def main():
parser = ArgumentParser(description='COCO Evaluation')
parser.add_argument('result', help='result file path')
parser.add_argument('--ann', help='annotation file path')
parser.add_argument(
'--types',
type=str,
nargs='+',
choices=['proposal_fast', 'proposal', 'bbox', 'segm', 'keypoint'],
default=['bbox'],
help='result types')
parser.add_argument(
'--max-dets',
type=int,
nargs='+',
default=[100, 300, 1000],
help='proposal numbers, only used for recall evaluation')
parser.add_argument('--LRPEval',
type=int,
default=1,
help='Whether or not to provide oLRP results')
parser.add_argument('--LRPtau',
type=float,
default=0.5,
help='True Positive Validation Threshold for LRP')
args = parser.parse_args()
coco_eval(args.result, args.types, args.ann, args.max_dets, args.LRPEval,
args.LRPtau)
def main():
parser = ArgumentParser(description='COCO Evaluation')
parser.add_argument('result', help='result file path')
parser.add_argument('--ann', help='annotation file path')
parser.add_argument('--in_detail',
type=int,
default=0,
help='whether or not use detail evaluation')
parser.add_argument(
'--types',
type=str,
nargs='+',
choices=['proposal_fast', 'proposal', 'bbox', 'segm', 'keypoint'],
default=['bbox'],
help='result types')
parser.add_argument(
'--max-dets',
type=int,
nargs='+',
default=[100, 300, 1000],
help='proposal numbers, only used for recall evaluation')
args = parser.parse_args()
results = {m: args.result for m in args.types}
coco_eval(results, args.types, args.ann, args.max_dets, args.in_detail)
def main():
parser = ArgumentParser(description='COCO Evaluation')
parser.add_argument(
'--result',
default=
"/data/liphone/detcomp/mmdet-v2/tile/baseline_cut_1000x1000/data_mode=test+.bbox.json",
help='result file path')
parser.add_argument(
'--ann',
default=
"/home/lifeng/undone-work/dataset/detection/tile/annotations/cut_1000x1000/cut_1000x1000_test.json",
help='annotation file path')
parser.add_argument(
'--types',
type=str,
nargs='+',
choices=['proposal_fast', 'proposal', 'bbox', 'segm', 'keypoint'],
default=['bbox'],
help='result types')
parser.add_argument(
'--max-dets',
type=int,
nargs='+',
default=[100, 300, 1000],
help='proposal numbers, only used for recall evaluation')
parser.add_argument('--classwise',
default=True,
action='store_true',
help='whether eval class wise ap')
args = parser.parse_args()
coco_eval(args.result, args.types, args.ann, args.max_dets, args.classwise)
def main():
parser = ArgumentParser(description='COCO Evaluation')
parser.add_argument('result', help='result file path')
parser.add_argument('--ann', help='annotation file path')
parser.add_argument(
'--types',
type=str,
nargs='+',
choices=['proposal_fast', 'proposal', 'bbox', 'segm', 'keypoint'],
default=['bbox'],
help='result types')
parser.add_argument(
'--max-dets',
type=int,
nargs='+',
default=[100, 300, 1000],
help='proposal numbers, only used for recall evaluation')
parser.add_argument('--classwise',
action='store_true',
help='whether eval class wise ap')
parser.add_argument('--gzsi',
action='store_true',
help='whether eval class with gzsd setting')
parser.add_argument('--num-seen-classes', type=int, default=48)
args = parser.parse_args()
coco_eval(args.result, args.types, args.ann, args.max_dets, args.classwise,
args.gzsi, args.num_seen_classes)
def main():
parser = ArgumentParser(description="COCO Evaluation")
parser.add_argument("result", help="result file path")
parser.add_argument("--ann", help="annotation file path")
parser.add_argument(
"--types",
type=str,
nargs="+",
choices=[
"proposal_fast",
"proposal",
"bbox",
"segm",
"keypoint",
],
default=["bbox"],
help="result types",
)
parser.add_argument(
"--max-dets",
type=int,
nargs="+",
default=[100, 300, 1000],
help="proposal numbers, only used for recall evaluation",
)
args = parser.parse_args()
coco_eval(args.result, args.types, args.ann, args.max_dets)
def main():
parser = ArgumentParser(description='COCO Evaluation')
parser.add_argument('result', help='result file path')
parser.add_argument(
'--ann',
help='annotation file path',
default=
'/media/gzzn/Data/Datasets/ObjectDetection/COCO/annotations/instances_val2017.json'
)
parser.add_argument(
'--types',
type=str,
nargs='+',
choices=['proposal_fast', 'proposal', 'bbox', 'segm', 'keypoint'],
default=['bbox'],
help='result types')
parser.add_argument(
'--max-dets',
type=int,
nargs='+',
default=[100, 300, 1000],
