def main():
args = parse_args()
assert args.out or args.show, \
('Please specify at least one operation (save or show the results) '
'with the argument "--out" or "--show"')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.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')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
rank, _ = get_dist_info()
if args.out and rank == 0:
print('\nwriting results to {}'.format(args.out))
mmcv.dump(outputs, args.out)
eval_types = args.eval
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = args.out
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_files = results2json(dataset, outputs, args.out)
coco_eval(result_files, eval_types, dataset.coco)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = args.out + '.{}'.format(name)
result_files = results2json(dataset, outputs_,
result_file)
coco_eval(result_files, eval_types, dataset.coco)
def main(args):
cfg = Config.fromfile(args.config)
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * cfg.gpus / 8
# 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)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
logger.info('MMDetection Version: {}'.format(__version__))
logger.info('Config: {}'.format(cfg.text))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
model = build_detector(
cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
# if cfg.weights2d_path[0] is not None and cfg.load_from is None:
# expand_sd = pretrain2d_to_3d(model, cfg.weights2d_path[0])
# model.load_state_dict(expand_sd, strict=False)
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
datasets.append(build_dataset(cfg.data.val))
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__,
config=cfg.text,
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
validate = cfg.get('evaluation', False)
model.CLASSES = datasets[0].CLASSES
train_detector(
model,
datasets,
cfg,
distributed=distributed,
validate=validate,
logger=logger)
def main():
args = parse_args()
# assert args.show or args.json_out, \
# ('Please specify at least one operation (save or show the results) '
# 'with the argument "--out" or "--show" or "--json_out"')
if args.json_out is not None and args.json_out.endswith('.json'):
args.json_out = args.json_out[:-5]
cfg = mmcv.Config.fromfile(args.config)
checkpoint_file = args.checkpoint
if not checkpoint_file:
def _epoch_num(name):
return int(
re.findall('epoch_[0-9]*.pth',
name)[0].replace('epoch_', '').replace('.pth', ''))
pths = sorted(glob.glob(os.path.join(cfg.work_dir, 'epoch_*.pth')),
key=_epoch_num)
if len(pths) > 0:
print("Found {}, use it as checkpoint by default.".format(
pths[-1]))
checkpoint_file = pths[-1]
if not checkpoint_file:
raise ValueError("Checkpoints not found, check work_dir non empty.")
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=args.shuffle) # TODO: hack shuffle True
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, checkpoint_file, map_location='cpu')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
num_evals = args.num_evals
if num_evals < 0:
num_evals = len(data_loader)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, num_evals, args.show)
rank, _ = get_dist_info()
if rank == 0:
gt_bboxes, gt_labels, gt_ignore, dataset_name = get_pascal_gts(
dataset, num_evals)
print('\nStarting evaluate {}'.format(dataset_name))
eval_map(outputs,
gt_bboxes,
gt_labels,
gt_ignore,
scale_ranges=None,
iou_thr=0.5,
dataset=dataset_name,
print_summary=True)
# Always output to pkl for analysing.
if args.out is None:
args.out = osp.join(
cfg.work_dir,
args.config.split('/')[-1].replace('.py', '_results.pkl'))
with open(args.out, 'wb') as f:
pickle.dump(outputs, f, pickle.HIGHEST_PROTOCOL)
# Save predictions in the COCO json format
if args.json_out and rank == 0:
if not isinstance(outputs[0], dict):
results2json(dataset, outputs, args.json_out)
else:
for name in outputs[0]:
outputs_ = [out[name] for out in outputs]
result_file = args.json_out + '.{}'.format(name)
results2json(dataset, outputs_, result_file)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
cfg.train_cfg.rcnn.sampler.add_gt_as_proposals = False # Actually it doesn't matter.
if args.ckpt:
cfg.resume_from = args.ckpt
if args.imgs_per_gpu > 0:
cfg.data.imgs_per_gpu = args.imgs_per_gpu
if args.nms_thr:
cfg.test_cfg.rcnn.nms.iou_thr = args.nms_thr
FOCAL_LENGTH = cfg.get('FOCAL_LENGTH', 1000)
# 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)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
# train_dataset = get_dataset(cfg.datasets[0].train)
train_dataset = get_dataset(cfg.datasets[1].train)
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__,
config=cfg.text,
CLASSES=train_dataset.CLASSES)
# add an attribute for visualization convenience
model.CLASSES = train_dataset.CLASSES
model = MMDataParallel(model, device_ids=range(cfg.gpus)).cuda()
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
runner = Runner(model, lambda x: x, optimizer, cfg.work_dir, cfg.log_level)
runner.resume(cfg.resume_from)
model = runner.model
# ONLY FOR DEBUG
# print('remove DDP for debug!')
# model = model._modules['module']
model.eval()
dataset_cfg = eval_dataset_mapper[args.dataset]
dataset_cfg.update(cfg.common_val_cfg)
dataset_cfg.pop('max_samples')
dataset = get_dataset(dataset_cfg)
# dataset.debugging = True
shuffle = False if args.dataset in stable_list else True
data_loader = build_dataloader_fuse(
dataset,
1,
0,
cfg.gpus,
dist=False,
shuffle=shuffle,
drop_last=False,
)
dump_dir = os.path.join(cfg.work_dir, f'eval_{args.dataset}')
os.makedirs(dump_dir, exist_ok=True)
if args.viz_dir:
os.makedirs(args.viz_dir, exist_ok=True)
eval_handler = eval_handler_mapper[args.dataset](
writer=tqdm.write,
viz_dir=args.viz_dir,
FOCAL_LENGTH=FOCAL_LENGTH,
work_dir=cfg.work_dir) # type: EvalHandler
with torch.no_grad():
for i, data_batch in enumerate(tqdm(data_loader)):
file_name = data_batch['img_meta'].data[0][0]['file_name']
try:
bbox_results, pred_results = model(**data_batch,
return_loss=False,
use_gt_bboxes=args.use_gt)
pred_results['bboxes'] = bbox_results
if args.paper_dir:
os.makedirs(args.paper_dir, exist_ok=True)
img = denormalize(data_batch['img'].data[0][0].numpy())
verts = pred_results['pred_vertices'] + pred_results[
'pred_translation']
dump_folder = osp.join(args.paper_dir, file_name)
os.makedirs(dump_folder, exist_ok=True)
plt.imsave(osp.join(dump_folder, 'img.png'), img)
for obj_i, vert in enumerate(verts):
nr.save_obj(osp.join(dump_folder, f'{obj_i}.obj'),
vert,
torch.tensor(smpl.faces.astype(np.int64)))
save_pack = eval_handler(data_batch,
pred_results,
use_gt=args.use_gt)
save_pack.update({'bbox_results': pred_results['bboxes']})
if args.dump_pkl:
with open(
osp.join(dump_dir,
f"{save_pack['file_name']}.pkl"),
'wb') as f:
pickle.dump(save_pack, f)
except Exception as e:
tqdm.write(f"Fail on {file_name}")
tqdm.write(str(e))
eval_handler.finalize()
def set_configuration(self, cfg_in):
cfg = self.get_configuration()
cfg.merge_config(cfg_in)
self._config_file = str(cfg.get_value("config_file"))
self._seed_weights = str(cfg.get_value("seed_weights"))
self._train_directory = str(cfg.get_value("train_directory"))
self._output_directory = str(cfg.get_value("output_directory"))
self._gpu_count = int(cfg.get_value("gpu_count"))
self._integer_labels = strtobool(cfg.get_value("integer_labels"))
self._launcher = str(cfg.get_value("launcher"))
self._validate = strtobool(cfg.get_value("validate"))
self._training_data = []
from mmcv import Config
self._cfg = Config.fromfile(self._config_file)
if self._cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if self._train_directory is not None:
self._cfg.work_dir = self._train_directory
self._groundtruth_store = os.path.join(self._train_directory,
self._tmp_annotation_file)
if not os.path.exists(self._train_directory):
os.mkdir(self._train_directory)
else:
self._groundtruth_store = self._tmp_annotation_file
if self._seed_weights is not None:
self._cfg.resume_from = self._seed_weights
if self._gpu_count > 0:
self._cfg.gpus = self._gpu_count
else:
self._cfg.gpus = torch.cuda.device_count()
if self._cfg.checkpoint_config is not None:
from mmdet import __version__
self._cfg.checkpoint_config.meta = dict(mmdet_version=__version__,
config=self._cfg.text)
if self._launcher == 'none':
self._distributed = False
else:
self._distributed = True
from mmdet.apis import init_dist
init_dist(self._launcher, **self._cfg.dist_params)
from mmdet.apis import get_root_logger
self._logger = get_root_logger(self._cfg.log_level)
self._logger.info('Distributed training: {}'.format(self._distributed))
if self._random_seed is not "none":
logger.info('Set random seed to {}'.format(self._random_seed))
from mmdet.apis import set_random_seed
set_random_seed(int(self._random_seed))
from mmdet.models import build_detector
self._model = build_detector(self._cfg.model,
train_cfg=self._cfg.train_cfg,
test_cfg=self._cfg.test_cfg)
def main():
args = parse_args()
assert args.out or args.show or args.json_out, \
