def test_bottom_up_demo():
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(
'configs/body/2d_kpt_sview_rgb_img/associative_embedding/'
'coco/res50_coco_512x512.py',
None,
device='cpu')
image_name = 'tests/data/coco/000000000785.jpg'
dataset_info = DatasetInfo(pose_model.cfg.data['test'].get(
'dataset_info', None))
pose_results, _ = inference_bottom_up_pose_model(pose_model,
image_name,
dataset_info=dataset_info)
# show the results
vis_pose_result(pose_model,
image_name,
pose_results,
dataset_info=dataset_info)
# test dataset_info without sigmas
pose_model_copy = copy.deepcopy(pose_model)
pose_model_copy.cfg.data.test.dataset_info.pop('sigmas')
pose_results, _ = inference_bottom_up_pose_model(pose_model_copy,
image_name,
dataset_info=dataset_info)
def test_bottom_up_pose_tracking_demo():
# COCO demo
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(
'configs/body/2d_kpt_sview_rgb_img/associative_embedding/'
'coco/res50_coco_512x512.py',
None,
device='cpu')
image_name = 'tests/data/coco/000000000785.jpg'
pose_results, _ = inference_bottom_up_pose_model(pose_model, image_name)
pose_results, next_id = get_track_id(pose_results, [], next_id=0)
# show the results
vis_pose_tracking_result(pose_model,
image_name,
pose_results,
dataset='BottomUpCocoDataset')
pose_results_last = pose_results
# oks
pose_results, next_id = get_track_id(pose_results,
pose_results_last,
next_id=next_id,
use_oks=True)
pose_results_last = pose_results
# one_euro
pose_results, next_id = get_track_id(pose_results,
pose_results_last,
next_id=next_id,
use_one_euro=True)
def main(args):
os.makedirs(args.out_dir, exist_ok=True)
# Inference single image by native apis.
model = init_pose_model(args.config, args.checkpoint, device=args.device)
if isinstance(model, TopDown):
pytorch_result, _ = inference_top_down_pose_model(model,
args.img,
person_results=None)
elif isinstance(model, (AssociativeEmbedding, )):
pytorch_result, _ = inference_bottom_up_pose_model(model, args.img)
else:
raise NotImplementedError()
vis_pose_result(model,
args.img,
pytorch_result,
out_file=osp.join(args.out_dir, 'pytorch_result.png'))
# Inference single image by torchserve engine.
url = 'http://' + args.inference_addr + '/predictions/' + args.model_name
with open(args.img, 'rb') as image:
response = requests.post(url, image)
server_result = response.json()
vis_pose_result(model,
args.img,
server_result,
out_file=osp.join(args.out_dir, 'torchserve_result.png'))
def test_bottom_up_demo():
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(
'configs/bottom_up/resnet/coco/res50_coco_512x512.py',
None,
device='cpu')
image_name = 'tests/data/coco/000000000785.jpg'
pose_results, _ = inference_bottom_up_pose_model(pose_model, image_name)
# show the results
vis_pose_result(
pose_model, image_name, pose_results, dataset='BottomUpCocoDataset')
def test_bottom_up_demo():
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]]
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(
'configs/bottom_up/resnet/coco/res50_coco_512x512.py',
None,
device='cpu')
image_name = 'tests/data/coco/000000000785.jpg'
pose_results = inference_bottom_up_pose_model(pose_model, image_name)
# show the results
vis_pose_result(pose_model, image_name, pose_results, skeleton=skeleton)
def test_bottom_up_pose_tracking_demo():
# COCO demo
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(
'configs/body/2d_kpt_sview_rgb_img/associative_embedding/'
'coco/res50_coco_512x512.py',
None,
device='cpu')
image_name = 'tests/data/coco/000000000785.jpg'
dataset_info = DatasetInfo(pose_model.cfg.data['test']['dataset_info'])
pose_results, _ = inference_bottom_up_pose_model(pose_model,
image_name,
dataset_info=dataset_info)
pose_results, next_id = get_track_id(pose_results, [], next_id=0)
# show the results
vis_pose_tracking_result(pose_model,
image_name,
pose_results,
dataset_info=dataset_info)
pose_results_last = pose_results
# oks
pose_results, next_id = get_track_id(pose_results,
pose_results_last,
next_id=next_id,
use_oks=True)
pose_results_last = pose_results
# one_euro (will be deprecated)
with pytest.deprecated_call():
pose_results, next_id = get_track_id(pose_results,
pose_results_last,
next_id=next_id,
use_one_euro=True)
def get_pose(
img,
result_path,
pose_config='./mobilenetv2_coco_512x512.py',
pose_checkpoint='./mobilenetv2_coco_512x512-4d96e309_20200816.pth',
device='cpu',
kpt_thr=0.5):
# build the pose model from a config file and a checkpoint file
pose_model = init_pose_model(pose_config,
pose_checkpoint,
device=device.lower())
# optional
return_heatmap = False