help='proposal numbers, only used for recall evaluation')
parser.add_argument('--class_wise',
action='store_true',
help='whether eval class wise ap')
args = parser.parse_args()
coco_eval(args.result, args.types, args.ann, args.max_dets,
args.class_wise)
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)
cfg.model.pretrained = None
cfg.data.test.test_mode = True
dataset = obj_from_dict(cfg.data.test, datasets, dict(test_mode=True))
if args.gpus == 1:
model = build_detector(cfg.model,
train_cfg=None,
test_cfg=cfg.test_cfg)
load_checkpoint(model, args.checkpoint)
model = MMDataParallel(model, device_ids=[0])
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
num_gpus=1,
dist=False,
shuffle=False)
outputs = single_test(model, data_loader, args.show)
else:
model_args = cfg.model.copy()
model_args.update(train_cfg=None, test_cfg=cfg.test_cfg)
model_type = getattr(detectors, model_args.pop('type'))
outputs = parallel_test(model_type,
model_args,
args.checkpoint,
dataset,
_data_func,
range(args.gpus),
workers_per_gpu=args.proc_per_gpu)
if args.out:
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
else:
result_file = args.out + '.json'
results2json(dataset, outputs, result_file)
coco_eval(result_file, eval_types, dataset.coco)
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)
cfg.model.pretrained = None
dataset = utils.get_dataset(cfg.data.val)
class_names = cfg.data.val.class_names
if args.gpus == 1:
model = build_detector(cfg.model,
train_cfg=None,
test_cfg=cfg.test_cfg)
load_checkpoint(model, args.checkpoint)
model = MMDataParallel(model, device_ids=[0])
data_loader = build_dataloader(
dataset,
1,
cfg.data.workers_per_gpu,
num_gpus=1,
#collate_fn= cfg.data.collate_fn,
shuffle=False,
dist=False)
outputs = single_test(model, data_loader, args.out, class_names)
else:
NotImplementedError
# kitti evaluation
gt_annos = kitti.get_label_annos(dataset.label_prefix, dataset.sample_ids)
result = get_official_eval_result(gt_annos,
outputs,
current_classes=class_names)
print(result)
if args.out:
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('\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()
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.input.split('/')[:-1])
if not os.path.exists(root_Path):
os.makedirs(root_Path)
#mmcv.dump(outputs, args.out)
outputs = mmcv.load(args.input)
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 start_testing(self):
if not self.distributed:
self.model = MMDataParallel(self.model, device_ids=[0])
outputs = self.__single_gpu_test()
else:
self.model = MMDistributedDataParallel(self.model.cuda())
outputs = self.__multi_gpu_test()
dir_name = os.path.dirname(self.out_pkl)
if not os.path.exists(dir_name):
os.makedirs(dir_name)
rank, _ = get_dist_info()
if self.out_pkl and rank == 0:
print('\nwriting results to {}'.format(self.out_pkl))
mmcv.dump(outputs, self.out_pkl)
eval_types = self.eval_types
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = self.out_pkl
coco_eval(result_file, eval_types, self.dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_files = results2json(self.dataset, outputs,
self.out_pkl)
coco_eval(result_files, eval_types, self.dataset.coco)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = self.out_pkl + '.{}'.format(name)
result_files = results2json(
self.dataset, outputs_, result_file)
coco_eval(result_files, eval_types,
self.dataset.coco)
# Save predictions in the COCO json format
if self.out_json and rank == 0:
if not isinstance(outputs[0], dict):
results2json(self.dataset, outputs, self.out_json)
else:
for name in outputs[0]:
outputs_ = [out[name] for out in outputs]
result_file = self.out_json + '.{}'.format(name)
results2json(self.dataset, outputs_, result_file)
def main():
args = parse_args()
cfg = mmcv.Config.fromfile(args.config)
if args.saved_preds is None:
outputs = get_outputs(args)
else:
outputs = mmcv.load(args.saved_preds)
dataset = build_dataset(cfg.data.test)
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)
# 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()
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 = get_dataset(cfg.data.test)
outputs = mmcv.load(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 = 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)
prefix = './mrcnn_r50_dual'
# 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))
set_combine = set0 + set1 + set2 + set3 + set4 + set5 + set6 + set7
print('start eval')
