init

.dev_scripts/gather_models.py

+# Copyright (c) OpenMMLab. All rights reserved.
+import argparse
+import glob
+import os
+import os.path as osp
+import shutil
+import subprocess
+import time
+from collections import OrderedDict
+
+import torch
+import yaml
+from mmengine.config import Config
+from mmengine.fileio import dump
+from mmengine.utils import digit_version, mkdir_or_exist, scandir
+
+
+def ordered_yaml_dump(data, stream=None, Dumper=yaml.SafeDumper, **kwds):
+
+    class OrderedDumper(Dumper):
+        pass
+
+    def _dict_representer(dumper, data):
+        return dumper.represent_mapping(
+            yaml.resolver.BaseResolver.DEFAULT_MAPPING_TAG, data.items())
+
+    OrderedDumper.add_representer(OrderedDict, _dict_representer)
+    return yaml.dump(data, stream, OrderedDumper, **kwds)
+
+
+def process_checkpoint(in_file, out_file):
+    checkpoint = torch.load(in_file, map_location='cpu')
+    # remove optimizer for smaller file size
+    if 'optimizer' in checkpoint:
+        del checkpoint['optimizer']
+    if 'ema_state_dict' in checkpoint:
+        del checkpoint['ema_state_dict']
+
+    # remove ema state_dict
+    for key in list(checkpoint['state_dict']):
+        if key.startswith('ema_'):
+            checkpoint['state_dict'].pop(key)
+        elif key.startswith('data_preprocessor'):
+            checkpoint['state_dict'].pop(key)
+
+    # if it is necessary to remove some sensitive data in checkpoint['meta'],
+    # add the code here.
+    if digit_version(torch.__version__) >= digit_version('1.6'):
+        torch.save(checkpoint, out_file, _use_new_zipfile_serialization=False)
+    else:
+        torch.save(checkpoint, out_file)
+    sha = subprocess.check_output(['sha256sum', out_file]).decode()
+    final_file = out_file.rstrip('.pth') + '-{}.pth'.format(sha[:8])
+    subprocess.Popen(['mv', out_file, final_file])
+    return final_file
+
+
+def is_by_epoch(config):
+    cfg = Config.fromfile('./configs/' + config)
+    return cfg.train_cfg.type == 'EpochBasedTrainLoop'
+
+
+def get_final_epoch_or_iter(config):
+    cfg = Config.fromfile('./configs/' + config)
+    if cfg.train_cfg.type == 'EpochBasedTrainLoop':
+        return cfg.train_cfg.max_epochs
+    else:
+        return cfg.train_cfg.max_iters
+
+
+def get_best_epoch_or_iter(exp_dir):
+    best_epoch_iter_full_path = list(
+        sorted(glob.glob(osp.join(exp_dir, 'best_*.pth'))))[-1]
+    best_epoch_or_iter_model_path = best_epoch_iter_full_path.split('/')[-1]
+    best_epoch_or_iter = best_epoch_or_iter_model_path.\
+        split('_')[-1].split('.')[0]
+    return best_epoch_or_iter_model_path, int(best_epoch_or_iter)
+
+
+def get_real_epoch_or_iter(config):
+    cfg = Config.fromfile('./configs/' + config)
+    if cfg.train_cfg.type == 'EpochBasedTrainLoop':
+        epoch = cfg.train_cfg.max_epochs
+        return epoch
+    else:
+        return cfg.train_cfg.max_iters
+
+
+def get_final_results(log_json_path,
+                      epoch_or_iter,
+                      results_lut='coco/bbox_mAP',
+                      by_epoch=True):
+    result_dict = dict()
+    with open(log_json_path) as f:
+        r = f.readlines()[-1]
+        last_metric = r.split(',')[0].split(': ')[-1].strip()
+    result_dict[results_lut] = last_metric
+    return result_dict
+
+
+def get_dataset_name(config):
+    # If there are more dataset, add here.
+    name_map = dict(
+        CityscapesDataset='Cityscapes',
+        CocoDataset='COCO',
+        CocoPanopticDataset='COCO',
+        DeepFashionDataset='Deep Fashion',
+        LVISV05Dataset='LVIS v0.5',
+        LVISV1Dataset='LVIS v1',
+        VOCDataset='Pascal VOC',
+        WIDERFaceDataset='WIDER Face',
+        OpenImagesDataset='OpenImagesDataset',
+        OpenImagesChallengeDataset='OpenImagesChallengeDataset',
+        Objects365V1Dataset='Objects365 v1',
+        Objects365V2Dataset='Objects365 v2')
+    cfg = Config.fromfile('./configs/' + config)
+    return name_map[cfg.dataset_type]
+
+
+def find_last_dir(model_dir):
+    dst_times = []
+    for time_stamp in os.scandir(model_dir):
+        if osp.isdir(time_stamp):
+            dst_time = time.mktime(
+                time.strptime(time_stamp.name, '%Y%m%d_%H%M%S'))
+            dst_times.append([dst_time, time_stamp.name])
+    return max(dst_times, key=lambda x: x[0])[1]
+
+
+def convert_model_info_to_pwc(model_infos):
+    pwc_files = {}
+    for model in model_infos:
+        cfg_folder_name = osp.split(model['config'])[-2]
+        pwc_model_info = OrderedDict()
+        pwc_model_info['Name'] = osp.split(model['config'])[-1].split('.')[0]
+        pwc_model_info['In Collection'] = 'Please fill in Collection name'
+        pwc_model_info['Config'] = osp.join('configs', model['config'])
+
+        # get metadata
+        meta_data = OrderedDict()
+        if 'epochs' in model:
+            meta_data['Epochs'] = get_real_epoch_or_iter(model['config'])
+        else:
+            meta_data['Iterations'] = get_real_epoch_or_iter(model['config'])
+        pwc_model_info['Metadata'] = meta_data
+
+        # get dataset name
+        dataset_name = get_dataset_name(model['config'])
+
+        # get results
+        results = []
+        # if there are more metrics, add here.
+        if 'bbox_mAP' in model['results']:
+            metric = round(model['results']['bbox_mAP'] * 100, 1)
+            results.append(
+                OrderedDict(
+                    Task='Object Detection',
+                    Dataset=dataset_name,
+                    Metrics={'box AP': metric}))