dataset = pose_model.cfg.data['test']['type']
assert (dataset == 'BottomUpCocoDataset')
# e.g. use ('backbone', ) to return backbone feature
output_layer_names = None
img = cv2.imread(img)
pose_results, returned_outputs = inference_bottom_up_pose_model(
pose_model,
img,
return_heatmap=return_heatmap,
outputs=output_layer_names)
# show the results
vis_img = vis_pose_result(pose_model,
img,
pose_results,
dataset=dataset,
kpt_score_thr=kpt_thr,
show=False)
cv2.imwrite(result_path, vis_img)
sample0 = {"url": result_path}
res_list = [sample0]
return res_list
def main():
args = parse_args()
device = torch.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.lower())
# optional
return_heatmap = False
dataset = pose_model.cfg.data['test']['type']
assert (dataset == 'BottomUpCocoDataset')
# e.g. use ('backbone', ) to return backbone feature
output_layer_names = None
print('Press "Esc", "q" or "Q" to exit.')
while True:
# ret_val, img = camera.read()
img = cv2.imread(args.img_root)
pose_results, returned_outputs = inference_bottom_up_pose_model(
pose_model,
img,
return_heatmap=return_heatmap,
outputs=output_layer_names)
# show the results
vis_img = vis_pose_result(pose_model,
img,
pose_results,
dataset=dataset,
kpt_score_thr=args.kpt_thr,
show=False)
ch = cv2.waitKey(1)
if ch == 27 or ch == ord('q') or ch == ord('Q'):
break
cv2.imshow('Image', vis_img)
def main():
"""Visualize the demo images."""
parser = ArgumentParser()
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('--kpt-thr',
type=float,
default=0.3,
help='Keypoint score threshold')
args = parser.parse_args()
assert args.show or (args.out_video_root != '')
# 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)
dataset = pose_model.cfg.data['test']['type']
assert (dataset == 'BottomUpCocoDataset')
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
pose_results = inference_bottom_up_pose_model(pose_model, img)
# show the results
vis_img = vis_pose_result(pose_model,
img,
pose_results,
dataset=dataset,
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()
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-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 != '')
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]]
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)):
image_id = img_keys[i]
image = coco.loadImgs(image_id)[0]
image_name = os.path.join(args.img_root, image['file_name'])
# test a single image, with a list of bboxes.
pose_results = inference_bottom_up_pose_model(pose_model, image_name)
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)
def main():
"""Visualize the demo images."""
parser = ArgumentParser()
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('--kpt-thr',
type=float,
default=0.5,
help='Keypoint score threshold')
parser.add_argument('--pose-nms-thr',
type=float,
default=0.9,
help='OKS threshold for pose NMS')
parser.add_argument('--use-oks-tracking',
action='store_true',
help='Using OKS tracking')
parser.add_argument('--tracking-thr',
type=float,
default=0.3,
help='Tracking threshold')
parser.add_argument('--euro',
action='store_true',
help='Using One_Euro_Filter for smoothing')
parser.add_argument('--radius',
type=int,
default=4,
help='Keypoint radius for visualization')
parser.add_argument('--thickness',
type=int,
default=1,
help='Link thickness for visualization')
args = parser.parse_args()
assert args.show or (args.out_video_root != '')
# 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.lower())
dataset = pose_model.cfg.data['test']['type']
assert (dataset == 'BottomUpCocoDataset')
cap = cv2.VideoCapture(args.video_path)
fps = None
assert cap.isOpened(), f'Faild to load video file {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)
# optional
return_heatmap = False
# e.g. use ('backbone', ) to return backbone feature
output_layer_names = None
next_id = 0
pose_results = []
while (cap.isOpened()):
flag, img = cap.read()
if not flag:
break
pose_results_last = pose_results
pose_results, returned_outputs = inference_bottom_up_pose_model(
pose_model,
img,
pose_nms_thr=args.pose_nms_thr,
return_heatmap=return_heatmap,
outputs=output_layer_names)
# get track id for each person instance
pose_results, next_id = get_track_id(pose_results,
pose_results_last,
next_id,
use_oks=args.use_oks_tracking,
tracking_thr=args.tracking_thr,
use_one_euro=args.euro,
fps=fps)
# show the results
vis_img = vis_pose_tracking_result(pose_model,
img,
pose_results,
radius=args.radius,
thickness=args.thickness,
dataset=dataset,
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()
def main():
"""Visualize the demo images."""