if hasattr(dataset, 'coco'):
result_files = results2json(dataset, set_combine, args.out, dump=False)
coco_eval(result_files, args.eval, dataset.coco)
elif hasattr(dataset, 'lvis'):
result_files = results2json(dataset, set_combine, args.out, dump=False)
lvis_eval(result_files, args.eval, dataset.lvis)
def main():
args = parse_args()
search_cfg = mmcv_config.fromfile(args.fb_cfg)
_space = search_cfg.search_space
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)
cfg = mmcv.Config.fromfile(args.model_cfg)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# cfg.model.pretrained = None
cfg.data.test.test_mode = True
dataset = obj_from_dict(cfg.data.test, datasets, dict(test_mode=True))
if args.gpus == 1:
model = detection(mmcv_config(cfg['model_cfg']),
mmcv_config(cfg['train_cfg']),
mmcv_config(cfg['test_cfg']), _space, args.theta_txt)
# model = build_detector(
# cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
load_checkpoint(model, args.checkpoint)
model = MMDataParallel(model, device_ids=[0])
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
num_gpus=1,
dist=False,
shuffle=False)
outputs = single_test(model, data_loader, args.show)
else:
model_args = cfg.model.copy()
model_args.update(train_cfg=None, test_cfg=cfg.test_cfg)
model_type = getattr(detectors, model_args.pop('type'))
outputs = parallel_test(model_type,
model_args,
args.checkpoint,
dataset,
_data_func,
range(args.gpus),
workers_per_gpu=args.proc_per_gpu)
if args.out:
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('\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()
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
dataset = obj_from_dict(
cfg.data.test, datasets, dict(test_mode=True)
)
if args.gpus == 1:
model = build_detector(
cfg.model, train_cfg=None, test_cfg=cfg.test_cfg
)
load_checkpoint(model, args.checkpoint)
model = MMDataParallel(model, device_ids=[0])
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
num_gpus=1,
dist=False,
shuffle=False,
)
outputs = single_test(model, data_loader, args.show)
else:
model_args = cfg.model.copy()
model_args.update(train_cfg=None, test_cfg=cfg.test_cfg)
model_type = getattr(detectors, model_args.pop("type"))
outputs = parallel_test(
model_type,
model_args,
args.checkpoint,
dataset,
_data_func,
range(args.gpus),
workers_per_gpu=args.proc_per_gpu,
)
if args.out:
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("\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()
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
for t in cfg.data.test:
t.test_mode = True
cfg.out_path = args.out.split('.pkl')[0] if args.out else None
# 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 model and load checkpoint
model = build_detector(
cfg.model, train_cfg=None, test_cfg=cfg.test_cfg, global_cfg=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
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
if not type(cfg.data.test) == list:
cfg.data.test = [cfg.data.test]
if not distributed:
model = MMDataParallel(model, device_ids=[0])
else:
model = MMDistributedDataParallel(model.cuda())
outputs = dict()
for c in cfg.data.test:
dataset = build_dataset(c)
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
if not distributed:
results = single_gpu_test(model, data_loader, args.out, args.show)
if results is not None:
outputs.update(results)
else:
outputs.update(multi_gpu_test(model, data_loader, args.tmpdir))
rank, _ = get_dist_info()
if len(outputs.keys()) > 0 and args.out and rank == 0:
print('\nwriting results to {}'.format(args.out))
if not (args.out.endswith('.pkl') or args.out.endswith('.json')):
args.out += '.pkl'
if 'track_results' in outputs.keys():
mmcv.dump(outputs['track_results'], args.out)
else:
mmcv.dump(outputs, args.out)
if 'bbox_results' in outputs.keys():
result_files = results2json(dataset, outputs['bbox_results'], args.out)
coco_eval(result_files, ['bbox', 'segm'], cfg.data.test[0].ann_file)
if 'segm_results' in outputs.keys():
result_files = results2json(dataset, [(b, s) for b, s in zip(outputs['bbox_results'], outputs['segm_results'])], args.out)
coco_eval(result_files, ['segm'], cfg.data.test[0].ann_file)
# if 'new_bbox_results' in outputs.keys():
# # For tracking
# result_files = results2json(dataset, outputs['new_bbox_results'],
# args.out)
# coco_eval(result_files, ['bbox'], cfg.data.test[0].ann_file)
if 'track_results' in outputs.keys():
print("Evaluating box tracking...")