+        if 'segm_mAP' in model['results']:
+            metric = round(model['results']['segm_mAP'] * 100, 1)
+            results.append(
+                OrderedDict(
+                    Task='Instance Segmentation',
+                    Dataset=dataset_name,
+                    Metrics={'mask AP': metric}))
+        if 'PQ' in model['results']:
+            metric = round(model['results']['PQ'], 1)
+            results.append(
+                OrderedDict(
+                    Task='Panoptic Segmentation',
+                    Dataset=dataset_name,
+                    Metrics={'PQ': metric}))
+        pwc_model_info['Results'] = results
+
+        link_string = 'https://download.openmmlab.com/mmdetection/v3.0/'
+        link_string += '{}/{}'.format(model['config'].rstrip('.py'),
+                                      osp.split(model['model_path'])[-1])
+        pwc_model_info['Weights'] = link_string
+        if cfg_folder_name in pwc_files:
+            pwc_files[cfg_folder_name].append(pwc_model_info)
+        else:
+            pwc_files[cfg_folder_name] = [pwc_model_info]
+    return pwc_files
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Gather benchmarked models')
+    parser.add_argument(
+        'root',
+        type=str,
+        default='work_dirs',
+        help='root path of benchmarked models to be gathered')
+    parser.add_argument(
+        '--out',
+        type=str,
+        default='gather',
+        help='output path of gathered models to be stored')
+    parser.add_argument(
+        '--best',
+        action='store_true',
+        help='whether to gather the best model.')
+
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = parse_args()
+    models_root = args.root
+    models_out = args.out
+    mkdir_or_exist(models_out)
+
+    # find all models in the root directory to be gathered
+    raw_configs = list(scandir('./configs', '.py', recursive=True))
+
+    # filter configs that is not trained in the experiments dir
+    used_configs = []
+    for raw_config in raw_configs:
+        if osp.exists(osp.join(models_root, raw_config)):
+            used_configs.append(raw_config)
+    print(f'Find {len(used_configs)} models to be gathered')
+
+    # find final_ckpt and log file for trained each config
+    # and parse the best performance
+    model_infos = []
+    for used_config in used_configs:
+        exp_dir = osp.join(models_root, used_config)
+        by_epoch = is_by_epoch(used_config)
+        # check whether the exps is finished
+        if args.best is True:
+            final_model, final_epoch_or_iter = get_best_epoch_or_iter(exp_dir)
+        else:
+            final_epoch_or_iter = get_final_epoch_or_iter(used_config)
+            final_model = '{}_{}.pth'.format('epoch' if by_epoch else 'iter',
+                                             final_epoch_or_iter)
+
+        model_path = osp.join(exp_dir, final_model)
+        # skip if the model is still training
+        if not osp.exists(model_path):
+            continue
+
+        # get the latest logs
+        latest_exp_name = find_last_dir(exp_dir)
+        latest_exp_json = osp.join(exp_dir, latest_exp_name, 'vis_data',
+                                   latest_exp_name + '.json')
+
+        model_performance = get_final_results(
+            latest_exp_json, final_epoch_or_iter, by_epoch=by_epoch)
+
+        if model_performance is None:
+            continue
+
+        model_info = dict(
+            config=used_config,
+            results=model_performance,
+            final_model=final_model,
+            latest_exp_json=latest_exp_json,
+            latest_exp_name=latest_exp_name)
+        model_info['epochs' if by_epoch else 'iterations'] =\
+            final_epoch_or_iter
+        model_infos.append(model_info)
+
+    # publish model for each checkpoint
+    publish_model_infos = []
+    for model in model_infos:
+        model_publish_dir = osp.join(models_out, model['config'].rstrip('.py'))
+        mkdir_or_exist(model_publish_dir)
+
+        model_name = osp.split(model['config'])[-1].split('.')[0]
+
+        model_name += '_' + model['latest_exp_name']
+        publish_model_path = osp.join(model_publish_dir, model_name)
+        trained_model_path = osp.join(models_root, model['config'],
+                                      model['final_model'])
+
+        # convert model
+        final_model_path = process_checkpoint(trained_model_path,
+                                              publish_model_path)
+
+        # copy log
+        shutil.copy(model['latest_exp_json'],
+                    osp.join(model_publish_dir, f'{model_name}.log.json'))
+
+        # copy config to guarantee reproducibility
+        config_path = model['config']
+        config_path = osp.join(
+            'configs',
+            config_path) if 'configs' not in config_path else config_path
+        target_config_path = osp.split(config_path)[-1]
+        shutil.copy(config_path, osp.join(model_publish_dir,
+                                          target_config_path))
+
+        model['model_path'] = final_model_path
+        publish_model_infos.append(model)
+
+    models = dict(models=publish_model_infos)
+    print(f'Totally gathered {len(publish_model_infos)} models')
+    dump(models, osp.join(models_out, 'model_info.json'))
+
+    pwc_files = convert_model_info_to_pwc(publish_model_infos)
+    for name in pwc_files:
+        with open(osp.join(models_out, name + '_metafile.yml'), 'w') as f:
+            ordered_yaml_dump(pwc_files[name], f, encoding='utf-8')
+
+
+if __name__ == '__main__':
+    main()

