def main():
"""Visualize the demo images.
Using mmdet to detect the human.
"""
parser = ArgumentParser()
parser.add_argument('det_config', help='Config file for detection')
parser.add_argument('det_checkpoint', help='Checkpoint file for detection')
parser.add_argument('pose_config', help='Config file for pose')
parser.add_argument('pose_checkpoint', help='Checkpoint file for pose')
parser.add_argument('--img-root', type=str, default='', help='Image root')
parser.add_argument('--img', type=str, default='', help='Image file')
parser.add_argument('--show',
action='store_true',
default=False,
help='whether to show img')
parser.add_argument('--out-img-root',
type=str,
default='',
help='root of the output img file. '
'Default not saving the visualization images.')
parser.add_argument('--device',
default='cuda:0',
help='Device used for inference')
parser.add_argument('--bbox-thr',
type=float,
default=0.3,
help='Bounding bbox score threshold')
parser.add_argument('--kpt-thr',
type=float,
default=0.3,
help='Keypoint score threshold')
args = parser.parse_args()
skeleton = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12],
[7, 13], [6, 7], [6, 8], [7, 9], [8, 10], [9, 11], [2, 3],
[1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]
assert args.show or (args.out_img_root != '')
assert args.img != ''
assert 'cuda' in args.device
assert args.det_config is not None
assert args.det_checkpoint is not None
det_model = init_detector(args.det_config,
args.det_checkpoint,
device=args.device)
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(args.pose_config,
args.pose_checkpoint,
device=args.device)
image_name = os.path.join(args.img_root, args.img)
# test a single image, the resulting box is (x1, y1, x2, y2)
det_results = inference_detector(det_model, image_name)
# keep the person class bounding boxes. (FasterRCNN)
person_bboxes = det_results[0].copy()
# test a single image, with a list of bboxes.
pose_results = inference_pose_model(pose_model,
image_name,
person_bboxes,
bbox_thr=args.bbox_thr,
format='xyxy')
if args.out_img_root == '':
out_file = None
else:
out_file = os.path.join(args.out_img_root, f'vis_{args.img}')
# show the results
vis_pose_result(pose_model,
image_name,
pose_results,
skeleton=skeleton,
kpt_score_thr=args.kpt_thr,
show=args.show,
out_file=out_file)
def main():
"""Visualize the demo images.
Using mmdet to detect the human.
"""
parser = ArgumentParser()
parser.add_argument('det_config', help='Config file for detection')
parser.add_argument('det_checkpoint', help='Checkpoint file for detection')
parser.add_argument('pose_config', help='Config file for pose')
parser.add_argument('pose_checkpoint', help='Checkpoint file for pose')
parser.add_argument('--video-path', type=str, help='Video path')
parser.add_argument('--show',
action='store_true',
default=False,
help='whether to show visualizations.')
parser.add_argument('--out-video-root',
default='',
help='Root of the output video file. '
'Default not saving the visualization video.')
parser.add_argument('--device',
default='cuda:0',
help='Device used for inference')
parser.add_argument('--bbox-thr',
type=float,
default=0.3,
help='Bounding box score threshold')
parser.add_argument('--kpt-thr',
type=float,
default=0.3,
help='Keypoint score threshold')
args = parser.parse_args()
skeleton = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12],
[7, 13], [6, 7], [6, 8], [7, 9], [8, 10], [9, 11], [2, 3],
[1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]
assert args.show or (args.out_video_root != '')
assert 'cuda' in args.device
assert args.det_config is not None
assert args.det_checkpoint is not None
det_model = init_detector(args.det_config,
args.det_checkpoint,
device=args.device)
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(args.pose_config,
args.pose_checkpoint,
device=args.device)
cap = cv2.VideoCapture(args.video_path)
if args.out_video_root == '':
save_out_video = False
else:
os.makedirs(args.out_video_root, exist_ok=True)
save_out_video = True
if save_out_video:
fps = cap.get(cv2.CAP_PROP_FPS)
size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
videoWriter = cv2.VideoWriter(
os.path.join(args.out_video_root,
f'vis_{os.path.basename(args.video_path)}'), fourcc,
fps, size)
while (cap.isOpened()):
flag, img = cap.read()
if not flag:
break
# test a single image, the resulting box is (x1, y1, x2, y2)
det_results = inference_detector(det_model, img)