mdat_eval(outputs['track_results'], dataset, args.out, cfg)
if 'segm_track_results' in outputs.keys():
print("Evaluating segmentation tracking...")
mdat_eval(outputs['segm_track_results'], dataset, args.out, cfg, with_mask=True)
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
if args.ann_file is not None:
cfg.data.test.ann_file = args.ann_file
if args.img_prefix is not None:
cfg.data.test.img_prefix = args.img_prefix
if args.flip:
cfg.data.test.flip_ratio = 1
# 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 = get_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)
load_checkpoint(model, args.checkpoint, map_location='cpu')
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_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()
if os.path.isdir(args.checkpoint):
print(args.checkpoint)
checkpoints = glob.glob(args.checkpoint + '/epoch_*.pth')
checkpoints = sorted(
checkpoints,
key=lambda x: int(x.split('epoch_')[-1].split('.')[0]))
print(checkpoints)
if args.out is not None:
if not os.path.exists(args.out):
os.mkdir(args.out)
elif os.path.isfile(args.out):
raise ValueError('args.out must be a directory.')
# Create TensorBoard writer for output checkpoint dir.
tensorboard_writer = SummaryWriter(args.out)
else:
checkpoints = [args.checkpoint]
tensorboard_writer = None
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
dataset = obj_from_dict(cfg.data.test, datasets, dict(test_mode=True))
for i, checkpoint in enumerate(checkpoints):
outpath = args.out
if os.path.isdir(args.checkpoint):
outpath = args.out + '/%d_out.pkl' % i
if not os.path.exists(outpath):
if args.gpus == 1:
model = build_detector(cfg.model,
train_cfg=None,
test_cfg=cfg.test_cfg)
load_checkpoint(model, checkpoint)
model = MMDataParallel(model, device_ids=[0])
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
num_gpus=1,
dist=False,
shuffle=False)
outputs = single_test(model, data_loader, args.show)
else:
model_args = cfg.model.copy()
model_args.update(train_cfg=None, test_cfg=cfg.test_cfg)
model_type = getattr(detectors, model_args.pop('type'))
outputs = parallel_test(model_type,
model_args,
checkpoint,
dataset,
_data_func,
range(args.gpus),
workers_per_gpu=args.proc_per_gpu)
# TODO: Currently assume test set is same size as training set.
num_iters = (i + 1) * len(dataset)
if outpath:
if os.path.exists(outpath):
print('reading results from {}'.format(outpath))
outputs = mmcv.load(outpath)
else:
print('writing results to {}'.format(outpath))
mmcv.dump(outputs, outpath)
eval_types = args.eval
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = outpath
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_file = outpath + '.json'
results2json(dataset, outputs, result_file)
results_dict = coco_eval(result_file, eval_types,
dataset.coco)
if tensorboard_writer:
for eval_type in eval_types:
out = capture_stdout(lambda: results_dict[
eval_type].summarize())
for line in out.split('\n')[:-1]:
parts = line.split('=')
name, score = '='.join(parts[:-1]), float(
parts[-1])
tensorboard_writer.add_scalar(
'eval/' + name, score, num_iters)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = outpath + '.{}.json'.format(name)
results2json(dataset, outputs_, result_file)
results_dict = coco_eval(result_file, eval_types,
dataset.coco)
if tensorboard_writer:
for eval_type in eval_types:
out = capture_stdout(lambda: results_dict[
eval_type].summarize())
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
# VOCDataset(ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
# img_prefix=data_root + 'VOC2007/',
# img_scale=(300, 300),
# img_norm_cfg=img_norm_cfg,
# size_divisor=None,
# flip_ratio=0,
# with_mask=False,
# with_label=False,
# test_mode=True,
# resize_keep_ratio=False)
dataset = obj_from_dict(cfg.data.test, datasets, dict(test_mode=True))
if args.gpus == 1:
# build(cfg, DETECTORS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
# SingleStageDetector(pretrained=..., backbone=..., neck=..., bbox_head=...,
# train_cfg=None, test_cfg=...)
# 首先要先注册 BACKBONES、 NECKS、 ROI_EXTRACTORS、 HEADS、 DETECTORS、
# 然后 BACKBONES.register_module（class SSDVGG） @HEADS.register_module(class AnchorHead)
# @HEADS.register_module(class SSDHead) @DETECTORS.register_module(class SingleStageDetector)
# 最后 build_detector() 相当于SingleStageDetector(**args)
model = build_detector(cfg.model,
train_cfg=None,
test_cfg=cfg.test_cfg)
load_checkpoint(model, args.checkpoint)
model = MMDataParallel(model, device_ids=[0])
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
num_gpus=1,
dist=False,
shuffle=False)
outputs = single_test(model, data_loader, args.show)
else:
model_args = cfg.model.copy()
model_args.update(train_cfg=None, test_cfg=cfg.test_cfg)
model_type = getattr(detectors, model_args.pop('type'))
outputs = parallel_test(model_type,
model_args,
args.checkpoint,
dataset,
_data_func,
range(args.gpus),
workers_per_gpu=args.proc_per_gpu)
if args.out:
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('\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():
# import os
# os.environ['CUDA_VISIBLE_DEVICES'] = '2'
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.')
global work_dirs
work_dirs = os.path.dirname(args.checkpoint)
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':
import torch.distributed as dist
dist.init_process_group('gloo',
init_method='file:///tmp/somefile',
rank=0,
world_size=1)
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 = get_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)
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:
# pass
model = MMDataParallel(model, device_ids=[0])
# model = MMDataParallel(model, device_ids=[3])
outputs = single_gpu_test(model, data_loader, args.show, args.log_dir)
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)
# import pickle
# F=open(r'/disk2/zzr/work_dirs/PANet_r50_isaid/epoch_12_test_on_val_opencv_remap_maxdets_1000.pkl','rb')
# outputs = pickle.load(F)
outputs = tran2obb_results(outputs)
# outputs = tran2mix_results(outputs)
# outputs = trans2ms_results(outputs)
# outputs = trans2mix_results(outputs)
# outputs = trans2mask_results(outputs)
# outputs = trans2hbb_results(outputs)
# outputs = trans2mask_score(outputs)
# outputs = trans2mask_results_V2(outputs)
# outputs = assembel_mask(outputs)
# outputs = assembel_mask_V2(outputs)
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('\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()
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)
imgs_per_gpu = cfg.data.test.pop('imgs_per_gpu', 1)
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = get_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
imgs_per_gpu=imgs_per_gpu,
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)
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, args.log_dir)
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 args.csv:
csv_path = (args.out).replace('.pkl', '.csv')
print('\nwriting results as csv to {}'.format(csv_path))
convert_output_to_csv(dataset, outputs, csv_path)
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('\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)
import mmcv
from mmdet.core import coco_eval, results2json
from mmdet.datasets import build_dataset
import os
os.chdir('..') # change dir to mmdetection root
# eval_types = ['bbox']
# eval_types = ['proposal']
eval_types = ['proposal', 'bbox']
config = 'configs/faster_rcnn_r50_fpn_1x_train.py'
result_files = 'checkpoints'
# result_files = 'results/2019-09-15_train/eval_epoch2.pkl.bbox.json'
result_files = 'results/2019-09-15_train/eval_epoch8.pkl.bbox.json'
# outputs = mmcv.load(result_files)[0]
cfg = mmcv.Config.fromfile(config)
dataset = build_dataset(cfg.data.test)
# result_files = results2json(dataset, outputs, args.out)
coco_eval(result_files, eval_types, dataset.coco)
print('Done!')