('Please specify at least one operation (save or show the results) '
'with the argument "--out" or "--show" or "--json_out"')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
if args.json_out is not None and args.json_out.endswith('.json'):
args.json_out = args.json_out[:-5]
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
# cfg.data.test.test_mode = False
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
## uncomment to only eval on first 100 imgs
data_loader = build_dataloader(dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
print('load model from {}'.format(cfg.load_from))
# checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
checkpoint = load_checkpoint(model, cfg.load_from, map_location='cpu')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
# set0 = mmcv.load('../liyu_mmdet/set0.pkl')
# set1 = mmcv.load('../liyu_mmdet/set1.pkl')
# set2 = mmcv.load('../liyu_mmdet/set2.pkl')
# set3 = mmcv.load('../liyu_mmdet/set3.pkl')
# set4 = mmcv.load('../liyu_mmdet/set4.pkl')
# set5 = mmcv.load('../liyu_mmdet/set5.pkl')
# set6 = mmcv.load('../liyu_mmdet/set6.pkl')
# set7 = mmcv.load('../liyu_mmdet/set7.pkl')
# set0 = mmcv.load('./set0.pkl')
# set1 = mmcv.load('./set1.pkl')
# set2 = mmcv.load('./set2.pkl')
# set3 = mmcv.load('./set3.pkl')
# set4 = mmcv.load('./set4.pkl')
# set5 = mmcv.load('./set5.pkl')
# set6 = mmcv.load('./set6.pkl')
# set7 = mmcv.load('./set7.pkl')
# set_combine = set0+set1+set2+set3+set4+set5+set6+set7
# prefix = 'mrcnnr50_14.3_clshead'
# set0 = mmcv.load('./{}_set0.pkl'.format(prefix))
# set1 = mmcv.load('./{}_set1.pkl'.format(prefix))
# set2 = mmcv.load('./{}_set2.pkl'.format(prefix))
# set3 = mmcv.load('./{}_set3.pkl'.format(prefix))
# set_combine = set0+set1+set2+set3
# prefix = '/mrcnnr50_ag_coco_clshead'
prefix = 'mrcnnr50_ag_3fc_ft_cocolongtail_cat400_epoch_2'
prefix = 'mrcnn_r50_ag_cocolt'
print(prefix)
set0 = mmcv.load('./{}_set0.pkl'.format(prefix))
set1 = mmcv.load('./{}_set1.pkl'.format(prefix))
set2 = mmcv.load('./{}_set2.pkl'.format(prefix))
set3 = mmcv.load('./{}_set3.pkl'.format(prefix))
set4 = mmcv.load('./{}_set4.pkl'.format(prefix))
set5 = mmcv.load('./{}_set5.pkl'.format(prefix))
set6 = mmcv.load('./{}_set6.pkl'.format(prefix))
set7 = mmcv.load('./{}_set7.pkl'.format(prefix))
# set0 = mmcv.load('./set0.pkl')
# set1 = mmcv.load('./set1.pkl')
# set2 = mmcv.load('./set2.pkl')
# set3 = mmcv.load('./set3.pkl')
# set4 = mmcv.load('./set4.pkl')
# set5 = mmcv.load('./set5.pkl')
# set6 = mmcv.load('./set6.pkl')
# set7 = mmcv.load('./set7.pkl')
set_combine = set0 + set1 + set2 + set3 + set4 + set5 + set6 + set7
# set_liyu = mmcv.load('../mmdet_ensemble/results319.pkl')
# mmcv.dump(set_combine, args.out)
# result_files = results2json(dataset, set_combine,
# args.out)
print('pkl result dumped, start eval')
# result_files = results2json(dataset, set_combine,
# args.out, dump=False)
#
# lvis_eval(result_files, args.eval, dataset.lvis)
result_files = results2json(dataset, set_combine, args.out, dump=False)
coco_eval(result_files, args.eval, dataset.coco)
def evaluate_model(model_name, paper_arxiv_id, weights_url, weights_name,
paper_results, config):
print('---')
print('Now Evaluating %s' % model_name)
evaluator = COCOEvaluator(root='./.data/vision/coco',
model_name=model_name,
paper_arxiv_id=paper_arxiv_id,
paper_results=paper_results)
out = 'results.pkl'
launcher = 'none'
if out is not None and not out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(config)
cfg.data.test[
'ann_file'] = './.data/vision/coco/annotations/instances_val2017.json'
cfg.data.test['img_prefix'] = './.data/vision/coco/val2017/'
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
if launcher == 'none':
distributed = False
else:
distributed = True
init_dist(launcher, **cfg.dist_params)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
local_checkpoint, _ = urllib.request.urlretrieve(
weights_url, '%s/.cache/torch/%s' % (str(Path.home()), weights_name))
print(local_checkpoint)
# '/home/ubuntu/GCNet/mask_rcnn_r50_fpn_1x_20181010-069fa190.pth'
checkpoint = load_checkpoint(model, local_checkpoint, map_location='cpu')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
evaluator.reset_time()
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs, cache_exists = single_gpu_test(model, data_loader, False,
evaluator)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
if cache_exists:
print('Cache exists: %s' % (evaluator.batch_hash))
evaluator.save()
else:
from mmdet.core import results2json
rank, _ = get_dist_info()
if out and rank == 0:
print('\nwriting results to {}'.format(out))
mmcv.dump(outputs, out)
eval_types = ['bbox']
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = out
else:
if not isinstance(outputs[0], dict):
result_files = results2json(dataset, outputs, out)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = out + '.{}'.format(name)
result_files = results2json(
dataset, outputs_, result_file)
anns = json.load(open(result_files['bbox']))
evaluator.detections = []
evaluator.add(anns)
evaluator.save()
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
# 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)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
logger.info('after building detector')
cfg.past_iteration = args.past_iteration
# load model to continue training
if args.past_iteration > 0:
load_checkpoint(model, args.work_dir + 'epoch_1.pth')
logger.info('after loading checkpoint')
try:
datasets = eval(args.dataset)
ann_csvs = eval(args.ann_csv)
train_dataset = []
for i in range(len(datasets)):
cfg.data.train.img_prefix_list = [datasets[i]]
cfg.data.train.ann_file = ann_csvs[i]
train_dataset.append(get_dataset(cfg.data.train))
CLASSES = train_dataset[0].CLASSES
except:
cfg.data.train.img_prefix_list = [args.dataset]
cfg.data.train.ann_file = args.ann_csv
train_dataset = get_dataset(cfg.data.train)
CLASSES = train_dataset.CLASSES
logger.info('after getting 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__,
config=cfg.text,
CLASSES=CLASSES)
# add an attribute for visualization convenience
model.CLASSES = CLASSES
train_detector(model,
train_dataset,
cfg,
distributed=distributed,
validate=args.validate,
logger=logger)
logger.info('after training')
def main():
#os.environ["CUDA_VISIBLE_DEVICES"] = "1"
args = parse_args()
assert args.out or args.show, \
('Please specify at least one operation (save or show the results) '
'with the argument "--out" or "--show"')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.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')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
rank, _ = get_dist_info()
if args.out and rank == 0:
print('\nwriting results to {}'.format(args.out))
mmcv.dump(outputs, args.out)
result_file = args.out
# args = parser.parse_args()
# cfg = mmcv.Config.fromfile(args.config)
# test_dataset = mmcv.runner.obj_from_dict(cfg.data.test, datasets)
# txt_eval(args.result, test_dataset, args.iou_thr)
txt_eval(result_file, dataset, iou_thr=args.iou_thr)
def main():
args = parse_args()
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset_type = 'OIDSegDataset'
data_root = 'gs://oid2019/data/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True)
dataset = get_dataset(
dict(type=dataset_type,
ann_file='/home/bo_liu/' + args.ann_file,
img_prefix=data_root +
('val/'
if args.ann_file == 'seg_val_2844_ann.pkl' else 'OD_test/'),
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=True,
with_label=False,
test_mode=True))
data_loader = build_dataloader(dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
test_cfg = mmcv.ConfigDict(
dict(
rpn=dict(nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=args.thres,
# score_thr=0.0,
nms=dict(type=args.nms_type, iou_thr=0.5),
max_per_img=args.max_per_img,
mask_thr_binary=0.5),
keep_all_stages=False))
model = build_detector(cfg.model, train_cfg=None, test_cfg=test_cfg)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
rank, _ = get_dist_info()
if args.out and rank == 0:
print('writing results to {}'.format(args.out))
mmcv.dump(outputs, args.out)
eval_types = args.eval
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = args.out
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_file = args.out + '.json'
results2json(dataset, outputs, result_file)
coco_eval(result_file, eval_types, dataset.coco)
else:
for name in outputs[0]:
print('Evaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = args.out + '.{}.json'.format(name)
results2json(dataset, outputs_, result_file)
coco_eval(result_file, eval_types, dataset.coco)
def main(config,
work_dir=None,
resume_from=None,
validate=False,
visible_gpus='0,1,2,3',
gpus=1,
seed=None,
launcher='none',
local_rank=0,
autoscale_lr=False):
if 'LOCAL_RANK' not in os.environ:
os.environ['LOCAL_RANK'] = str(local_rank)
os.environ['CUDA_VISIBLE_DEVICES'] = visible_gpus
cfg = Config.fromfile(config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if work_dir is not None:
cfg.work_dir = work_dir
if resume_from is not None:
cfg.resume_from = resume_from
cfg.gpus = gpus
if autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * cfg.gpus / 8
# init distributed env first, since logger depends on the dist info.
if launcher == 'none':
distributed = False
else:
distributed = True
init_dist(launcher, **cfg.dist_params)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# set random seeds
if seed is not None:
logger.info('Set random seed to {}'.format(seed))
set_random_seed(seed)
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
datasets.append(build_dataset(cfg.data.val))
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__,
config=cfg.text,
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
train_detector(model,
datasets,
cfg,
distributed=distributed,
validate=validate,
logger=logger)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# 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.gpus = args.gpus
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * cfg.gpus / 8
# 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)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
model = build_detector(
cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
datasets.append(build_dataset(cfg.data.val))
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__,
config=cfg.text,
CLASSES=datasets[0].CLASSES)
maybe_init_wandb(cfg)
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
train_detector(
model,
datasets,
cfg,
distributed=distributed,
validate=args.validate,
logger=logger)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * cfg.gpus / 8
# 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)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
model = build_detector(
cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
if args.non_inplace:
convert_non_inplace(model)
if args.read_zip:
# cfg.data.train.img_prefix = cfg.data.train.img_prefix[:-1] + '.zip@/' + cfg.data.train.img_prefix.split('/')[-2] + '/'
# cfg.data.val.img_prefix = cfg.data.val.img_prefix[:-1] + '.zip@/' + cfg.data.val.img_prefix.split('/')[-2] + '/'
# cfg.data.test.img_prefix = cfg.data.test.img_prefix[:-1] + '.zip@/' + cfg.data.test.img_prefix.split('/')[-2] + '/'
cfg.data.train.img_prefix = cfg.data.train.img_prefix[:-1] + '.zip@/'
cfg.data.val.img_prefix = cfg.data.val.img_prefix[:-1] + '.zip@/'
cfg.data.test.img_prefix = cfg.data.test.img_prefix[:-1] + '.zip@/'
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
datasets.append(build_dataset(cfg.data.val))
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__,
config=cfg.text,
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
train_detector(
model,
datasets,
cfg,
distributed=distributed,
validate=args.validate,
logger=logger)
def main():
args = parse_args()
if args.json_out is not None and args.json_out.endswith('.json'):
args.json_out = args.json_out[:-5]
cfg = mmcv.Config.fromfile(args.config)
# Wudi change the args.out directly related to the model checkpoint file data
if args.horizontal_flip:
args.out = os.path.join(cfg.work_dir,
cfg.data.test.img_prefix.split('/')[-2].replace('_images', '_') +
args.checkpoint.split('/')[-1][:-4] + '_horizontal_flip.pkl')
print('horizontal_flip activated')
else:
args.out = os.path.join(cfg.work_dir,
cfg.data.test.img_prefix.split('/')[-2].replace('_images', '_') +
args.checkpoint.split('/')[-2][:-4] + '.pkl')
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
args.out = '/data/Kaggle/wudi_data/validation_Jan16-09-20.pkl'
if not os.path.exists(args.out):
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.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')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
mmcv.dump(outputs, args.out)
else:
outputs = mmcv.load(args.out)
if distributed:
rank, _ = get_dist_info()
if rank != 0:
return
outputs = outputs
local_rank = args.local_rank
world_size = args.world_size
for idx, output in enumerate(outputs):
#if idx % world_size == local_rank:
#if output[2]['file_name'].split('/')[-1] == 'ID_0cec00e6a.jpg':
if True:
finetune_RT(output, dataset,
draw_flag=True,
num_epochs=20,
loss_grayscale_light=0.02,
loss_grayscale_RT=0.02,
loss_IoU=0.95,
lr=0.05,
conf_thresh=0.8,
fix_rot=False,
tmp_save_dir='/data/Kaggle/wudi_data/tmp_output_grayscale')
def load_network(self):
train_config = "train_config.py"
if len(self._train_directory) > 0:
if not os.path.exists(self._train_directory):
os.mkdir(self._train_directory)
train_config = os.path.join(self._train_directory, train_config)
self.insert_training_params(self._config_file, train_config)
from mmcv import Config
self._cfg = Config.fromfile(train_config)
if self._cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if self._train_directory is not None:
self._cfg.work_dir = self._train_directory
self._groundtruth_store = os.path.join(self._train_directory,
self._tmp_annotation_file)
if not os.path.exists(self._train_directory):
os.mkdir(self._train_directory)
else:
self._groundtruth_store = self._tmp_annotation_file
if self._seed_weights is not None:
self._cfg.resume_from = self._seed_weights
if self._gpu_count > 0:
self._cfg.gpus = self._gpu_count
else:
self._cfg.gpus = torch.cuda.device_count()
if self._cfg.checkpoint_config is not None:
from mmdet import __version__
self._cfg.checkpoint_config.meta = dict(mmdet_version=__version__,
config=self._cfg.text)
if self._launcher == 'none':
self._distributed = False
else:
self._distributed = True
from mmdet.apis import init_dist
init_dist(self._launcher, **self._cfg.dist_params)
from mmdet.apis import get_root_logger
self._logger = get_root_logger(self._cfg.log_level)
self._logger.info('Distributed training: {}'.format(self._distributed))
if self._random_seed is not 'none':
self._logger.info('Set random seed to {}'.format(
self._random_seed))
from mmdet.apis import set_random_seed
if isinstance(self._random_seed, int):
set_random_seed(int(self._random_seed))
from mmdet.models import build_detector
if self._cfg.model['pretrained'] is not None:
if not os.path.exists(self._cfg.model['pretrained']):
dirname = os.path.dirname(self._config_file)
relpath = os.path.join(dirname, self._cfg.model['pretrained'])
if os.path.exists(relpath):
self._cfg.model['pretrained'] = relpath
self._model = build_detector(self._cfg.model,
train_cfg=self._cfg.train_cfg,
test_cfg=self._cfg.test_cfg)
def main():
args = parse_args()
assert args.out or args.show, \
('Please specify at least one operation (save or show the results) '
'with the argument "--out" or "--show"')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
# data_loader = build_dataloader(
# dataset,
# imgs_per_gpu=1,
# workers_per_gpu=cfg.data.workers_per_gpu,
# dist=distributed,
# shuffle=False)
#
# # build the model and load checkpoint
# model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.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.det_ckpt is not None:
# print('Loading Detection Models!!!!!!')
# det_ckpt = load_checkpoint(model, args.det_ckpt, map_location='cpu')
# # old versions did not save class info in checkpoints, this walkaround is
# # for backward compatibility
# if 'CLASSES' in checkpoint['meta']:
# model.CLASSES = checkpoint['meta']['CLASSES']
# else:
# model.CLASSES = dataset.CLASSES
#
# if not distributed:
# model = MMDataParallel(model, device_ids=[0])
# outputs = single_gpu_test(model, data_loader, args.show)
# else:
# model = MMDistributedDataParallel(model.cuda())
# outputs = multi_gpu_test(model, data_loader, args.tmpdir)
outputs = mmcv.load(args.out)
print('Finding video tubes...')
