def __init__(self,
dataset,
num_replicas=None,
rank=None,
shuffle=True,
seed=0):
super().__init__(dataset,
num_replicas=num_replicas,
rank=rank,
shuffle=shuffle)
# In distributed sampling, different ranks should sample
# non-overlapped data in the dataset. Therefore, this function
# is used to make sure that each rank shuffles the data indices
# in the same order based on the same seed. Then different ranks
# could use different indices to select non-overlapped data from the
# same data list.
device = get_device()
self.seed = sync_random_seed(seed, device)
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
# replace the ${key} with the value of cfg.key
cfg = replace_cfg_vals(cfg)
# update data root according to MMDET_DATASETS
update_data_root(cfg)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
cfg = compat_cfg(cfg)
# set multi-process settings
setup_multi_processes(cfg)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if 'pretrained' in cfg.model:
cfg.model.pretrained = None
elif 'init_cfg' in cfg.model.backbone:
cfg.model.backbone.init_cfg = None
if cfg.model.get('neck'):
if isinstance(cfg.model.neck, list):
for neck_cfg in cfg.model.neck:
if neck_cfg.get('rfp_backbone'):
if neck_cfg.rfp_backbone.get('pretrained'):
neck_cfg.rfp_backbone.pretrained = None
elif cfg.model.neck.get('rfp_backbone'):
if cfg.model.neck.rfp_backbone.get('pretrained'):
cfg.model.neck.rfp_backbone.pretrained = None
# override img_scale
if args.img_scale_short is not None:
img_scale = [(round(short * args.img_aspect_ratio), short)
for short in args.img_scale_short]
cfg.data.test.pipeline[1].img_scale = img_scale
print('test img_scale:', cfg.data.test.pipeline[1].img_scale)
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids[0:1]
warnings.warn('`--gpu-ids` is deprecated, please use `--gpu-id`. '
'Because we only support single GPU mode in '
'non-distributed testing. Use the first GPU '
'in `gpu_ids` now.')
else:
cfg.gpu_ids = [args.gpu_id]
cfg.device = get_device()
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
test_dataloader_default_args = dict(samples_per_gpu=1,
workers_per_gpu=2,
dist=distributed,
shuffle=False)
# in case the test dataset is concatenated
if isinstance(cfg.data.test, dict):
cfg.data.test.test_mode = True
if cfg.data.test_dataloader.get('samples_per_gpu', 1) > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(
cfg.data.test.pipeline)
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
if cfg.data.test_dataloader.get('samples_per_gpu', 1) > 1:
for ds_cfg in cfg.data.test:
ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
test_loader_cfg = {
**test_dataloader_default_args,
**cfg.data.get('test_dataloader', {})
}
rank, _ = get_dist_info()
# allows not to create
if args.work_dir is not None and rank == 0:
mmcv.mkdir_or_exist(osp.abspath(args.work_dir))
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
json_file = osp.join(args.work_dir, f'eval_{timestamp}.json')
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset, **test_loader_cfg)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint.get('meta', {}):
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = build_dp(model, cfg.device, device_ids=cfg.gpu_ids)
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
args.show_score_thr)
else:
model = build_ddp(model,
cfg.device,
device_ids=[int(os.environ['LOCAL_RANK'])],
broadcast_buffers=False)
outputs = multi_gpu_test(
model, data_loader, args.tmpdir, args.gpu_collect
or cfg.evaluation.get('gpu_collect', False))
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
for key in [
'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best',
'rule', 'dynamic_intervals'
]:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
if 'area_range_type' in eval_kwargs:
metric = dataset.evaluate_custom(outputs, **eval_kwargs)
else:
metric = dataset.evaluate(outputs, **eval_kwargs)
print(metric)
metric_dict = dict(config=args.config, metric=metric)
if args.work_dir is not None and rank == 0:
mmcv.dump(metric_dict, json_file)
if args.img_scale_short is not None:
print('test img_scale:', cfg.data.test.pipeline[1].img_scale)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# replace the ${key} with the value of cfg.key
cfg = replace_cfg_vals(cfg)
# update data root according to MMDET_DATASETS
update_data_root(cfg)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
if args.auto_scale_lr:
if 'auto_scale_lr' in cfg and \
'enable' in cfg.auto_scale_lr and \
'base_batch_size' in cfg.auto_scale_lr:
cfg.auto_scale_lr.enable = True
else:
warnings.warn('Can not find "auto_scale_lr" or '
'"auto_scale_lr.enable" or '
'"auto_scale_lr.base_batch_size" in your'
' configuration file. Please update all the '
'configuration files to mmdet >= 2.24.1.')
# set multi-process settings
setup_multi_processes(cfg)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# work_dir is determined in this priority: CLI > segment in file > filename
if args.work_dir is not None:
# update configs according to CLI args if args.work_dir is not None
cfg.work_dir = args.work_dir
elif cfg.get('work_dir', None) is None:
# use config filename as default work_dir if cfg.work_dir is None
cfg.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.auto_resume = args.auto_resume
if args.gpus is not None:
cfg.gpu_ids = range(1)
warnings.warn('`--gpus` is deprecated because we only support '
'single GPU mode in non-distributed training. '
'Use `gpus=1` now.')
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids[0:1]
warnings.warn('`--gpu-ids` is deprecated, please use `--gpu-id`. '
'Because we only support single GPU mode in '
'non-distributed training. Use the first GPU '
'in `gpu_ids` now.')
if args.gpus is None and args.gpu_ids is None:
cfg.gpu_ids = [args.gpu_id]
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# re-set gpu_ids with distributed training mode
_, world_size = get_dist_info()
cfg.gpu_ids = range(world_size)
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# dump config
cfg.dump(osp.join(cfg.work_dir, osp.basename(args.config)))
# init the logger before other steps
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)
# init the meta dict to record some important information such as
# environment info and seed, which will be logged
meta = dict()
# log env info
env_info_dict = collect_env()
env_info = '\n'.join([(f'{k}: {v}') for k, v in env_info_dict.items()])
dash_line = '-' * 60 + '\n'
logger.info('Environment info:\n' + dash_line + env_info + '\n' +
dash_line)
meta['env_info'] = env_info
meta['config'] = cfg.pretty_text
# log some basic info
logger.info(f'Distributed training: {distributed}')
logger.info(f'Config:\n{cfg.pretty_text}')
cfg.device = get_device()
# set random seeds
seed = init_random_seed(args.seed, device=cfg.device)
seed = seed + dist.get_rank() if args.diff_seed else seed
logger.info(f'Set random seed to {seed}, '
f'deterministic: {args.deterministic}')
set_random_seed(seed, deterministic=args.deterministic)
cfg.seed = seed
meta['seed'] = seed
meta['exp_name'] = osp.basename(args.config)
model = build_detector(cfg.model,
train_cfg=cfg.get('train_cfg'),
test_cfg=cfg.get('test_cfg'))
model.init_weights()
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
val_dataset = copy.deepcopy(cfg.data.val)
val_dataset.pipeline = cfg.data.train.pipeline
datasets.append(build_dataset(val_dataset))
if cfg.checkpoint_config is not None:
# save mmdet version, config file content and class names in
# checkpoints as meta data
cfg.checkpoint_config.meta = dict(mmdet_version=__version__ +
get_git_hash()[:7],
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
train_detector(model,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
meta=meta)