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 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)
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)
while not osp.isfile(args.checkpoint):
print('Waiting for {} to exist...'.format(args.checkpoint))
time.sleep(60)
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
# assert not distributed
if not distributed:
model = MMDataParallel(model, device_ids=[0])
# data_loader.dataset.img_infos = data_loader.dataset.img_infos[:10]
outputs = single_gpu_test(model, data_loader)
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):
if dataset.ann_file == 'data/coco/annotations/image_info_test-dev2017.json':
result_files = results2json_segm(dataset,
outputs,
args.out,
dump=True)
else:
result_files = results2json_segm(dataset,
outputs,
args.out,
dump=False)
if 'lvis' in dataset.ann_file: ## an ugly fix to make it compatible with coco eval
from lvis import LVISEval
lvisEval = LVISEval(cfg.data.test.ann_file,
result_files, 'segm')
lvisEval.run()
lvisEval.print_results()
#fix lvis api eval iou_thr error, should be 0.9 but was 0.8999
lvisEval.params.iou_thrs[8] = 0.9
for iou in [0.5, 0.6, 0.7, 0.8, 0.9]:
print('AP at iou {}: {}'.format(
iou, lvisEval._summarize('ap', iou_thr=iou)))
else:
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,
dump=False)
coco_eval(result_files, eval_types, dataset.coco)
##eval on lvis-77######
cfg.data.test.ann_file = 'data/lvis/lvis_v0.5_val_cocofied.json'
cfg.data.test.img_prefix = 'data/lvis/val2017/'
cfg.data.test.test_mode = True
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# model_orig=model.module
# model = MMDataParallel(model, device_ids=[0]).cuda()
# data_loader.dataset.img_infos = data_loader.dataset.img_infos[:10]
outputs = single_gpu_test(model, data_loader)
print('\nwriting results to {}'.format('xxx'))
# mmcv.dump(outputs, 'xxx')
eval_types = ['segm']
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = 'xxx'
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_files = results2json_segm(dataset,
outputs,
'xxx',
dump=False)
from lvis import LVISEval
lvisEval = LVISEval(
'data/lvis/lvis_v0.5_val_cocofied.json', result_files,
'segm')
lvisEval.run()
lvisEval.print_results()
# fix lvis api eval iou_thr error, should be 0.9 but was 0.8999
lvisEval.params.iou_thrs[8] = 0.9
for iou in [0.5, 0.6, 0.7, 0.8, 0.9]:
print('AP at iou {}: {}'.format(
iou, lvisEval._summarize('ap', iou_thr=iou)))
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = 'xxx' + '.{}'.format(name)
result_files = results2json(dataset,
outputs_,
result_file,
dump=False)
coco_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 _non_dist_train(model,
dataset,
cfg,
validate=False,
logger=None,
timestamp=None):
if validate:
raise NotImplementedError('Built-in validation is not implemented '
'yet in not-distributed training. Use '
'distributed training or test.py and '
'*eval.py scripts instead.')
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
data_loaders = [
build_dataloader(
ds,
cfg.data.imgs_per_gpu,
cfg.data.workers_per_gpu,
cfg.gpus,
dist=False) for ds in dataset
]
# put model on gpus
model = MMDataParallel(model, device_ids=range(cfg.gpus)).cuda()
# # if model.module.bbox_head.freeze_solov2_and_train_combonly:
# if model.module.bbox_head.optimize_list is not None:
# for (key, param) in model.named_parameters():
# # if 'kernel_convs_convcomb' not in key and 'context_fusion_convs' not in key and 'learned_weight' not in key:
# if not any(s in key for s in model.module.bbox_head.optimize_list):
# param.requires_grad=False
# else:
# # print('optimize {}'.format(key))
# logger.info('optimize {}'.format(key))
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
runner = Runner(
model, batch_processor, optimizer, cfg.work_dir, logger=logger)
# an ugly walkaround to make the .log and .log.json filenames the same
runner.timestamp = timestamp
# fp16 setting
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