track_results = finding_video_tubes(outputs, dataset)
print('Finding video tubes done!')
# draw_results(track_results, dataset, args.out, cfg)
rank, _ = get_dist_info()
if args.out and rank == 0:
# print('\nwriting results to {}'.format(args.out))
# mmcv.dump(outputs, args.out)
# result_files = results2json(dataset, outputs['bbox_results'], args.out)
# coco_eval(result_files, ['bbox'], cfg.data.test.ann_file)
# For tracking
# result_files = results2json(dataset, track_results['bbox_results'],
# args.out)
# coco_eval(result_files, ['bbox'], cfg.data.test.ann_file)
print("Evaluating tracking...")
mdat_eval(track_results['track_results'], dataset, args.out, cfg)
def main():
args = parse_args()
assert args.out or args.show or args.json_out, \
('Please specify at least one operation (save or show the results) '
'with the argument "--out" or "--show" or "--json_out"')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
if args.json_out is not None and args.json_out.endswith('.json'):
args.json_out = args.json_out[:-5]
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
# cfg.data.test.test_mode = False
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
## uncomment to only eval on first 100 imgs
dataset.img_infos = dataset.img_infos[:20]
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
print('load model from {}'.format(cfg.load_from))
checkpoint = load_checkpoint(model, cfg.load_from, map_location='cpu')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
def load_ckpt(ncm_model, cal_head):
print('load cls head {}'.format('{}/{}.pth'.format(cfg.work_dir, cal_head)))
# epoch = torch.load('{}/{}_epoch.pth'.format(cfg.work_dir, cal_head))
load_checkpoint(ncm_model, '{}/{}.pth'.format(cfg.work_dir, cal_head))
# return epoch
print('use {}'.format(args.cal_head))
if len(dataset.CLASSES) == 1230:##lvis
if '2fc_rand' in args.cal_head:
calibrated_head = simple2fc().cuda()
elif '3fc_rand' in args.cal_head or '3fc_ft' in args.cal_head:
calibrated_head = simple3fc().cuda()
elif len(dataset.CLASSES) ==80:## coco
if '2fc_rand' in args.cal_head:
calibrated_head = simple2fc(num_classes=81).cuda()
elif '3fc_rand' in args.cal_head or '3fc_ft' in args.cal_head:
calibrated_head = simple3fc(num_classes=81).cuda()
# epoch = load_ckpt(calibrated_head, args.head_ckpt)
load_ckpt(calibrated_head, args.head_ckpt)
calibrated_head.eval()
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, calibrated_head, args.show)
else:
model = MMDistributedDataParallel(model.cuda())
calibrated_head = MMDistributedDataParallel(calibrated_head.cuda())
outputs = multi_gpu_test(model, data_loader, calibrated_head, args.show, args.tmpdir)
rank, _ = get_dist_info()
if args.out and rank == 0:
print('\nwriting results to {}'.format(args.out))
# mmcv.dump(outputs, args.out)
eval_types = args.eval
if len(dataset.CLASSES) == 1230:
if eval_types:
if eval_types == ['proposal_fast']:
result_file = args.out
lvis_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_files = results2json(dataset, outputs, args.out, dump=False)
print('Starting evaluate {}'.format(' and '.join(eval_types)))
lvis_eval(result_files, eval_types, dataset.lvis)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = args.out + '.{}'.format(name)
result_files = results2json(dataset, outputs_,
result_file)
lvis_eval(result_files, eval_types, dataset.coco)
elif len(dataset.CLASSES) == 80:
result_files = results2json(dataset, outputs, args.out, dump=False)
coco_eval(result_files, args.eval, dataset.coco)
# Save predictions in the COCO json format
if args.json_out and rank == 0:
if not isinstance(outputs[0], dict):
results2json(dataset, outputs, args.json_out)
else:
for name in outputs[0]:
outputs_ = [out[name] for out in outputs]
result_file = args.json_out + '.{}'.format(name)
results2json(dataset, outputs_, result_file)
def main():
args = parse_args()
assert type(args.input) is list()
N = len(args.input)
for ii in range(N):
if args.input[ii] is not None and not args.input[ii].endswith(
('.pkl', '.pickle')):
raise ValueError('The input file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
rank, _ = get_dist_info()
if args.input and rank == 0:
print('\n results is {}'.format(args.input))
root_Path = '/'.join(args.out[0].split('/')[:-1])
if not os.path.exists(root_Path):
os.makedirs(root_Path)
#mmcv.dump(outputs, args.out)
outputs = list()
print("{} models ".format(N))
for jj in range(N):
input = mmcv.load(args.input[jj])
print("{} images".format(len(input)))
for zz in range(len(input)):
if jj == 0:
outputs.append(input[zz])
else:
assert len(outputs[zz]) == len(input[zz])
outputs[zz].extend(input[zz])
mmcv.dump(outputs, args.out)
eval_types = args.eval
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if not args.is_coco:
# test VisDrone2019
if args.eval == ['bbox']:
print("eval {}".format(args.eval))
test_dataset = cfg.data.test
eval_visdrone_det(cfg.work_dir, args.out, test_dataset,
args.is_patch, args.show)
else:
if eval_types == ['proposal_fast']:
result_file = args.out
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_file = args.out + '.json'
results2json(dataset, outputs, result_file)
coco_eval(result_file, eval_types, dataset.coco)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = args.out + '.{}.json'.format(name)
results2json(dataset, outputs_, result_file)
coco_eval(result_file, eval_types, dataset.coco)
def main():
args = parse_args()
assert args.out or args.show, \
('Please specify at least one operation (save or show the results) '
'with the argument "--out" or "--show"')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
if args.workers == 0:
args.workers = cfg.data.workers_per_gpu
# 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)
# set random seeds
if args.seed is not None:
set_random_seed(args.seed)
if 'all' in args.corruptions:
corruptions = [
'gaussian_noise', 'shot_noise', 'impulse_noise', 'defocus_blur',
'glass_blur', 'motion_blur', 'zoom_blur', 'snow', 'frost', 'fog',
'brightness', 'contrast', 'elastic_transform', 'pixelate',
'jpeg_compression', 'speckle_noise', 'gaussian_blur', 'spatter',
'saturate'
]
elif 'benchmark' in args.corruptions:
corruptions = [
'gaussian_noise', 'shot_noise', 'impulse_noise', 'defocus_blur',
'glass_blur', 'motion_blur', 'zoom_blur', 'snow', 'frost', 'fog',
'brightness', 'contrast', 'elastic_transform', 'pixelate',
'jpeg_compression'
]
elif 'noise' in args.corruptions:
corruptions = ['gaussian_noise', 'shot_noise', 'impulse_noise']
elif 'blur' in args.corruptions:
corruptions = [
'defocus_blur', 'glass_blur', 'motion_blur', 'zoom_blur'
]
elif 'weather' in args.corruptions:
corruptions = ['snow', 'frost', 'fog', 'brightness']
elif 'digital' in args.corruptions:
corruptions = [
'contrast', 'elastic_transform', 'pixelate', 'jpeg_compression'
]
elif 'holdout' in args.corruptions:
corruptions = ['speckle_noise', 'gaussian_blur', 'spatter', 'saturate']
elif 'None' in args.corruptions:
corruptions = ['None']
args.severities = [0]
else:
corruptions = args.corruptions
aggregated_results = {}
for corr_i, corruption in enumerate(corruptions):
aggregated_results[corruption] = {}
for sev_i, corruption_severity in enumerate(args.severities):
# evaluate severity 0 (= no corruption) only once
if corr_i > 0 and corruption_severity == 0:
aggregated_results[corruption][0] = \
aggregated_results[corruptions[0]][0]
continue
test_data_cfg = copy.deepcopy(cfg.data.test)
# assign corruption and severity
if corruption_severity > 0:
corruption_trans = dict(type='Corrupt',
corruption=corruption,
severity=corruption_severity)
# TODO: hard coded "1", we assume that the first step is
# loading images, which needs to be fixed in the future
test_data_cfg['pipeline'].insert(1, corruption_trans)
# print info
print('\nTesting {} at severity {}'.format(corruption,
corruption_severity))
# build the dataloader
# TODO: support multiple images per gpu
# (only minor changes are needed)
dataset = build_dataset(test_data_cfg)
data_loader = build_dataloader(dataset,
imgs_per_gpu=1,
workers_per_gpu=args.workers,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model,
train_cfg=None,
test_cfg=cfg.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')
# old versions did not save class info in checkpoints,
# this walkaround is for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
rank, _ = get_dist_info()
if args.out and rank == 0:
eval_results_filename = (osp.splitext(args.out)[0] +
'_results' +
osp.splitext(args.out)[1])
mmcv.dump(outputs, args.out)
eval_types = args.eval
if cfg.dataset_type == 'VOCDataset':
if eval_types:
for eval_type in eval_types:
if eval_type == 'bbox':
test_dataset = mmcv.runner.obj_from_dict(
cfg.data.test, datasets)
mean_ap, eval_results = \
voc_eval_with_return(
args.out, test_dataset,
args.iou_thr, args.summaries)
aggregated_results[corruption][
corruption_severity] = eval_results
else:
print('\nOnly "bbox" evaluation \
is supported for pascal voc')
else:
if eval_types:
print('Starting evaluate {}'.format(
' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = args.out
else:
if not isinstance(outputs[0], dict):
result_files = results2json(
dataset, outputs, args.out)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = args.out
+ '.{}'.format(name)
result_files = results2json(
dataset, outputs_, result_file)
eval_results = coco_eval_with_return(
result_files, eval_types, dataset.coco)
aggregated_results[corruption][
corruption_severity] = eval_results
else:
print('\nNo task was selected for evaluation;'
'\nUse --eval to select a task')
# save results after each evaluation
mmcv.dump(aggregated_results, eval_results_filename)
# print filan results
print('\nAggregated results:')
prints = args.final_prints
aggregate = args.final_prints_aggregate
if cfg.dataset_type == 'VOCDataset':
get_results(eval_results_filename,
dataset='voc',
prints=prints,
aggregate=aggregate)
else:
get_results(eval_results_filename,
dataset='coco',
prints=prints,
aggregate=aggregate)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
if args.imgs_per_gpu > 0:
cfg.data.imgs_per_gpu = args.imgs_per_gpu
# 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)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
if hasattr(cfg, 'fuse') and cfg.fuse:
train_dataset = get_dataset(cfg.datasets[0].train)
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__,
config=cfg.text,
CLASSES=train_dataset.CLASSES)
# add an attribute for visualization convenience
model.CLASSES = train_dataset.CLASSES
datasets = list()
for flow in cfg.workflow:
mode, epoches = flow
cur_datasets = list()
for dataset_cfg in cfg.datasets:
if hasattr(dataset_cfg, mode):
cur_datasets.append(get_dataset(getattr(dataset_cfg,
mode)))
datasets.append(ConcatDataset(cur_datasets))
val_dataset = None
if cfg.data.train.get('val_every', None):
val_dataset = list()
for dataset_cfg in cfg.datasets:
if hasattr(dataset_cfg, 'val'):
val_dataset.append(get_dataset(dataset_cfg.val))
val_dataset = ConcatDataset(val_dataset)
if hasattr(cfg.model,
'smpl_head') and cfg.model.smpl_head.loss_cfg.get(
'adversarial_cfg', False):
train_adv_smpl_detector(
model,
datasets,
cfg,
distributed=distributed,
validate=args.validate,
logger=logger,
create_dummy=args.create_dummy,
val_dataset=val_dataset,
load_pretrain=args.load_pretrain,
)
else:
train_smpl_detector_fuse(model,
datasets,
cfg,
distributed=distributed,
validate=args.validate,
logger=logger,
create_dummy=args.create_dummy,
val_dataset=val_dataset,
load_pretrain=args.load_pretrain)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * cfg.gpus / 8
# 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)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
datasets.append(build_dataset(cfg.data.val))
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__,
config=cfg.text,
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
tune_part = cfg.get('selectp', 0)
if tune_part == 1:
print('Train fc_cls only.')
model = select_training_param(model)
elif tune_part == 2:
print('Train bbox head only.')
model = select_head(model)
elif tune_part == 3:
print('Train cascade fc_cls only.')
model = select_cascade_cls_params(model)
elif tune_part == 4:
print('Train bbox and mask head.')
model = select_mask_params(model)
else:
print('Train all params.')
train_detector(model,
datasets,
cfg,
distributed=distributed,
validate=args.validate,
logger=logger)
def main():
args = parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpuid
img_dir = args.img_dir
out_dir = args.out_dir
batch_size = args.batch_size
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
if args.img_dir != '':
file_list = common.load_filepaths(args.img_dir,
suffix=('.jpg', '.png', '.jpeg'),
recursive=True)
elif args.img_list != '':
file_list = parse_testfile(args.img_list)
else:
raise "Both img_dir and img_list is empty."