parser = ArgumentParser()
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('--kpt-thr',
type=float,
default=0.5,
help='Keypoint score threshold')
parser.add_argument('--pose-nms-thr',
type=float,
default=0.9,
help='OKS threshold for pose NMS')
parser.add_argument('--use-oks-tracking',
action='store_true',
help='Using OKS tracking')
parser.add_argument('--tracking-thr',
type=float,
default=0.3,
help='Tracking threshold')
parser.add_argument(
'--euro',
action='store_true',
help='(Deprecated, please use --smooth and --smooth-filter-cfg) '
'Using One_Euro_Filter for smoothing.')
parser.add_argument(
'--smooth',
action='store_true',
help='Apply a temporal filter to smooth the pose estimation results. '
'See also --smooth-filter-cfg.')
parser.add_argument(
'--smooth-filter-cfg',
type=str,
default='configs/_base_/filters/one_euro.py',
help='Config file of the filter to smooth the pose estimation '
'results. See also --smooth.')
parser.add_argument('--radius',
type=int,
default=4,
help='Keypoint radius for visualization')
parser.add_argument('--thickness',
type=int,
default=1,
help='Link thickness for visualization')
args = parser.parse_args()
assert args.show or (args.out_video_root != '')
# 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.lower())
dataset = pose_model.cfg.data['test']['type']
dataset_info = pose_model.cfg.data['test'].get('dataset_info', None)
if dataset_info is None:
warnings.warn(
'Please set `dataset_info` in the config.'
'Check https://github.com/open-mmlab/mmpose/pull/663 for details.',
DeprecationWarning)
assert (dataset == 'BottomUpCocoDataset')
else:
dataset_info = DatasetInfo(dataset_info)
video = mmcv.VideoReader(args.video_path)
assert video.opened, f'Faild to load video file {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 = video.fps
size = (video.width, video.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)
# optional
return_heatmap = False
# build pose smoother for temporal refinement
if args.euro:
warnings.warn(
'Argument --euro will be deprecated in the future. '
'Please use --smooth to enable temporal smoothing, and '
'--smooth-filter-cfg to set the filter config.',
DeprecationWarning)
smoother = Smoother(filter_cfg='configs/_base_/filters/one_euro.py',
keypoint_dim=2)
elif args.smooth:
smoother = Smoother(filter_cfg=args.smooth_filter_cfg, keypoint_dim=2)
else:
smoother = None
# e.g. use ('backbone', ) to return backbone feature
output_layer_names = None
next_id = 0
pose_results = []
for cur_frame in mmcv.track_iter_progress(video):
pose_results_last = pose_results
pose_results, _ = inference_bottom_up_pose_model(
pose_model,
cur_frame,
dataset=dataset,
dataset_info=dataset_info,
pose_nms_thr=args.pose_nms_thr,
return_heatmap=return_heatmap,
outputs=output_layer_names)
# get track id for each person instance
pose_results, next_id = get_track_id(pose_results,
pose_results_last,
next_id,
use_oks=args.use_oks_tracking,
tracking_thr=args.tracking_thr,
use_one_euro=args.euro,
fps=fps)
# post-process the pose results with smoother
if smoother:
pose_results = smoother.smooth(pose_results)
# show the results
vis_frame = vis_pose_tracking_result(pose_model,
cur_frame,
pose_results,
radius=args.radius,
thickness=args.thickness,
dataset=dataset,
dataset_info=dataset_info,
kpt_score_thr=args.kpt_thr,
show=False)
if args.show:
cv2.imshow('Image', vis_frame)
if save_out_video:
videoWriter.write(vis_frame)
if args.show and cv2.waitKey(1) & 0xFF == ord('q'):
break
if save_out_video:
videoWriter.release()
if args.show:
cv2.destroyAllWindows()
def _inference_bottom_up_pose_model(self, data):
results = []
for image in data:
preds, _ = inference_bottom_up_pose_model(self.model, image)
results.append(preds)
return results
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-path',
type=str,
help='Path to an image file or a image folder.')