optimizer_config = Fp16OptimizerHook(
**cfg.optimizer_config, **fp16_cfg, distributed=False)
else:
optimizer_config = cfg.optimizer_config
runner.register_training_hooks(cfg.lr_config, optimizer_config,
cfg.checkpoint_config, cfg.log_config)
if cfg.resume_from:
runner.resume(cfg.resume_from)
elif cfg.load_from:
runner.load_checkpoint(cfg.load_from)
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
## add test after training
if cfg.data.test.ann_file != 'data/lvis/lvis_v0.5_val_lvis_freqset.json': # if val set is lvis freq, only eval on lvis-freq val set
cfg.data.test.test_mode = True
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
model_orig=model.module
model = MMDataParallel(model, device_ids=[0]).cuda()
data_loader.dataset.img_infos = data_loader.dataset.img_infos[:100]
outputs = single_gpu_test(model, data_loader)
print('\nwriting results to {}'.format('xxx'))
# mmcv.dump(outputs, 'xxx')
eval_types = ['segm']
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = 'xxx'
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_files = results2json_segm(dataset, outputs, 'xxx', dump=False)
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 = 'xxx' + '.{}'.format(name)
result_files = results2json(dataset, outputs_,
result_file, dump=False)
coco_eval(result_files, eval_types, dataset.coco)
##eval on lvis-77######
cfg.data.test.ann_file = 'data/lvis/lvis_v0.5_val_cocofied.json'
cfg.data.test.img_prefix = 'data/lvis/val2017/'
cfg.data.test.test_mode = True
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# model_orig=model.module
# model = MMDataParallel(model, device_ids=[0]).cuda()
data_loader.dataset.img_infos = data_loader.dataset.img_infos[:100]
outputs = single_gpu_test(model, data_loader)
print('\nwriting results to {}'.format('xxx'))
# mmcv.dump(outputs, 'xxx')
eval_types = ['segm']
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = 'xxx'
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_files = results2json_segm(dataset, outputs, 'xxx', dump=False)
from lvis import LVISEval
lvisEval = LVISEval('data/lvis/lvis_v0.5_val_cocofied.json', result_files, 'segm')
lvisEval.run()
lvisEval.print_results()
# fix lvis api eval iou_thr error, should be 0.9 but was 0.8999
lvisEval.params.iou_thrs[8] = 0.9
for iou in [0.5, 0.6, 0.7, 0.8, 0.9]:
print('AP at iou {}: {}'.format(iou, lvisEval._summarize('ap', iou_thr=iou)))
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = 'xxx' + '.{}'.format(name)
result_files = results2json(dataset, outputs_,
result_file, dump=False)
coco_eval(result_files, eval_types, dataset.coco)
else:
##eval on lvis-freq######
cfg.data.test.test_mode = True
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# model_orig=model.module
# model = MMDataParallel(model, device_ids=[0]).cuda()
data_loader.dataset.img_infos = data_loader.dataset.img_infos[:100]
outputs = single_gpu_test(model, data_loader)
print('\nwriting results to {}'.format('xxx'))
# mmcv.dump(outputs, 'xxx')
eval_types = ['segm']
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = 'xxx'
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_files = results2json_segm(dataset, outputs, 'xxx', dump=False)
from lvis import LVISEval
lvisEval = LVISEval(cfg.data.test.ann_file, result_files, 'segm')
lvisEval.run()
lvisEval.print_results()
# fix lvis api eval iou_thr error, should be 0.9 but was 0.8999
lvisEval.params.iou_thrs[8] = 0.9
for iou in [0.5, 0.6, 0.7, 0.8, 0.9]:
print('AP at iou {}: {}'.format(iou, lvisEval._summarize('ap', iou_thr=iou)))
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = 'xxx' + '.{}'.format(name)
result_files = results2json(dataset, outputs_,
result_file, dump=False)
coco_eval(result_files, eval_types, dataset.coco)
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(args):
if args.model.endswith('.onnx'):
backend = 'onnx'
elif args.model.endswith('.xml'):
backend = 'openvino'
else:
raise ValueError('Unknown model type.')
