# Copyright (c) OpenMMLab. All rights reserved.
"""Image Demo.
This script adopts a new infenence class, currently supports image path,
np.array and folder input formats, and will support video and webcam
in the future.
Example:
Save visualizations and predictions results::
python demo/image_demo.py demo/demo.jpg rtmdet-s
python demo/image_demo.py demo/demo.jpg \
configs/rtmdet/rtmdet_s_8xb32-300e_coco.py \
--weights rtmdet_s_8xb32-300e_coco_20220905_161602-387a891e.pth
python demo/image_demo.py demo/demo.jpg \
glip_atss_swin-t_a_fpn_dyhead_pretrain_obj365 --texts bench
python demo/image_demo.py demo/demo.jpg \
glip_atss_swin-t_a_fpn_dyhead_pretrain_obj365 --texts 'bench . car .'
python demo/image_demo.py demo/demo.jpg \
glip_atss_swin-t_a_fpn_dyhead_pretrain_obj365
--texts 'bench . car .' -c
python demo/image_demo.py demo/demo.jpg \
glip_atss_swin-t_a_fpn_dyhead_pretrain_obj365 \
--texts 'There are a lot of cars here.'
Visualize prediction results::
python demo/image_demo.py demo/demo.jpg rtmdet-ins-s --show
python demo/image_demo.py demo/demo.jpg rtmdet-ins_s_8xb32-300e_coco \
--show
"""
from argparse import ArgumentParser
from mmengine.logging import print_log
from mmdet.apis import DetInferencer
def parse_args():
parser = ArgumentParser()
parser.add_argument(
'inputs', type=str, help='Input image file or folder path.')
parser.add_argument(
'model',
type=str,
help='Config or checkpoint .pth file or the model name '
'and alias defined in metafile. The model configuration '
'file will try to read from .pth if the parameter is '
'a .pth weights file.')
parser.add_argument('--weights', default=None, help='Checkpoint file')
parser.add_argument(
'--out-dir',
type=str,
default='outputs',
help='Output directory of images or prediction results.')
parser.add_argument('--texts', help='text prompt')
parser.add_argument(
'--device', default='cuda:0', help='Device used for inference')
parser.add_argument(
'--pred-score-thr',
type=float,
default=0.3,
help='bbox score threshold')
parser.add_argument(
'--batch-size', type=int, default=1, help='Inference batch size.')
parser.add_argument(
'--show',
action='store_true',
help='Display the image in a popup window.')
parser.add_argument(
'--no-save-vis',
action='store_true',
help='Do not save detection vis results')
parser.add_argument(
'--no-save-pred',
action='store_true',
help='Do not save detection json results')
parser.add_argument(
'--print-result',
action='store_true',
help='Whether to print the results.')
parser.add_argument(
'--palette',
default='none',
choices=['coco', 'voc', 'citys', 'random', 'none'],
help='Color palette used for visualization')
# only for GLIP
parser.add_argument(
'--custom-entities',
'-c',
action='store_true',
help='Whether to customize entity names? '
'If so, the input text should be '
'"cls_name1 . cls_name2 . cls_name3 ." format')
call_args = vars(parser.parse_args())
if call_args['no_save_vis'] and call_args['no_save_pred']:
call_args['out_dir'] = ''
if call_args['model'].endswith('.pth'):
print_log('The model is a weight file, automatically '
'assign the model to --weights')
call_args['weights'] = call_args['model']
call_args['model'] = None
init_kws = ['model', 'weights', 'device', 'palette']
init_args = {}
for init_kw in init_kws:
init_args[init_kw] = call_args.pop(init_kw)
return init_args, call_args
def main():
init_args, call_args = parse_args()
# TODO: Video and Webcam are currently not supported and
# may consume too much memory if your input folder has a lot of images.
# We will be optimized later.
inferencer = DetInferencer(**init_args)
inferencer(**call_args)
if call_args['out_dir'] != '' and not (call_args['no_save_vis']
and call_args['no_save_pred']):
print_log(f'results have been saved at {call_args["out_dir"]}')
if __name__ == '__main__':
main()
