import argparse
import os
import warnings
import mmcv
import torch
from mmcv import Config, DictAction
from mmcv.cnn import fuse_conv_bn
from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from mmcv.runner import (get_dist_info, init_dist, load_checkpoint,
wrap_fp16_model)
from mmdet.apis import multi_gpu_test
from mmocr.apis.test import single_gpu_test
from mmocr.apis.utils import (disable_text_recog_aug_test,
replace_image_to_tensor)
from mmocr.datasets import build_dataloader, build_dataset
from mmocr.models import build_detector
from mmocr.utils import revert_sync_batchnorm, setup_multi_processes
def parse_args():
parser = argparse.ArgumentParser(
description='MMOCR test (and eval) a model.')
parser.add_argument('config', help='Test config file path.')
parser.add_argument('checkpoint', help='Checkpoint file.')
parser.add_argument('--out', help='Output result file in pickle format.')
parser.add_argument(
'--gpu-id',
type=int,
default=0,
help='id of gpu to use '
'(only applicable to non-distributed testing)')
parser.add_argument(
'--eval',
type=str,
nargs='+',
help='The evaluation metrics. Options: \'hmean-ic13\', \'hmean-iou'
'\' for text detection tasks, \'acc\' for text recognition tasks, and '
'\'macro-f1\' for key information extraction tasks.')
parser.add_argument(
'--show-score-thr',
type=float,
default=0.3,
help='Score threshold (default: 0.3).')
parser.add_argument(
'--cfg-options',
nargs='+',
action=DictAction,
help='Override some settings in the used config, the key-value pair '
'in xxx=yyy format will be merged into the config file. If the value '
'to be overwritten is a list, it should be of the form of either '
'key="[a,b]" or key=a,b. The argument also allows nested list/tuple '
'values, e.g. key="[(a,b),(c,d)]". Note that the quotation marks '
'are necessary and that no white space is allowed.')
parser.add_argument(
'--options',
nargs='+',
action=DictAction,
help='Custom options for evaluation, the key-value pair in xxx=yyy '
'format will be kwargs for dataset.evaluate() function (deprecate), '
'change to --eval-options instead.')
parser.add_argument(
'--eval-options',
nargs='+',
action=DictAction,
help='Custom options for evaluation, the key-value pair in xxx=yyy '
'format will be kwargs for dataset.evaluate() function.')
parser.add_argument(
'--launcher',
choices=['none', 'pytorch', 'slurm', 'mpi'],
default='none',
help='Options for job launcher.')
parser.add_argument('--local_rank', type=int, default=0)
args = parser.parse_args()
if 'LOCAL_RANK' not in os.environ:
os.environ['LOCAL_RANK'] = str(args.local_rank)
if args.options and args.eval_options:
raise ValueError(
'--options and --eval-options cannot be both '
'specified, --options is deprecated in favor of --eval-options.')
if args.options:
warnings.warn('--options is deprecated in favor of --eval-options.')
args.eval_options = args.options
return args
def main():
args = parse_args()
assert (
args.out or args.eval or args.format_only or args.show
or args.show_dir), (
'Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir".')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
setup_multi_processes(cfg)
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if cfg.model.get('pretrained'):
cfg.model.pretrained = None
if cfg.model.get('neck'):
if isinstance(cfg.model.neck, list):
for neck_cfg in cfg.model.neck:
if neck_cfg.get('rfp_backbone'):
if neck_cfg.rfp_backbone.get('pretrained'):
neck_cfg.rfp_backbone.pretrained = None
elif cfg.model.neck.get('rfp_backbone'):
if cfg.model.neck.rfp_backbone.get('pretrained'):
cfg.model.neck.rfp_backbone.pretrained = None
samples_per_gpu = (cfg.data.get('test_dataloader', {})).get(
'samples_per_gpu', cfg.data.get('samples_per_gpu', 1))
if samples_per_gpu > 1:
cfg = disable_text_recog_aug_test(cfg)
cfg = replace_image_to_tensor(cfg)
if args.launcher == 'none':
cfg.gpu_ids = [args.gpu_id]
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
cfg.data.test['datasets'][0]['ann_file'] = "mmocr/" + cfg.data.test['datasets'][0]['ann_file']
cfg.data.test['datasets'][0]['img_prefix'] = "mmocr/" + cfg.data.test['datasets'][0]['img_prefix']
dataset = build_dataset(cfg.data.test, dict(test_mode=True))
loader_cfg = {
**dict(seed=cfg.get('seed'), drop_last=False, dist=distributed),
**({} if torch.__version__ != 'parrots' else dict(
prefetch_num=2,
pin_memory=False,
)),
**dict((k, cfg.data[k]) for k in [
'workers_per_gpu',
'seed',
'prefetch_num',
'pin_memory',
'persistent_workers',
] if k in cfg.data)
}
test_loader_cfg = {
**loader_cfg,
**dict(shuffle=False, drop_last=False),
**cfg.data.get('test_dataloader', {}),
**dict(samples_per_gpu=samples_per_gpu)
}
data_loader = build_dataloader(dataset, **test_loader_cfg)
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
model = revert_sync_batchnorm(model)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if not distributed:
model = MMDataParallel(model, device_ids=cfg.gpu_ids)
is_kie = cfg.model.type in ['SDMGR']
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
for key in [
'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best',
'rule'
]:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
output_file_path = './boundary_results.txt'
boundary_results = []
with open(output_file_path, 'r') as ff:
temp = ff.readlines()
for item in temp:
tmp = eval(item)
boundary_results.append(tmp)
print(dataset.evaluate(boundary_results, **eval_kwargs))
if __name__ == '__main__':
main()