.dev_scripts/gather_test_benchmark_metric.py

+# Copyright (c) OpenMMLab. All rights reserved.
+import argparse
+import glob
+import os.path as osp
+
+from mmengine.config import Config
+from mmengine.fileio import dump, load
+from mmengine.utils import mkdir_or_exist
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description='Gather benchmarked models metric')
+    parser.add_argument('config', help='test config file path')
+    parser.add_argument(
+        'root',
+        type=str,
+        help='root path of benchmarked models to be gathered')
+    parser.add_argument(
+        '--out', type=str, help='output path of gathered metrics to be stored')
+    parser.add_argument(
+        '--not-show', action='store_true', help='not show metrics')
+    parser.add_argument(
+        '--show-all', action='store_true', help='show all model metrics')
+
+    args = parser.parse_args()
+    return args
+
+
+if __name__ == '__main__':
+    args = parse_args()
+
+    root_path = args.root
+    metrics_out = args.out
+    result_dict = {}
+
+    cfg = Config.fromfile(args.config)
+
+    for model_key in cfg:
+        model_infos = cfg[model_key]
+        if not isinstance(model_infos, list):
+            model_infos = [model_infos]
+        for model_info in model_infos:
+            record_metrics = model_info['metric']
+            config = model_info['config'].strip()
+            fname, _ = osp.splitext(osp.basename(config))
+            metric_json_dir = osp.join(root_path, fname)
+            if osp.exists(metric_json_dir):
+                json_list = glob.glob(osp.join(metric_json_dir, '*.json'))
+                if len(json_list) > 0:
+                    log_json_path = list(sorted(json_list))[-1]
+
+                    metric = load(log_json_path)
+                    if config in metric.get('config', {}):
+
+                        new_metrics = dict()
+                        for record_metric_key in record_metrics:
+                            record_metric_key_bk = record_metric_key
+                            old_metric = record_metrics[record_metric_key]
+                            if record_metric_key == 'AR_1000':
+                                record_metric_key = 'AR@1000'
+                            if record_metric_key not in metric['metric']:
+                                raise KeyError(
+                                    'record_metric_key not exist, please '
+                                    'check your config')
+                            new_metric = round(
+                                metric['metric'][record_metric_key] * 100, 1)
+                            new_metrics[record_metric_key_bk] = new_metric
+
+                        if args.show_all:
+                            result_dict[config] = dict(
+                                before=record_metrics, after=new_metrics)
+                        else:
+                            for record_metric_key in record_metrics:
+                                old_metric = record_metrics[record_metric_key]
+                                new_metric = new_metrics[record_metric_key]
+                                if old_metric != new_metric:
+                                    result_dict[config] = dict(
+                                        before=record_metrics,
+                                        after=new_metrics)
+                                    break
+                    else:
+                        print(f'{config} not included in: {log_json_path}')
+                else:
+                    print(f'{config} not exist file: {metric_json_dir}')
+            else:
+                print(f'{config} not exist dir: {metric_json_dir}')
+
+    if metrics_out:
+        mkdir_or_exist(metrics_out)
+        dump(result_dict, osp.join(metrics_out, 'batch_test_metric_info.json'))
+    if not args.not_show:
+        print('===================================')
+        for config_name, metrics in result_dict.items():
+            print(config_name, metrics)
+        print('===================================')