# keep the person class bounding boxes.
person_bboxes = det_results[0].copy()
# test a single image, with a list of bboxes.
pose_results = inference_pose_model(pose_model,
img,
person_bboxes,
bbox_thr=args.bbox_thr,
format='xyxy')
# show the results
vis_img = vis_pose_result(pose_model,
img,
pose_results,
skeleton=skeleton,
kpt_score_thr=args.kpt_thr,
show=False)
if args.show:
cv2.imshow('Image', vis_img)
if save_out_video:
videoWriter.write(vis_img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
if save_out_video:
videoWriter.release()
cv2.destroyAllWindows()
# In[4]:
result = pickle.load(open("../data/results_bbox_test.pkl", 'rb'))
len(result)
# In[5]:
final_result = []
for idx, (img, r) in tqdm(enumerate(zip(paths, result))):
person_bboxes = r[
-1] #[[128.54112 , 64.24658 , 143.41219 , 156.22845 ,0.98622096]]
pose_results = inference_pose_model(pose_model,
img,
person_bboxes,
format='xyxy')
final_result.append(pose_results)
# palette = np.array([[255, 128, 0], [255, 153, 51], [255, 178, 102],
# [230, 230, 0], [255, 153, 255], [153, 204, 255],
# [255, 102, 255], [255, 51, 255], [102, 178, 255],
# [51, 153, 255], [255, 153, 153], [255, 102, 102],
# [255, 51, 51], [153, 255, 153], [102, 255, 102],
# [51, 255, 51], [0, 255, 0]])
# pose_limb_color = palette[[
# 0, 0, 0, 0, 7, 7, 7, 9, 9, 9, 9, 9, 16, 16, 16, 16, 16, 16, 16
# ]]
# pose_kpt_color = palette[[
def main():
"""Visualize the demo images.
Using mmdet to detect the human.
"""
parser = ArgumentParser()
parser.add_argument('det_config', help='Config file for detection')
parser.add_argument('det_checkpoint', help='Checkpoint file for detection')
parser.add_argument('pose_config', help='Config file for pose')
parser.add_argument('pose_checkpoint', help='Checkpoint file for pose')
parser.add_argument('--img_prefix',
type=str,
default='',
help='Image prefix')
parser.add_argument('--img', type=str, default='', help='Image file')
parser.add_argument('--device',
default='cuda:0',
help='Device used for inference')
parser.add_argument('--bbox_thr',
type=float,
default=0.3,
help='bbox score threshold')
parser.add_argument('--kpt_thr',
type=float,
default=0.3,
help='keypoint score threshold')
args = parser.parse_args()
skeleton = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12],
[7, 13], [6, 7], [6, 8], [7, 9], [8, 10], [9, 11], [2, 3],
[1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]
assert args.img != ''
assert args.det_config is not None
assert args.det_checkpoint is not None
det_model = init_detector(args.det_config,
args.det_checkpoint,
device=args.device)
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(args.pose_config,
args.pose_checkpoint,
device=args.device)
image_name = os.path.join(args.img_prefix, args.img)
# test a single image, the resulting box is (x1, y1, x2, y2)
det_results = inference_detector(det_model, image_name)
# keep the person class bounding boxes.
person_bboxes = det_results[0][0].copy()
# test a single image, with a list of bboxes.
pose_results = inference_pose_model(pose_model,
image_name,
person_bboxes,
bbox_thr=args.bbox_thr,
format='xyxy')
# show the results
show_pose_result(pose_model,
image_name,
pose_results,
skeleton=skeleton,
kpt_score_thr=args.kpt_thr)
def main():
"""Visualize the demo images."""