cfg = mmcv.Config.fromfile(args.config)
cfg.model.pretrained = None
cfg.data.test.test_mode = True
if backend == 'openvino':
assert cfg.data.test.pipeline[1]['type'] == 'MultiScaleFlipAug'
normalize_idx = [i for i, v in enumerate(cfg.data.test.pipeline[1]['transforms']) if v['type'] == 'Normalize'][0]
cfg.data.test.pipeline[1]['transforms'][normalize_idx]['mean'] = [0.0, 0.0, 0.0]
cfg.data.test.pipeline[1]['transforms'][normalize_idx]['std'] = [1.0, 1.0, 1.0]
cfg.data.test.pipeline[1]['transforms'][normalize_idx]['to_rgb'] = False
print(cfg.data.test)
if args.video is not None and args.show:
dataset = VideoDataset(int(args.video), cfg.data)
data_loader = iter(dataset)
wait_key = 1
else:
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
wait_key = -1
# Valid classes + background.
classes_num = len(dataset.CLASSES) + 1
if backend == 'openvino':
from mmdet.utils.deployment import DetectorOpenVINO
model = DetectorOpenVINO(args.model,
args.model[:-3] + 'bin',
mapping_file_path=args.model[:-3] + 'mapping',
cfg=cfg,
classes=dataset.CLASSES)
else:
from mmdet.utils.deployment import ModelONNXRuntime
model = ModelONNXRuntime(args.model, cfg=cfg, classes=dataset.CLASSES)
results = []
prog_bar = mmcv.ProgressBar(len(dataset))
for i, data in enumerate(data_loader):
im_data = data['img'][0].cpu().numpy()
try:
result = model(im_data)
result = postprocess(
result,
data['img_meta'][0].data[0],
num_classes=classes_num,
rescale=not args.show)
except Exception as ex:
print('\nException raised while processing item {}:'.format(i))
print(ex)
result = empty_result(
num_classes=classes_num,
with_mask=model.pt_model.with_mask)
results.append(result)
if args.show:
model.show(data, result, score_thr=args.score_thr, wait_time=wait_key)
batch_size = data['img'][0].size(0)
for _ in range(batch_size):
prog_bar.update()
print('')
print('Writing results to {}'.format(args.out))
mmcv.dump(results, 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(results[0], dict):
result_files = results2json(dataset, results, args.out)
coco_eval(result_files, eval_types, dataset.coco)
else:
for name in results[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in results]
result_file = args.out + '.{}'.format(name)
result_files = results2json(dataset, outputs_,
result_file)
coco_eval(result_files, eval_types, dataset.coco)
# Save predictions in the COCO json format
if args.json_out:
if not isinstance(results[0], dict):
results2json(dataset, results, args.json_out)
else:
for name in results[0]:
outputs_ = [out[name] for out in results]
result_file = args.json_out + '.{}'.format(name)
results2json(dataset, outputs_, result_file)
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
dataset = obj_from_dict(cfg.data.test, datasets, dict(test_mode=True))
if args.gpus == 1:
model = build_detector(
cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
load_checkpoint(model, args.checkpoint)
model = MMDataParallel(model, device_ids=[0])
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
num_gpus=1,
dist=False,
shuffle=False)
outputs = single_test(model, data_loader, args.show)
else:
model_args = cfg.model.copy()
model_args.update(train_cfg=None, test_cfg=cfg.test_cfg)
model_type = getattr(detectors, model_args.pop('type'))
outputs = parallel_test(
model_type,
model_args,
args.checkpoint,
dataset,
_data_func,
range(args.gpus),
workers_per_gpu=args.proc_per_gpu)
# run evaluation
import zipfile
from mmdet.core.evaluation.icdar_evaluation import icdar_eval
import os
pt_zip_dir = os.path.join('../output', 'pt.zip')
output_pt_dir = os.path.join('../output', 'pt/')
z = zipfile.ZipFile(pt_zip_dir, 'w', zipfile.ZIP_DEFLATED)
for dirpath, dirnames, filenames in os.walk(output_pt_dir):
for filename in filenames:
z.write(os.path.join(dirpath, filename), filename)
z.close()
#3 use icdar eval
if args.dataset=='icdar2015':
gt_zip_dir = './work_dirs/gt_ic15.zip'
elif args.dataset=='icdar2013':
gt_zip_dir = './work_dirs/gt_ic13.zip'
elif args.dataset=='td500':
gt_zip_dir = './work_dirs/gt_td500.zip'
param_dict = dict(
# gt zip file path
g = gt_zip_dir,
# prediction zip file path
s = pt_zip_dir,
)
result_dict = icdar_eval(param_dict)
print(result_dict)
for i in range(6):
print('')
if args.out:
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('\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 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]
# print('args.config:',args.config) #config file로 가야 됨()
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)
# 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 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)