dataset = FilesDataset(file_list, cfg.test_pipeline)
data_loader = build_dataloader(dataset,
imgs_per_gpu=batch_size,
workers_per_gpu=batch_size,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.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')
model = reweight_cls(model, args.tau).cuda()
model = MMDataParallel(model, device_ids=[0])
model.eval()
count = 0
for i, data in enumerate(data_loader):
with torch.no_grad():
# bbox_results, segm_results
results = model(return_loss=False, rescale=True, **data)
# batch
#for result in results:
# file_path = file_list[count]
# save_name = file_path.replace('/home/songbai.xb/workspace/projects/TAO/data/TAO/frames/val/', '')
# save_path = os.path.join(out_dir, save_name)
# common.makedirs(os.path.dirname(save_path))
# save_in_tao_format(result, save_path)
# count += 1
file_path = file_list[i]
save_name = file_path.replace(
'/home/songbai.xb/workspace/projects/TAO/data/TAO/frames/val/', '')
save_name = save_name.replace('.jpg', '.pkl').replace('.jpeg', '')
save_path = os.path.join(out_dir, save_name)
common.makedirs(os.path.dirname(save_path))
save_in_tao_format(results[0], save_path)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
if not os.path.exists(cfg.work_dir):
os.makedirs(cfg.work_dir)
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
# 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)
# init 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}')
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
model = build_detector(
cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
train_dataset, dataset_dicts = get_dataset(cfg.data.train)
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__,
config=cfg.text,
CLASSES=train_dataset.CLASSES)
# add an attribute for visualization convenience
model.CLASSES = train_dataset.CLASSES
train_detector(
model,
train_dataset,
cfg,
distributed=distributed,
validate=args.validate,
dataset_dicts=dataset_dicts)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
# 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)
# update gpu num
if dist.is_initialized():
cfg.gpus = dist.get_world_size()
cfg.data.imgs_per_gpu = int(cfg.data.imgs_per_gpu * args.scale_bs)
cfg.data.workers_per_gpu = int(cfg.data.workers_per_gpu * args.scale_bs)
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer[
'lr'] * cfg.gpus / 8 * cfg.data.imgs_per_gpu / 2
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# log cfg
logger.info('training config:{}\n'.format(pprint.pformat(cfg._cfg_dict)))
# log git hash
logger.info('git hash: {}'.format(get_git_hash()))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
datasets.append(build_dataset(cfg.data.val))
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__,
config=cfg.text,
CLASSES=datasets[0].CLASSES,
git_hash=get_git_hash())
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
try:
logger.info(summary(model, cfg))
except RuntimeError:
logger.info('RuntimeError during summary')
logger.info(str(model))
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
train_detector(model,
datasets,
cfg,
distributed=distributed,
validate=args.validate,
logger=logger)
logger.info('git hash: {}'.format(get_git_hash()))
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.work_dir is not None:
if args.job_name is '':
args.job_name = 'output'
else:
args.job_name = time.strftime("%Y%m%d-%H%M%S-") + args.job_name
cfg.work_dir = osp.join(args.work_dir, args.job_name)
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
os.environ['MASTER_ADDR'] = 'localhost'
os.environ['MASTER_PORT'] = '%d' % args.port
init_dist(args.launcher, **cfg.dist_params)
# init logger before other steps
# logger = get_root_logger(cfg.log_level)
utils.create_work_dir(cfg.work_dir)
logger = utils.get_root_logger(cfg.work_dir, cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
logger.info('Retrain configs: \n' + str(cfg))
logger.info('Retrain args: \n' + str(args))
if cfg.checkpoint_config is not None:
# save mmdet version in checkpoints as meta data
cfg.checkpoint_config.meta = dict(mmdet_version=__version__,
config=cfg.text)
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
utils.set_data_path(args.data_path, cfg.data)
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
if not hasattr(model, 'neck'):
model.neck = None
logger.info('Backbone net config: \n' + cfg.model.backbone.net_config)
utils.get_network_madds(model.backbone, model.neck, model.bbox_head,
cfg.image_size_madds, logger)
if cfg.use_syncbn:
model = utils.convert_sync_batchnorm(model)
train_dataset = get_dataset(cfg.data.train)
train_detector(model,
train_dataset,
cfg,
distributed=distributed,
validate=args.validate,
logger=logger)
logger.info('Backbone net config: \n' + cfg.model.backbone.net_config)
utils.get_network_madds(model.backbone, model.neck, model.bbox_head,
cfg.image_size_madds, logger)
def main(): # noqa: C901
"""Start test."""
args = parse_args()
if args.work_dir is not None:
mmcv.mkdir_or_exist(args.work_dir)
if args.tmpdir is None:
args.tmpdir = osp.join(args.work_dir, 'tmp_dir')
mmcv.mkdir_or_exist(args.tmpdir)
if args.out is None:
args.out = osp.join(args.work_dir, 'result.pkl')
if args.checkpoint is None:
args.checkpoint = osp.join(args.work_dir, 'latest.pth')
fps_file = osp.join(args.work_dir, 'fps.pkl')
mAP_file = osp.join(args.work_dir, 'mAP.pkl')
else:
mAP_file, fps_file = None, None
if args.checkpoint is None:
raise ValueError('Checkpoint file cannot be empty.')
if args.config.endswith(".json"):
load_method = mmcv.load
mmcv.load = json_to_dict
cfg = mmcv.Config.fromfile(args.config)
mmcv.load = load_method
else:
cfg = mmcv.Config.fromfile(args.config)
cfg = mmcv.Config.fromfile(args.config)
cfg.model.pretrained = None
cfg.data.test.test_mode = True
if args.dist:
init_dist('pytorch', **cfg.dist_params)
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=True,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
load_checkpoint(model, args.checkpoint, map_location='cpu')
model.CLASSES = dataset.CLASSES
if args.dist:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
else:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, fps_file)
rank, _ = get_dist_info()
if args.out and rank == 0:
print('\nwriting results to {}'.format(args.out))
mmcv.dump(outputs, args.out)
eval_types = args.eval
if eval_types:
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
assert not isinstance(outputs[0], dict)
result_files = results2json(dataset, outputs, args.out)
coco_eval(result_files,
eval_types,
dataset.coco,
dump_file=mAP_file)
def main():
args = parse_args()
assert args.out or args.show or args.json_out, \
('Please specify at least one operation (save or show the results) '
'with the argument "--out" or "--show" or "--json_out"')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
if args.json_out is not None and args.json_out.endswith('.json'):
args.json_out = args.json_out[:-5]
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
# per_set_img_num = int(len(dataset.img_infos)/args.total_set_num)
# this_set_start = per_set_img_num*args.set
# if args.set < args.total_set_num-1:
# dataset.img_infos = dataset.img_infos[this_set_start: this_set_start+per_set_img_num]
# else:
# dataset.img_infos = dataset.img_infos[this_set_start:]
# dataset.img_infos = dataset.img_infos[:100]
data_loader = build_dataloader(dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
# print('load from {}'.format(args.checkpoint))
# checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
print('load model from {}'.format(cfg.load_from))
# checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
checkpoint = load_checkpoint(model, cfg.load_from, map_location='cpu')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
## load longtail classifier
# def load_ncm_ckpt(ncm_model):
# if not os.path.exists('./simple3fc.pth'):
# print('start training from 0 epoch')
# return 0
# else:
# epoch = torch.load('./simple3fc_epoch.pth')
# load_checkpoint(ncm_model, './simple3fc.pth')
# return epoch
# def load_ncm_ckpt(ncm_model):
# if not os.path.exists('./simple3fc.pth'):
# print('start training from 0 epoch')
# return 0
# else:
# epoch = torch.load('./finetune_simple3fc_epoch.pth')
# load_checkpoint(ncm_model, './finetune_simple3fc.pth')
# return epoch
def load_ncm_ckpt(ncm_model):
if not os.path.exists(