.dev_scripts/gather_train_benchmark_metric.py

+# Copyright (c) OpenMMLab. All rights reserved.
+import argparse
+import glob
+import os.path as osp
+
+from gather_models import get_final_results
+from mmengine.config import Config
+from mmengine.fileio import dump
+from mmengine.utils import mkdir_or_exist
+
+try:
+    import xlrd
+except ImportError:
+    xlrd = None
+try:
+    import xlutils
+    from xlutils.copy import copy
+except ImportError:
+    xlutils = None
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description='Gather benchmarked models metric')
+    parser.add_argument(
+        'root',
+        type=str,
+        help='root path of benchmarked models to be gathered')
+    parser.add_argument(
+        'txt_path', type=str, help='txt path output by benchmark_filter')
+    parser.add_argument(
+        '--out', type=str, help='output path of gathered metrics to be stored')
+    parser.add_argument(
+        '--not-show', action='store_true', help='not show metrics')
+    parser.add_argument(
+        '--excel', type=str, help='input path of excel to be recorded')
+    parser.add_argument(
+        '--ncol', type=int, help='Number of column to be modified or appended')
+
+    args = parser.parse_args()
+    return args
+
+
+if __name__ == '__main__':
+    args = parse_args()
+
+    if args.excel:
+        assert args.ncol, 'Please specify "--excel" and "--ncol" ' \
+                          'at the same time'
+        if xlrd is None:
+            raise RuntimeError(
+                'xlrd is not installed,'
+                'Please use “pip install xlrd==1.2.0” to install')
+        if xlutils is None:
+            raise RuntimeError(
+                'xlutils is not installed,'
+                'Please use “pip install xlutils==2.0.0” to install')
+        readbook = xlrd.open_workbook(args.excel)
+        sheet = readbook.sheet_by_name('Sheet1')
+        sheet_info = {}
+        total_nrows = sheet.nrows
+        for i in range(3, sheet.nrows):
+            sheet_info[sheet.row_values(i)[0]] = i
+        xlrw = copy(readbook)
+        table = xlrw.get_sheet(0)
+
+    root_path = args.root
+    metrics_out = args.out
+
+    result_dict = {}
+    with open(args.txt_path, 'r') as f:
+        model_cfgs = f.readlines()
+        for i, config in enumerate(model_cfgs):
+            config = config.strip()
+            if len(config) == 0:
+                continue
+
+            config_name = osp.split(config)[-1]
+            config_name = osp.splitext(config_name)[0]
+            result_path = osp.join(root_path, config_name)
+            if osp.exists(result_path):
+                # 1 read config
+                cfg = Config.fromfile(config)
+                total_epochs = cfg.runner.max_epochs
+                final_results = cfg.evaluation.metric
+                if not isinstance(final_results, list):
+                    final_results = [final_results]
+                final_results_out = []
+                for key in final_results:
+                    if 'proposal_fast' in key:
+                        final_results_out.append('AR@1000')  # RPN
+                    elif 'mAP' not in key:
+                        final_results_out.append(key + '_mAP')
+
+                # 2 determine whether total_epochs ckpt exists
+                ckpt_path = f'epoch_{total_epochs}.pth'
+                if osp.exists(osp.join(result_path, ckpt_path)):
+                    log_json_path = list(
+                        sorted(glob.glob(osp.join(result_path,
+                                                  '*.log.json'))))[-1]
+
+                    # 3 read metric
+                    model_performance = get_final_results(
+                        log_json_path, total_epochs, final_results_out)
+                    if model_performance is None:
+                        print(f'log file error: {log_json_path}')
+                        continue
+                    for performance in model_performance:
+                        if performance in ['AR@1000', 'bbox_mAP', 'segm_mAP']:
+                            metric = round(
+                                model_performance[performance] * 100, 1)
+                            model_performance[performance] = metric
+                    result_dict[config] = model_performance
+
+                    # update and append excel content
+                    if args.excel:
+                        if 'AR@1000' in model_performance:
+                            metrics = f'{model_performance["AR@1000"]}' \
+                                      f'(AR@1000)'
+                        elif 'segm_mAP' in model_performance:
+                            metrics = f'{model_performance["bbox_mAP"]}/' \
+                                      f'{model_performance["segm_mAP"]}'
+                        else:
+                            metrics = f'{model_performance["bbox_mAP"]}'
+
+                        row_num = sheet_info.get(config, None)
+                        if row_num:
+                            table.write(row_num, args.ncol, metrics)
+                        else:
+                            table.write(total_nrows, 0, config)
+                            table.write(total_nrows, args.ncol, metrics)
+                            total_nrows += 1
+
+                else:
+                    print(f'{config} not exist: {ckpt_path}')
+            else:
+                print(f'not exist: {config}')
+
+        # 4 save or print results
+        if metrics_out:
+            mkdir_or_exist(metrics_out)
+            dump(result_dict, osp.join(metrics_out, 'model_metric_info.json'))
+        if not args.not_show:
+            print('===================================')
+            for config_name, metrics in result_dict.items():
+                print(config_name, metrics)
+            print('===================================')
+        if args.excel:
+            filename, sufflx = osp.splitext(args.excel)
+            xlrw.save(f'{filename}_o{sufflx}')
+            print(f'>>> Output {filename}_o{sufflx}')

