modules are then combined to generate positive and negative weights to adjust each location's confidence. Extensive experiments on the MS COCO show that our method steadily surpasses other best sampling strategies by large margins with various backbones. Moreover, our best model achieves 52.1% AP, outperforming all existing one-stage detectors. Besides, experiments on other datasets, e.g., PASCAL VOC, Objects365, and WiderFace, demonstrate the broad applicability of AutoAssign.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/40661020/143870875-33567e44-0584-4470-9a90-0df0fb6c1fe2.png"/>
+</div>
+
+## Results and Models
+
+| Backbone | Style | Lr schd | Mem (GB) | box AP |                     Config                      |                                                                                                                                                        Download                                                                                                                                                         |
+| :------: | :---: | :-----: | :------: | :----: | :---------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|   R-50   | caffe |   1x    |   4.08   |  40.4  | [config](autoassign_r50-caffe_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/autoassign/auto_assign_r50_fpn_1x_coco/auto_assign_r50_fpn_1x_coco_20210413_115540-5e17991f.pth) \| [log](https://download.openmmlab.com/mmdetection/v2.0/autoassign/auto_assign_r50_fpn_1x_coco/auto_assign_r50_fpn_1x_coco_20210413_115540-5e17991f.log.json) |
+
+**Note**:
+
+1. We find that the performance is unstable with 1x setting and may fluctuate by about 0.3 mAP. mAP 40.3 ~ 40.6 is acceptable. Such fluctuation can also be found in the original implementation.
+2. You can get a more stable results ~ mAP 40.6 with a schedule total 13 epoch, and learning rate is divided by 10 at 10th and 13th epoch.
+
+## Citation
+
+```latex
+@article{zhu2020autoassign,
+  title={AutoAssign: Differentiable Label Assignment for Dense Object Detection},
+  author={Zhu, Benjin and Wang, Jianfeng and Jiang, Zhengkai and Zong, Fuhang and Liu, Songtao and Li, Zeming and Sun, Jian},
+  journal={arXiv preprint arXiv:2007.03496},
+  year={2020}
+}
+```

configs/backup/autoassign/autoassign_r50-caffe_fpn_1x_coco.py

@@ -0,0 +1,69 @@
+# We follow the original implementation which
+# adopts the Caffe pre-trained backbone.
+_base_ = [
+    '../_base_/datasets/coco_detection.py',
+    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+# model settings
+model = dict(
+    type='AutoAssign',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[102.9801, 115.9465, 122.7717],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs=True,
+        num_outs=5,
+        relu_before_extra_convs=True,
+        init_cfg=dict(type='Caffe2Xavier', layer='Conv2d')),
+    bbox_head=dict(
+        type='AutoAssignHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        strides=[8, 16, 32, 64, 128],
+        loss_bbox=dict(type='GIoULoss', loss_weight=5.0)),
+    train_cfg=None,
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms', iou_threshold=0.6),
+        max_per_img=100))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0,
+        end=1000),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=12,
+        by_epoch=True,
+        milestones=[8, 11],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(lr=0.01), paramwise_cfg=dict(norm_decay_mult=0.))