'./exp_randominit_negpossame_finetune_simple3fc_stage2_epoch.pth'
):
print('start training from 0 epoch')
return 0
else:
epoch = torch.load(
'./exp_randominit_negpossame_finetune_simple3fc_stage2_epoch.pth'
)
load_checkpoint(
ncm_model,
'exp_randominit_negpossame_finetune_simple3fc_stage2.pth')
return epoch
# def load_simple2fc_stage0_ckpt(ncm_model):
#
# epoch = torch.load('./finetune2fc_10epoch/exp_randominit_finetune_simple2fc_stage0_epoch.pth')
# load_checkpoint(ncm_model, './finetune2fc_10epoch/exp_randominit_finetune_simple2fc_stage0.pth')
# return epoch
#
# def load_simple2fc_stage1_ckpt(ncm_model):
#
# epoch = torch.load('./finetune2fc_10epoch/exp_randominit_finetune_simple2fc_stage1_epoch.pth')
# load_checkpoint(ncm_model, './finetune2fc_10epoch/exp_randominit_finetune_simple2fc_stage1.pth')
# return epoch
#
# def load_simple2fc_stage2_ckpt(ncm_model):
#
# epoch = torch.load('./finetune2fc_10epoch/exp_randominit_finetune_simple2fc_stage2_epoch.pth')
# load_checkpoint(ncm_model, './finetune2fc_10epoch/exp_randominit_finetune_simple2fc_stage2.pth')
# return epoch
#
#
# olongtail_model_stage0 = simple2fc().cuda()
# epoch = load_simple2fc_stage0_ckpt(olongtail_model_stage0)
# print('load model epoch {}'.format(epoch))
# olongtail_model_stage0.eval()
#
# olongtail_model_stage1 = simple2fc().cuda()
# epoch = load_simple2fc_stage1_ckpt(olongtail_model_stage1)
# olongtail_model_stage1.eval()
#
# olongtail_model_stage2 = simple2fc().cuda()
# epoch = load_simple2fc_stage2_ckpt(olongtail_model_stage2)
# olongtail_model_stage2.eval()
#
# olongtail_model_all_stage = [olongtail_model_stage0, olongtail_model_stage1, olongtail_model_stage2]
prefix = '3fc_ft'
def load_stage0_ckpt(ncm_model):
# epoch = torch.load('./work_dirs/htc/{}_stage0_epoch.pth'.format(prefix))
load_checkpoint(ncm_model,
'./work_dirs/htc/{}_stage0.pth'.format(prefix))
# return epoch
def load_stage1_ckpt(ncm_model):
# epoch = torch.load('./work_dirs/htc/{}_stage1_epoch.pth'.format(prefix))
load_checkpoint(ncm_model,
'./work_dirs/htc/{}_stage1.pth'.format(prefix))
# return epoch
def load_stage2_ckpt(ncm_model):
# epoch = torch.load('./work_dirs/htc/{}_stage2_epoch.pth'.format(prefix))
load_checkpoint(ncm_model,
'./work_dirs/htc/{}_stage2.pth'.format(prefix))
# return epoch
olongtail_model_stage0 = simple3fc().cuda()
epoch = load_stage0_ckpt(olongtail_model_stage0)
# print('load model epoch {}'.format(epoch))
olongtail_model_stage0.eval()
olongtail_model_stage1 = simple3fc().cuda()
epoch = load_stage1_ckpt(olongtail_model_stage1)
olongtail_model_stage1.eval()
olongtail_model_stage2 = simple3fc().cuda()
epoch = load_stage2_ckpt(olongtail_model_stage2)
olongtail_model_stage2.eval()
olongtail_model_all_stage = [
olongtail_model_stage0, olongtail_model_stage1, olongtail_model_stage2
]
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader,
olongtail_model_all_stage, args.show)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, olongtail_model_all_stage,
args.show, args.tmpdir)
# mmcv.dump(outputs, args.out)
rank, _ = get_dist_info()
if args.out and rank == 0:
print('\nwriting results to {}'.format(args.out))
# mmcv.dump(outputs, args.out)
eval_types = args.eval
if eval_types:
if eval_types == ['proposal_fast']:
result_file = args.out
lvis_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_files = results2json(dataset,
outputs,
args.out,
dump=False)
print('Starting evaluate {}'.format(
' and '.join(eval_types)))
lvis_eval(result_files, eval_types, dataset.lvis)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = args.out + '.{}'.format(name)
result_files = results2json(dataset, outputs_,
result_file)
lvis_eval(result_files, eval_types, dataset.coco)
# Save predictions in the COCO json format
if args.json_out and rank == 0:
if not isinstance(outputs[0], dict):
results2json(dataset, outputs, args.json_out)
else:
for name in outputs[0]:
outputs_ = [out[name] for out in outputs]
result_file = args.json_out + '.{}'.format(name)
results2json(dataset, outputs_, result_file)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# update configs according to CLI args
if args.resume_from is not None:
cfg.resume_from = args.resume_from
cfg.gpus = args.gpus
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * cfg.gpus / 8
# 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)
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info('Distributed training: {}'.format(distributed))
# set random seeds
if args.seed is not None:
logger.info('Set random seed to {}'.format(args.seed))
set_random_seed(args.seed)
datasets = [build_dataset(cfg.data.train)]
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
if cfg.load_from:
checkpoint = load_checkpoint(model, cfg.load_from, map_location='cpu')
model.CLASSES = datasets[0].CLASSES
if cfg.load_from:
checkpoint = load_checkpoint(model, cfg.load_from, map_location='cpu')
model.CLASSES = datasets[0].CLASSES
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__,
config=cfg.text,
CLASSES=datasets[0].CLASSES)
data_loader = build_dataloader(datasets[0],
imgs_per_gpu=cfg.data.imgs_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
num_gpus=cfg.gpus,
dist=False,
shuffle=False)
# put model on gpus
model = MMDataParallel(model, device_ids=range(cfg.gpus)).cuda()
model.train()
if hasattr(model, 'module'):
model_load = model.module
optimizer_all = obj_from_dict(cfg.optimizer, torch.optim,
dict(params=model_load.parameters()))
optimizer = obj_from_dict(cfg.optimizer, torch.optim,
dict(params=model_load.agg.parameters()))
check_video = None
start_epoch = 0
meta = None
epoch = start_epoch
vis = visdom.Visdom(env='fuse_c')
loss_cls_window = vis.line(X=torch.zeros((1, )).cpu(),
Y=torch.zeros((1)).cpu(),
opts=dict(xlabel='minibatches',
ylabel='Loss of classification',
title='Loss of classification ',
legend=['Loss of classification']))
loss_init_window = vis.line(X=torch.zeros((1, )).cpu(),
Y=torch.zeros((1)).cpu(),
opts=dict(xlabel='minibatches',
ylabel='Loss of init reppoint',
title='Loss of init reppoint',
legend=['Loss of init reppoint']))
loss_refine_window = vis.line(X=torch.zeros((1, )).cpu(),
Y=torch.zeros((1)).cpu(),
opts=dict(xlabel='minibatches',
ylabel='Loss of refine reppoint',
title='Loss of refine reppoint',
legend=['Loss of refine reppoint'
]))
loss_total_window = vis.line(X=torch.zeros((1, )).cpu(),
Y=torch.zeros((1)).cpu(),
opts=dict(xlabel='minibatches',
ylabel='Loss all',
title='Loss all',
legend=['Loss all']))
loss_trans_window = vis.line(X=torch.zeros((1, )).cpu(),
Y=torch.zeros((1)).cpu(),
opts=dict(xlabel='minibatches',
ylabel='Loss trans',
title='Loss trans',
legend=['Loss trans']))
training_sample = 0
for e in range(cfg.total_epochs):
i = 0
if epoch % 1 == 0:
if meta is None:
meta = dict(epoch=epoch + 1, iter=i)
else:
meta.update(epoch=epoch + 1, iter=i)
checkpoint = {
'meta': meta,
'state_dict': weights_to_cpu(model.state_dict())
}
print()
if optimizer_all is not None:
checkpoint['optimizer'] = optimizer_all.state_dict()
if not os.path.exists(cfg.work_dir):
os.mkdir(cfg.work_dir)
filename = os.path.join(cfg.work_dir, 'epoch_{}.pth'.format(epoch))
torch.save(checkpoint, filename)
for i, data in enumerate(data_loader):
# if len(data['gt_bboxes'].data[0][0]) == 0:
# continue
optimizer.zero_grad()
optimizer_all.zero_grad()
reference_id = (data['img_meta'].data[0][0]['filename'].split('/')
[-1]).split('.')[0]
video_id = data['img_meta'].data[0][0]['filename'].split('/')[-2]
print('start image:', data['img_meta'].data[0][0]['filename'])
print('end image:', data['img_meta'].data[-1][-1]['filename'])
# print(len(data['img'].data),len(data['img'].data[0]))
# exit()
for m in range(len(data['img_meta'].data)):
start_name = data['img_meta'].data[m][0]['filename'].split(
'/')[-2]
# print(data['img_meta'].data[m][0]['filename'])
for n in range(len(data['img_meta'].data[m])):
check_name = data['img_meta'].data[m][n]['filename'].split(
'/')[-2]
# print(data['img_meta'].data[m][n]['filename'])
if start_name != check_name:
print('end of video')
data['img_meta'].data[m][n] = data['img_meta'].data[m][
0]
data['gt_bboxes'].data[m][n] = data['gt_bboxes'].data[
m][0]
data['gt_labels'].data[m][n] = data['gt_labels'].data[
m][0]
data['img'].data[m][n] = data['img'].data[m][0]
# losses,loss_trans=model(return_loss=True, **data)
losses = model(return_loss=True, **data)