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')
parser.add_argument(
'--pose-nms-thr',
type=float,
default=0.9,
help='OKS threshold for pose NMS')
parser.add_argument(
'--radius',
type=int,
default=4,
help='Keypoint radius for visualization')
parser.add_argument(
'--thickness',
type=int,
default=1,
help='Link thickness for visualization')
args = parser.parse_args()
assert args.show or (args.out_img_root != '')
# prepare image list
if osp.isfile(args.img_path):
image_list = [args.img_path]
elif osp.isdir(args.img_path):
image_list = [
osp.join(args.img_path, fn) for fn in os.listdir(args.img_path)
if fn.lower().endswith(('.png', '.jpg', '.jpeg', '.tiff', '.bmp'))
]
else:
raise ValueError('Image path should be an image or image folder.'
f'Got invalid image path: {args.img_path}')
# 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.lower())
dataset = pose_model.cfg.data['test']['type']
dataset_info = pose_model.cfg.data['test'].get('dataset_info', None)
if dataset_info is None:
warnings.warn(
'Please set `dataset_info` in the config.'
'Check https://github.com/open-mmlab/mmpose/pull/663 for details.',
DeprecationWarning)
assert (dataset == 'BottomUpCocoDataset')
else:
dataset_info = DatasetInfo(dataset_info)
# optional
return_heatmap = False
# e.g. use ('backbone', ) to return backbone feature
output_layer_names = None
# process each image
for image_name in mmcv.track_iter_progress(image_list):
# test a single image, with a list of bboxes.
pose_results, returned_outputs = inference_bottom_up_pose_model(
pose_model,
image_name,
dataset=dataset,
dataset_info=dataset_info,
pose_nms_thr=args.pose_nms_thr,
return_heatmap=return_heatmap,
outputs=output_layer_names)
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_{osp.splitext(osp.basename(image_name))[0]}.jpg')
# show the results
vis_pose_result(
pose_model,
image_name,
pose_results,
radius=args.radius,
thickness=args.thickness,
dataset=dataset,
dataset_info=dataset_info,
kpt_score_thr=args.kpt_thr,
show=args.show,
out_file=out_file)
def test_inference_without_dataset_info():
# Top down
pose_model = init_pose_model(
'configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/'
'coco/res50_coco_256x192.py',
None,
device='cpu')
if 'dataset_info' in pose_model.cfg:
_ = pose_model.cfg.pop('dataset_info')
image_name = 'tests/data/coco/000000000785.jpg'
person_result = []
person_result.append({'bbox': [50, 50, 50, 100]})
with pytest.warns(DeprecationWarning):
pose_results, _ = inference_top_down_pose_model(pose_model,
image_name,
person_result,
format='xywh')
with pytest.warns(DeprecationWarning):
vis_pose_result(pose_model, image_name, pose_results)
with pytest.raises(NotImplementedError):
with pytest.warns(DeprecationWarning):
pose_results, _ = inference_top_down_pose_model(pose_model,
image_name,
person_result,
format='xywh',
dataset='test')
# Bottom up
pose_model = init_pose_model(
'configs/body/2d_kpt_sview_rgb_img/associative_embedding/'
'coco/res50_coco_512x512.py',
None,
device='cpu')
if 'dataset_info' in pose_model.cfg:
_ = pose_model.cfg.pop('dataset_info')
image_name = 'tests/data/coco/000000000785.jpg'
with pytest.warns(DeprecationWarning):
pose_results, _ = inference_bottom_up_pose_model(
pose_model, image_name)
with pytest.warns(DeprecationWarning):
vis_pose_result(pose_model, image_name, pose_results)
# Top down tracking
pose_model = init_pose_model(
'configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/'
'coco/res50_coco_256x192.py',
None,
device='cpu')
if 'dataset_info' in pose_model.cfg:
_ = pose_model.cfg.pop('dataset_info')
image_name = 'tests/data/coco/000000000785.jpg'
person_result = [{'bbox': [50, 50, 50, 100]}]
