search

Guanghan / lighttrack

LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
MIT License
720 stars 142 forks source link

TypeError: Error converting shape to a TensorShape: int() argument must be a string, a bytes-like object or a number, not 'tuple' #11

Open zhangdengp opened 5 years ago

zhangdengp commented 5 years ago

I run python demo_video_mobile.py ,but got error 'TypeError: Error converting shape to a TensorShape: int() argument must be a string, a bytes-like object or a number, not 'tuple'.' tensorflow:1.12 python:3.6.8 pytorch:1.1.0

Guanghan commented 5 years ago

I cannot replicate this problem. If anyone knows how to solve this problem, please help this dude.

17702513221 commented 5 years ago

我将flag_nms设置为True后，运行时也出现这一问题。 File "demo_video_mobile.py", line 192, in light_track keypoints = inference_keypoints(pose_estimator, bbox_det_dict)[0]["keypoints"] File "demo_video_mobile.py", line 554, in inference_keypoints cls_dets, keep = apply_nms(cls_dets, nms_method, nms_thresh) File "demo_video_mobile.py", line 572, in apply_nms keep = np.where((cls_dets[:, 4] >= min_scores) & TypeError: list indices must be integers or slices, not tuple 请问这部分是用于推理具体动作是什么吗，我之前用openpose+st-gcn做过姿态检测，我看到您使用了st_gcn_networks请问怎样看到动作结果