.dev_scripts/linter.sh

+yapf -r -i mmdet/ configs/ tests/ tools/
+isort -rc mmdet/ configs/ tests/ tools/
+flake8 .

.dev_scripts/test_init_backbone.py

+# Copyright (c) OpenMMLab. All rights reserved.
+"""Check out backbone whether successfully load pretrained checkpoint."""
+import copy
+import os
+from os.path import dirname, exists, join
+
+import pytest
+from mmengine.config import Config
+from mmengine.runner import CheckpointLoader
+from mmengine.utils import ProgressBar
+
+from mmdet.registry import MODELS
+
+
+def _get_config_directory():
+    """Find the predefined detector config directory."""
+    try:
+        # Assume we are running in the source mmdetection repo
+        repo_dpath = dirname(dirname(__file__))
+    except NameError:
+        # For IPython development when this __file__ is not defined
+        import mmdet
+        repo_dpath = dirname(dirname(mmdet.__file__))
+    config_dpath = join(repo_dpath, 'configs')
+    if not exists(config_dpath):
+        raise Exception('Cannot find config path')
+    return config_dpath
+
+
+def _get_config_module(fname):
+    """Load a configuration as a python module."""
+    config_dpath = _get_config_directory()
+    config_fpath = join(config_dpath, fname)
+    config_mod = Config.fromfile(config_fpath)
+    return config_mod
+
+
+def _get_detector_cfg(fname):
+    """Grab configs necessary to create a detector.
+
+    These are deep copied to allow for safe modification of parameters without
+    influencing other tests.
+    """
+    config = _get_config_module(fname)
+    model = copy.deepcopy(config.model)
+    return model
+
+
+def _traversed_config_file():
+    """We traversed all potential config files under the `config` file. If you
+    need to print details or debug code, you can use this function.
+
+    If the `backbone.init_cfg` is None (do not use `Pretrained` init way), you
+    need add the folder name in `ignores_folder` (if the config files in this
+    folder all set backbone.init_cfg is None) or add config name in
+    `ignores_file` (if the config file set backbone.init_cfg is None)
+    """
+    config_path = _get_config_directory()
+    check_cfg_names = []
+
+    # `base`, `legacy_1.x` and `common` ignored by default.
+    ignores_folder = ['_base_', 'legacy_1.x', 'common']
+    # 'ld' need load teacher model, if want to check 'ld',
+    # please check teacher_config path first.
+    ignores_folder += ['ld']
+    # `selfsup_pretrain` need convert model, if want to check this model,
+    # need to convert the model first.
+    ignores_folder += ['selfsup_pretrain']
+
+    # the `init_cfg` in 'centripetalnet', 'cornernet', 'cityscapes',
+    # 'scratch' is None.
+    # the `init_cfg` in ssdlite(`ssdlite_mobilenetv2_scratch_600e_coco.py`)
+    # is None
+    # Please confirm `bockbone.init_cfg` is None first.
+    ignores_folder += ['centripetalnet', 'cornernet', 'cityscapes', 'scratch']
+    ignores_file = ['ssdlite_mobilenetv2_scratch_600e_coco.py']
+
+    for config_file_name in os.listdir(config_path):
+        if config_file_name not in ignores_folder:
+            config_file = join(config_path, config_file_name)
+            if os.path.isdir(config_file):
+                for config_sub_file in os.listdir(config_file):
+                    if config_sub_file.endswith('py') and \
+                            config_sub_file not in ignores_file:
+                        name = join(config_file, config_sub_file)
+                        check_cfg_names.append(name)
+    return check_cfg_names
+
+
+def _check_backbone(config, print_cfg=True):
+    """Check out backbone whether successfully load pretrained model, by using
+    `backbone.init_cfg`.
+
+    First, using `CheckpointLoader.load_checkpoint` to load the checkpoint
+        without loading models.
+    Then, using `MODELS.build` to build models, and using
+        `model.init_weights()` to initialize the parameters.