with pytest.warns(DeprecationWarning):
pose_results, _ = inference_top_down_pose_model(pose_model,
image_name,
person_result,
format='xywh')
pose_results, _ = get_track_id(pose_results, [], next_id=0)
with pytest.warns(DeprecationWarning):
vis_pose_tracking_result(pose_model, image_name, pose_results)
with pytest.raises(NotImplementedError):
with pytest.warns(DeprecationWarning):
vis_pose_tracking_result(pose_model,
image_name,
pose_results,
dataset='test')
# Bottom up tracking
pose_model = init_pose_model(
'configs/body/2d_kpt_sview_rgb_img/associative_embedding/'
'coco/res50_coco_512x512.py',
None,
device='cpu')
if 'dataset_info' in pose_model.cfg:
_ = pose_model.cfg.pop('dataset_info')
image_name = 'tests/data/coco/000000000785.jpg'
with pytest.warns(DeprecationWarning):
pose_results, _ = inference_bottom_up_pose_model(
pose_model, image_name)
pose_results, next_id = get_track_id(pose_results, [], next_id=0)
with pytest.warns(DeprecationWarning):
vis_pose_tracking_result(pose_model,
image_name,
pose_results,
dataset='BottomUpCocoDataset')
# Pose lifting
pose_model = init_pose_model(
'configs/body/3d_kpt_sview_rgb_img/pose_lift/'
'h36m/simplebaseline3d_h36m.py',
None,
device='cpu')
pose_det_result = {
'keypoints': np.zeros((17, 3)),
'bbox': [50, 50, 50, 50],
'track_id': 0,
'image_name': 'tests/data/h36m/S1_Directions_1.54138969_000001.jpg',
}
if 'dataset_info' in pose_model.cfg:
_ = pose_model.cfg.pop('dataset_info')
pose_results_2d = [[pose_det_result]]
dataset = pose_model.cfg.data['test']['type']
pose_results_2d = extract_pose_sequence(pose_results_2d,
frame_idx=0,
causal=False,
seq_len=1,
step=1)
with pytest.warns(DeprecationWarning):
_ = inference_pose_lifter_model(pose_model,
pose_results_2d,
dataset,
with_track_id=False)
with pytest.warns(DeprecationWarning):
pose_lift_results = inference_pose_lifter_model(pose_model,
pose_results_2d,
dataset,
with_track_id=True)
for res in pose_lift_results:
res['title'] = 'title'
with pytest.warns(DeprecationWarning):
vis_3d_pose_result(pose_model,
pose_lift_results,
img=pose_results_2d[0][0]['image_name'],
dataset=dataset)
with pytest.raises(NotImplementedError):
with pytest.warns(DeprecationWarning):
_ = inference_pose_lifter_model(pose_model,
pose_results_2d,
dataset='test')
def main():
"""Visualize the demo images."""
parser = ArgumentParser()
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('--kpt-thr',
type=float,
default=0.3,
help='Keypoint score threshold')
parser.add_argument('--pose-nms-thr',
type=float,
default=0.9,
help='OKS threshold for pose NMS')
parser.add_argument('--radius',
type=int,
default=4,
help='Keypoint radius for visualization')
parser.add_argument('--thickness',
type=int,
default=1,
help='Link thickness for visualization')
args = parser.parse_args()
assert args.show or (args.out_video_root != '')
# 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.lower())
dataset = pose_model.cfg.data['test']['type']
dataset_info = pose_model.cfg.data['test'].get('dataset_info', None)
if dataset_info is None:
warnings.warn(
'Please set `dataset_info` in the config.'
'Check https://github.com/open-mmlab/mmpose/pull/663 for details.',
DeprecationWarning)
assert (dataset == 'BottomUpCocoDataset')
else:
dataset_info = DatasetInfo(dataset_info)
# read video
video = mmcv.VideoReader(args.video_path)
assert video.opened, f'Faild to load video file {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 = video.fps
size = (video.width, video.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)
# optional
return_heatmap = False
# e.g. use ('backbone', ) to return backbone feature
output_layer_names = None
print('Running inference...')