parser = ArgumentParser()
parser.add_argument('pose_config', help='Config file for detection')
parser.add_argument('pose_checkpoint', help='Checkpoint file')
parser.add_argument('--img_prefix',
type=str,
default='',
help='Image prefix')
parser.add_argument('--json_file',
type=str,
default='',
help='Json file containing image info.')
parser.add_argument('--device',
default='cuda:0',
help='Device used for inference')
parser.add_argument('--kpt_thr',
type=float,
default=0.3,
help='box score threshold')
args = parser.parse_args()
skeleton = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12],
[7, 13], [6, 7], [6, 8], [7, 9], [8, 10], [9, 11], [2, 3],
[1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]
from pycocotools.coco import COCO
coco = COCO(args.json_file)
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(args.pose_config,
args.pose_checkpoint,
device=args.device)
img_keys = list(coco.imgs.keys())
# process each image
for i in tqdm(range(len(img_keys))):
# get bounding box annotations
image_id = img_keys[i]
image = coco.loadImgs(image_id)[0]
image_name = os.path.join(args.img_prefix, image['file_name'])
ann_ids = coco.getAnnIds(image_id)
# make person bounding boxes
person_bboxes = []
for ann_id in ann_ids:
ann = coco.anns[ann_id]
# bbox format is 'xywh'
bbox = ann['bbox']
person_bboxes.append(bbox)
# test a single image, with a list of bboxes.
pose_results = inference_pose_model(pose_model,
image_name,
person_bboxes,
format='xywh')
# show the results
show_pose_result(pose_model,
image_name,
pose_results,
skeleton=skeleton,
kpt_score_thr=args.kpt_thr)
def main():
"""Visualize the demo images.
Require the json_file containing boxes.
"""
parser = ArgumentParser()
parser.add_argument('pose_config', help='Config file for detection')
parser.add_argument('pose_checkpoint', help='Checkpoint file')
parser.add_argument('--img-root', type=str, default='', help='Image root')
parser.add_argument('--json-file',
type=str,
default='',
help='Json file containing image info.')
parser.add_argument('--show',
action='store_true',
default=False,
help='whether to show img')
parser.add_argument('--out-img-root',
type=str,
default='',
help='Root of the output img file. '
'Default not saving the visualization images.')
parser.add_argument('--device',
default='cuda:0',
help='Device used for inference')
parser.add_argument('--kpt-thr',
type=float,
default=0.3,
help='Keypoint score threshold')
args = parser.parse_args()
assert args.show or (args.out_img_root != '')
assert 'cuda' in args.device
skeleton = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12],
[7, 13], [6, 7], [6, 8], [7, 9], [8, 10], [9, 11], [2, 3],
[1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]
from pycocotools.coco import COCO
coco = COCO(args.json_file)
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(args.pose_config,
args.pose_checkpoint,
device=args.device)
img_keys = list(coco.imgs.keys())
# process each image
for i in range(len(img_keys)):
# get bounding box annotations
image_id = img_keys[i]
image = coco.loadImgs(image_id)[0]
image_name = os.path.join(args.img_root, image['file_name'])
ann_ids = coco.getAnnIds(image_id)
# make person bounding boxes
person_bboxes = []
for ann_id in ann_ids:
ann = coco.anns[ann_id]
# bbox format is 'xywh'
bbox = ann['bbox']
person_bboxes.append(bbox)
# test a single image, with a list of bboxes.
pose_results = inference_pose_model(pose_model,
image_name,
person_bboxes,
format='xywh')
if args.out_img_root == '':
out_file = None
else:
os.makedirs(args.out_img_root, exist_ok=True)
out_file = os.path.join(args.out_img_root, f'vis_{i}.jpg')
# show the results
vis_pose_result(pose_model,
image_name,
pose_results,
skeleton=skeleton,
kpt_score_thr=args.kpt_thr,
show=args.show,
out_file=out_file)