+    Finally, assert weights and bias of each layer loaded from pretrained
+        checkpoint are equal to the weights and bias of original checkpoint.
+        For the convenience of comparison, we sum up weights and bias of
+        each loaded layer separately.
+
+    Args:
+        config (str): Config file path.
+        print_cfg (bool): Whether print logger and return the result.
+
+    Returns:
+        results (str or None): If backbone successfully load pretrained
+            checkpoint, return None; else, return config file path.
+    """
+    if print_cfg:
+        print('-' * 15 + 'loading ', config)
+    cfg = Config.fromfile(config)
+    init_cfg = None
+    try:
+        init_cfg = cfg.model.backbone.init_cfg
+        init_flag = True
+    except AttributeError:
+        init_flag = False
+    if init_cfg is None or init_cfg.get('type') != 'Pretrained':
+        init_flag = False
+    if init_flag:
+        checkpoint = CheckpointLoader.load_checkpoint(init_cfg.checkpoint)
+        if 'state_dict' in checkpoint:
+            state_dict = checkpoint['state_dict']
+        else:
+            state_dict = checkpoint
+
+        model = MODELS.build(cfg.model)
+        model.init_weights()
+
+        checkpoint_layers = state_dict.keys()
+        for name, value in model.backbone.state_dict().items():
+            if name in checkpoint_layers:
+                assert value.equal(state_dict[name])
+
+        if print_cfg:
+            print('-' * 10 + 'Successfully load checkpoint' + '-' * 10 +
+                  '\n', )
+            return None
+    else:
+        if print_cfg:
+            print(config + '\n' + '-' * 10 +
+                  'config file do not have init_cfg' + '-' * 10 + '\n')
+            return config
+
+
+@pytest.mark.parametrize('config', _traversed_config_file())
+def test_load_pretrained(config):
+    """Check out backbone whether successfully load pretrained model by using
+    `backbone.init_cfg`.
+
+    Details please refer to `_check_backbone`
+    """
+    _check_backbone(config, print_cfg=False)
+
+
+def _test_load_pretrained():
+    """We traversed all potential config files under the `config` file. If you
+    need to print details or debug code, you can use this function.
+
+    Returns:
+        check_cfg_names (list[str]): Config files that backbone initialized
+        from pretrained checkpoint might be problematic. Need to recheck
+        the config file. The output including the config files that the
+        backbone.init_cfg is None
+    """
+    check_cfg_names = _traversed_config_file()
+    need_check_cfg = []
+
+    prog_bar = ProgressBar(len(check_cfg_names))
+    for config in check_cfg_names:
+        init_cfg_name = _check_backbone(config)
+        if init_cfg_name is not None:
+            need_check_cfg.append(init_cfg_name)
+        prog_bar.update()
+    print('These config files need to be checked again')
+    print(need_check_cfg)

.github/CODE_OF_CONDUCT.md

+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+- Using welcoming and inclusive language
+- Being respectful of differing viewpoints and experiences
+- Gracefully accepting constructive criticism
+- Focusing on what is best for the community
+- Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+- The use of sexualized language or imagery and unwelcome sexual attention or
+  advances
+- Trolling, insulting/derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at chenkaidev@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+For answers to common questions about this code of conduct, see
+https://www.contributor-covenant.org/faq
+
+[homepage]: https://www.contributor-covenant.org

.github/CONTRIBUTING.md

+We appreciate all contributions to improve MMDetection. Please refer to [CONTRIBUTING.md](https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md) in MMCV for more details about the contributing guideline.