for _, cur_frame in enumerate(mmcv.track_iter_progress(video)):
pose_results, _ = inference_bottom_up_pose_model(
pose_model,
cur_frame,
dataset=dataset,
dataset_info=dataset_info,
pose_nms_thr=args.pose_nms_thr,
return_heatmap=return_heatmap,
outputs=output_layer_names)
# show the results
vis_frame = vis_pose_result(pose_model,
cur_frame,
pose_results,
radius=args.radius,
thickness=args.thickness,
dataset=dataset,
dataset_info=dataset_info,
kpt_score_thr=args.kpt_thr,
show=False)
if args.show:
cv2.imshow('Image', vis_frame)
if save_out_video:
videoWriter.write(vis_frame)
if args.show and cv2.waitKey(1) & 0xFF == ord('q'):
break
if save_out_video:
videoWriter.release()
if args.show:
cv2.destroyAllWindows()
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-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 != '')
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)
dataset = pose_model.cfg.data['test']['type']
assert (dataset == 'BottomUpCocoDataset')
img_keys = list(coco.imgs.keys())
# optional
return_heatmap = False
# e.g. use ('backbone', ) to return backbone feature
output_layer_names = None
# process each image
for i in range(len(img_keys)):
image_id = img_keys[i]
image = coco.loadImgs(image_id)[0]
image_name = os.path.join(args.img_root, image['file_name'])
# test a single image, with a list of bboxes.
pose_results, returned_outputs = inference_bottom_up_pose_model(
pose_model,
image_name,
return_heatmap=return_heatmap,
outputs=output_layer_names)
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,
dataset=dataset,
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('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='cpu',
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')
# parser.add_argument('--csv-path', type=str, help='CSV path')
args = parser.parse_args()
assert args.show or (args.out_video_root != '')
# 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)
print('loaded poes model')
dataset = pose_model.cfg.data['test']['type']
assert (dataset == 'BottomUpCocoDataset')
print(dataset)
cap = cv2.VideoCapture(args.video_path)
print('loaded video')
frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
if args.out_video_root == '':
save_out_video = False
else:
os.makedirs(args.out_video_root, exist_ok=True)
save_out_video = True
print('save path: {0}'.format(args.out_video_root))
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)}').replace(
'.mp4', '-bottom.mp4'), fourcc, fps, size)
print(pose_model.cfg.channel_cfg['dataset_joints'])
poses = np.zeros((frames, pose_model.cfg.channel_cfg['dataset_joints'], 3))
print(poses.shape)
frame = 0
t0 = time.perf_counter()
prev_pose = 0
width = (cap.get(3))
height = (cap.get(4))
print('width: {0}, height: {1}'.format(width, height))
skip_ratio = 4
person_bboxes = [[
2 * width / 10, height / 8, 0.9 * width, 7 * height / 8, 1
]]
# person_bboxes = [[width / 8, height / 8, 3 * width / 4, 3 * height / 4, 1]]
print(person_bboxes)
while (cap.isOpened()):
t1 = time.perf_counter()
flag, img = cap.read()
if not flag:
break
# check every 2nd frame
if frame % skip_ratio == 0:
# 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 = np.expand_dims(
# np.array(det_results[0])[0, :], axis=0)
#
# print(person_bboxes)
# test a single image, with a list of bboxes.
pose_results = inference_bottom_up_pose_model(pose_model, img)
t = time.perf_counter()
print('Frame {0} analysed in {1} secs. Total time: {2} secs\
'.format(frame, t - t1, t - t0))
# print(pose_results)
# np_results = np.asarray(pose_results[0]['keypoints'])
# print(pose_results[0]['keypoints'])
# print('Result shape: {0}'.format(np_results.shape))
# show the results
if np.shape(pose_results)[0] > 0:
prev_pose = pose_results
x_ratios = pose_results[0]['keypoints'][:, 0] / width
y_ratios = pose_results[0]['keypoints'][:, 1] / height
poses[frame, :, 0] = x_ratios
poses[frame, :, 1] = y_ratios
if frame == 0:
print(x_ratios)
else:
pose_results = prev_pose # or maybe just skip saving
print('lol')
# print('bbox shape: {0}'.format(np.array(person_bboxes)))
#
# print('pose_result shape: {0}'.format(
# np.array(pose_results).shape))
# cv2.imshow('Image', img)
# cv2.waitKey(0)
else:
pose_results = prev_pose
vis_img = vis_pose_result(pose_model,
img,
pose_results,
dataset=dataset,
kpt_score_thr=args.kpt_thr,
show=False)
# if
# pose_results =
# poses[frame, ...] = pose_results[0]['keypoints']
# print(frame)
if args.show or frame % skip_ratio == 0:
cv2.imshow('Image', vis_img)
frame += 1
if save_out_video:
videoWriter.write(vis_img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
if save_out_video:
videoWriter.release()
out_file = os.path.join(args.out_video_root,
os.path.basename(args.video_path)).replace(
'.mp4', '-bottom.npy')
np.save(out_file, poses)
cv2.destroyAllWindows()