# print(losses)
if isinstance(losses, list):
loss_all = []
log = []
for p in range(len(losses)):
# print(p)
# print(losses[p])
loss, log_var = parse_losses(losses[p])
loss_all.append(loss)
log.append(log_var)
else:
losses, log_vars = parse_losses(losses)
if isinstance(losses, list):
losses = loss_all[0] + 0.5 * loss_all[1] + 0.5 * loss_all[
2] + 0.5 * loss_all[3]
losses = losses / 2.5
# print(loss_trans.shape)
# loss_trans=torch.mean(loss_trans)*0.1
# losses=losses+loss_trans
# if losses.item()>10:
# losses.backward(retain_graph=False)
# optimizer.zero_grad()
# continue
losses.backward()
if epoch < 10:
optimizer.step()
else:
optimizer_all.step()
# if training_sample<700:
# optimizer.step()
# else:
# optimizer_all.step()
# print('transform kernel check',model.module.agg.trans_kernel.sum().item())
log_vars = log[0]
vis.line(X=torch.ones(1).cpu() * training_sample,
Y=(log_vars['loss_cls']) * torch.ones(1).cpu(),
win=loss_cls_window,
update='append')
vis.line(X=torch.ones(1).cpu() * training_sample,
Y=(log_vars['loss_pts_init']) * torch.ones(1).cpu(),
win=loss_init_window,
update='append')
vis.line(X=torch.ones(1).cpu() * training_sample,
Y=(log_vars['loss_pts_refine']) * torch.ones(1).cpu(),
win=loss_refine_window,
update='append')
vis.line(X=torch.ones(1).cpu() * training_sample,
Y=(losses).item() * torch.ones(1).cpu(),
win=loss_total_window,
update='append')
# vis.line(
# X=torch.ones(1).cpu() * training_sample,
# Y=loss_trans.item() * torch.ones(1).cpu(),
# win=loss_trans_window,
# update='append')
print('agg')
print('epoch:',epoch,'index:',i,'video_id:',video_id,'reference_id:',reference_id, \
'loss_cls:',log_vars['loss_cls'],'loss_init_box:',log_vars['loss_pts_init'], \
'loss_refine_box:',log_vars['loss_pts_refine'])
log_vars = log[1]
print('refer')
print('epoch:',epoch,'index:',i,'video_id:',video_id,'reference_id:',reference_id, \
'loss_cls:',log_vars['loss_cls'],'loss_init_box:',log_vars['loss_pts_init'], \
'loss_refine_box:',log_vars['loss_pts_refine'])
log_vars = log[2]
print('support')
print('epoch:',epoch,'index:',i,'video_id:',video_id,'reference_id:',reference_id, \
'loss_cls:',log_vars['loss_cls'],'loss_init_box:',log_vars['loss_pts_init'], \
'loss_refine_box:',log_vars['loss_pts_refine'])
training_sample += 1
# if i % 300 == 0:
# if meta is None:
# meta = dict(epoch=epoch + 1, iter=i)
# else:
# meta.update(epoch=epoch + 1, iter=i)
# checkpoint = {
# 'meta': meta,
# 'state_dict': weights_to_cpu(model.state_dict())
# }
# if optimizer_all is not None:
# checkpoint['optimizer'] = optimizer_all.state_dict()
# if not os.path.exists(cfg.work_dir):
# os.mkdir(cfg.work_dir)
# filename=os.path.join(cfg.work_dir,'epoch_{}_{}.pth'.format(epoch,i))
# torch.save(checkpoint,filename)
epoch += 1
def main():
args = parse_args()
assert args.out or args.show or args.json_out, \
('Please specify at least one operation (save or show the results) '
'with the argument "--out" or "--show" or "--json_out"')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
if args.json_out is not None and args.json_out.endswith('.json'):
args.json_out = args.json_out[:-5]
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
# cfg.data.test.test_mode = False
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
## uncomment to only eval on first 100 imgs
per_set_img_num = int(len(dataset.img_infos) / args.total_set_num)
this_set_start = per_set_img_num * args.set
## comment to perform normal test
# dataset.img_infos = dataset.img_infos[:100]
dataset.img_infos = dataset.img_infos[this_set_start:this_set_start +
per_set_img_num]
data_loader = build_dataloader(dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
print('load model from {}'.format(cfg.load_from))
# checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
checkpoint = load_checkpoint(model, cfg.load_from, map_location='cpu')
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
## use retrained cls head
if hasattr(dataset, 'coco'):
if '2fc_rand' in args.cal_head:
calibrated_head = simple2fc(num_classes=81).cuda()
elif '3fc_rand' in args.cal_head or '3fc_ft' in args.cal_head:
calibrated_head = simple3fc(num_classes=81).cuda()
elif hasattr(dataset, 'lvis'):
if '2fc_rand' in args.cal_head:
calibrated_head = simple2fc(num_classes=1231).cuda()
elif '3fc_rand' in args.cal_head or '3fc_ft' in args.cal_head:
calibrated_head = simple3fc(num_classes=1231).cuda()
def load_ckpt(ncm_model, cal_head):
print('load cls head {}'.format('{}/{}.pth'.format(
cfg.work_dir, cal_head)))
epoch = torch.load('{}/{}_epoch.pth'.format(cfg.work_dir, cal_head))
load_checkpoint(ncm_model, '{}/{}.pth'.format(cfg.work_dir, cal_head))
return epoch
epoch = load_ckpt(calibrated_head, args.head_ckpt)
calibrated_head.eval()
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, calibrated_head,
build_dataset(cfg.data.train), args.show)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
mmcv.dump(outputs, args.out)
def main():
args = parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpuid
img_dir = args.img_dir
out_dir = args.out_dir
batch_size = args.batch_size
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# 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)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
file_list = common.load_filepaths(img_dir,
suffix=('.jpg', '.png', '.jpeg'),
recursive=True)
print(file_list[:10])
print('imgs: ', len(file_list))
#
print(file_list[0].replace(img_dir, ''))
dataset = FilesDataset(file_list, cfg.test_pipeline)
data_loader = build_dataloader(dataset,
imgs_per_gpu=batch_size,
workers_per_gpu=batch_size,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.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')
model = reweight_cls(model, args.tau)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, False, cfg)
else:
model = MMDistributedDataParallel(model.cuda())
outputs = multi_gpu_test(model, data_loader, args.tmpdir)
print(type(outputs))
print(len(outputs))
print(len(outputs[0]))
exit()
# save outputs
for file_path, mmdet_ret in zip(file_list, outputs):
save_name = file_path.replace(img_dir, '')
save_path = os.path.join(out_dir, save_name)
common.makedirs(os.path.dirname(save_path))
save_in_tao_format(mmdet_ret, save_path)
def set_configuration( self, cfg_in ):
cfg = self.get_configuration()
cfg.merge_config( cfg_in )
self._config_file = str( cfg.get_value( "config_file" ) )
self._seed_weights = str( cfg.get_value( "seed_weights" ) )
self._train_directory = str( cfg.get_value( "train_directory" ) )
self._output_directory = str( cfg.get_value( "output_directory" ) )
self._gpu_count = int( cfg.get_value( "gpu_count" ) )
self._integer_labels = strtobool( cfg.get_value( "integer_labels" ) )
self._launcher = str( cfg.get_value( "launcher" ) )
self._validate = strtobool( cfg.get_value( "validate" ) )
self._training_data = []
from mmcv import Config
self._cfg = Config.fromfile( self._config_file )
if self._cfg.get( 'cudnn_benchmark', False ):
torch.backends.cudnn.benchmark = True
if self._train_directory is not None:
self._cfg.work_dir = self._train_directory
self._groundtruth_store = os.path.join(
self._train_directory, self._tmp_annotation_file )
if not os.path.exists( self._train_directory ):
os.mkdir( self._train_directory )
else:
self._groundtruth_store = self._tmp_annotation_file
if self._seed_weights is not None:
self._cfg.resume_from = self._seed_weights
if self._gpu_count > 0:
self._cfg.gpus = self._gpu_count
else:
self._cfg.gpus = torch.cuda.device_count()
if self._cfg.checkpoint_config is not None:
from mmdet import __version__
self._cfg.checkpoint_config.meta = dict(
mmdet_version=__version__, config=self._cfg.text )
if self._launcher == 'none':
self._distributed = False
else:
self._distributed = True
from mmdet.apis import init_dist
init_dist( self._launcher, **self._cfg.dist_params )
from mmdet.apis import get_root_logger
self._logger = get_root_logger( self._cfg.log_level )
self._logger.info( 'Distributed training: {}'.format( self._distributed ) )
if self._random_seed is not "none":
logger.info( 'Set random seed to {}'.format( self._random_seed ) )
from mmdet.apis import set_random_seed
set_random_seed( int( self._random_seed ) )
from mmdet.models import build_detector
self._model = build_detector(
self._cfg.model, train_cfg=self._cfg.train_cfg, test_cfg=self._cfg.test_cfg )