.github/ISSUE_TEMPLATE/config.yml

+blank_issues_enabled: false
+
+contact_links:
+  - name: Common Issues
+    url: https://mmdetection.readthedocs.io/en/latest/faq.html
+    about: Check if your issue already has solutions
+  - name: MMDetection Documentation
+    url: https://mmdetection.readthedocs.io/en/latest/
+    about: Check if your question is answered in docs

.github/ISSUE_TEMPLATE/error-report.md

+---
+name: Error report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+---
+
+Thanks for your error report and we appreciate it a lot.
+
+**Checklist**
+
+1. I have searched related issues but cannot get the expected help.
+2. I have read the [FAQ documentation](https://mmdetection.readthedocs.io/en/latest/faq.html) but cannot get the expected help.
+3. The bug has not been fixed in the latest version.
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**Reproduction**
+
+1. What command or script did you run?
+
+```none
+A placeholder for the command.
+```
+
+2. Did you make any modifications on the code or config? Did you understand what you have modified?
+3. What dataset did you use?
+
+**Environment**
+
+1. Please run `python mmdet/utils/collect_env.py` to collect necessary environment information and paste it here.
+2. You may add addition that may be helpful for locating the problem, such as
+   - How you installed PyTorch \[e.g., pip, conda, source\]
+   - Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
+
+**Error traceback**
+If applicable, paste the error trackback here.
+
+```none
+A placeholder for trackback.
+```
+
+**Bug fix**
+If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

.github/ISSUE_TEMPLATE/feature_request.md

+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+---
+
+**Describe the feature**
+
+**Motivation**
+A clear and concise description of the motivation of the feature.
+Ex1. It is inconvenient when \[....\].
+Ex2. There is a recent paper \[....\], which is very helpful for \[....\].
+
+**Related resources**
+If there is an official code release or third-party implementations, please also provide the information here, which would be very helpful.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.
+If you would like to implement the feature and create a PR, please leave a comment here and that would be much appreciated.

.github/ISSUE_TEMPLATE/general_questions.md

+---
+name: General questions
+about: Ask general questions to get help
+title: ''
+labels: ''
+assignees: ''
+---

.github/ISSUE_TEMPLATE/reimplementation_questions.md

+---
+name: Reimplementation Questions
+about: Ask about questions during model reimplementation
+title: ''
+labels: reimplementation
+assignees: ''
+---
+
+**Notice**
+
+There are several common situations in the reimplementation issues as below
+
+1. Reimplement a model in the model zoo using the provided configs
+2. Reimplement a model in the model zoo on other dataset (e.g., custom datasets)
+3. Reimplement a custom model but all the components are implemented in MMDetection
+4. Reimplement a custom model with new modules implemented by yourself
+
+There are several things to do for different cases as below.
+
+- For case 1 & 3, please follow the steps in the following sections thus we could help to quick identify the issue.
+- For case 2 & 4, please understand that we are not able to do much help here because we usually do not know the full code and the users should be responsible to the code they write.
+- One suggestion for case 2 & 4 is that the users should first check whether the bug lies in the self-implemented code or the original code. For example, users can first make sure that the same model runs well on supported datasets. If you still need help, please describe what you have done and what you obtain in the issue, and follow the steps in the following sections and try as clear as possible so that we can better help you.
+
+**Checklist**
+
+1. I have searched related issues but cannot get the expected help.
+2. The issue has not been fixed in the latest version.
+
+**Describe the issue**
+
+A clear and concise description of what the problem you meet and what have you done.
+
+**Reproduction**
+
+1. What command or script did you run?
+
+```none
+A placeholder for the command.
+```
+
+2. What config dir you run?
+
+```none
+A placeholder for the config.
+```
+
+3. Did you make any modifications on the code or config? Did you understand what you have modified?
+4. What dataset did you use?
+
+**Environment**
+
+1. Please run `python mmdet/utils/collect_env.py` to collect necessary environment information and paste it here.
+2. You may add addition that may be helpful for locating the problem, such as
+   1. How you installed PyTorch \[e.g., pip, conda, source\]
+   2. Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
+
+**Results**
+
+If applicable, paste the related results here, e.g., what you expect and what you get.
+
+```none
+A placeholder for results comparison
+```
+
+**Issue fix**
+
+If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

.github/pull_request_template.md

+Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
+
+## Motivation
+
+Please describe the motivation of this PR and the goal you want to achieve through this PR.
+
+## Modification
+
+Please briefly describe what modification is made in this PR.
+
+## BC-breaking (Optional)
+
+Does the modification introduce changes that break the backward-compatibility of the downstream repos?
+If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
+
+## Use cases (Optional)
+
+If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
+
+## Checklist
+
+1. Pre-commit or other linting tools are used to fix the potential lint issues.
+2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
+3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMPreTrain.
+4. The documentation has been modified accordingly, like docstring or example tutorials.

.github/workflows/deploy.yml

+name: deploy
+
+on: push
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build-n-publish:
+    runs-on: ubuntu-latest
+    if: startsWith(github.event.ref, 'refs/tags')
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.7
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.7
+      - name: Install torch
+        run: pip install torch
+      - name: Install wheel
+        run: pip install wheel
+      - name: Build MMDetection
+        run: python setup.py sdist bdist_wheel
+      - name: Publish distribution to PyPI
+        run: |
+          pip install twine
+          twine upload dist/* -u __token__ -p ${{ secrets.pypi_password }}

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/en/_build/
+docs/zh_cn/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+data/
+data
+.vscode
+.idea
+.DS_Store
+
+# custom
+*.pkl
+*.pkl.json
+*.log.json
+docs/modelzoo_statistics.md
+mmdet/.mim
+work_dirs/
+
+# Pytorch
+*.pth
+*.py~
+*.sh~

.owners.yml

+assign:
+  strategy:
+    # random
+    daily-shift-based
+  scedule:
+    '*/1 * * * *'
+  assignees:
+    - Czm369
+    - hhaAndroid
+    - jbwang1997
+    - RangiLyu
+    - BIGWangYuDong
+    - chhluo
+    - ZwwWayne

.pre-commit-config-zh-cn.yaml

+exclude: ^tests/data/
+repos:
+  - repo: https://gitee.com/openmmlab/mirrors-flake8
+    rev: 5.0.4
+    hooks:
+      - id: flake8
+  - repo: https://gitee.com/openmmlab/mirrors-isort
+    rev: 5.11.5
+    hooks:
+      - id: isort
+  - repo: https://gitee.com/openmmlab/mirrors-yapf
+    rev: v0.32.0
+    hooks:
+      - id: yapf
+  - repo: https://gitee.com/openmmlab/mirrors-pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: requirements-txt-fixer
+      - id: double-quote-string-fixer
+      - id: check-merge-conflict
+      - id: fix-encoding-pragma
+        args: ["--remove"]
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+  - repo: https://gitee.com/openmmlab/mirrors-mdformat
+    rev: 0.7.9
+    hooks:
+      - id: mdformat
+        args: ["--number"]
+        additional_dependencies:
+          - mdformat-openmmlab
+          - mdformat_frontmatter
+          - linkify-it-py
+  - repo: https://gitee.com/openmmlab/mirrors-codespell
+    rev: v2.2.1
+    hooks:
+      - id: codespell
+  - repo: https://gitee.com/openmmlab/mirrors-docformatter
+    rev: v1.3.1
+    hooks:
+      - id: docformatter
+        args: ["--in-place", "--wrap-descriptions", "79"]
+  - repo: https://gitee.com/openmmlab/mirrors-pyupgrade
+    rev: v3.0.0
+    hooks:
+      - id: pyupgrade
+        args: ["--py36-plus"]
+  - repo: https://gitee.com/open-mmlab/pre-commit-hooks
+    rev: v0.2.0
+    hooks:
+      - id: check-algo-readme
+      - id: check-copyright
+        args: ["mmdet"]
+#  - repo: https://gitee.com/openmmlab/mirrors-mypy
+#    rev: v0.812
+#    hooks:
+#      - id: mypy
+#        exclude: "docs"

.pre-commit-config.yaml

+repos:
+  - repo: https://github.com/PyCQA/flake8
+    rev: 5.0.4
+    hooks:
+      - id: flake8
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.11.5
+    hooks:
+      - id: isort
+  - repo: https://github.com/pre-commit/mirrors-yapf
+    rev: v0.32.0
+    hooks:
+      - id: yapf
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: requirements-txt-fixer
+      - id: double-quote-string-fixer
+      - id: check-merge-conflict
+      - id: fix-encoding-pragma
+        args: ["--remove"]
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.1
+    hooks:
+      - id: codespell
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.9
+    hooks:
+      - id: mdformat
+        args: ["--number"]
+        additional_dependencies:
+          - mdformat-openmmlab
+          - mdformat_frontmatter
+          - linkify-it-py
+  - repo: https://github.com/myint/docformatter
+    rev: v1.3.1
+    hooks:
+      - id: docformatter
+        args: ["--in-place", "--wrap-descriptions", "79"]
+  - repo: https://github.com/open-mmlab/pre-commit-hooks
+    rev: v0.2.0  # Use the ref you want to point at
+    hooks:
+      - id: check-algo-readme
+      - id: check-copyright
+        args: ["mmdet"]  # replace the dir_to_check with your expected directory to check