Junfa Liu

Results 17 comments of Junfa Liu

Please start the visdom service with the "python -m visdom.server" command before run head_detection_demo.py

Hi~ The 2D keypoints detected from CPN used in the article is from [VideoPose3D](https://github.com/facebookresearch/VideoPose3D). We also provide a [tutorial](https://github.com/fabro66/GAST-Net-3DPoseEstimation/blob/783310d0b26f9ff0b47e5036b7c6b864dfb120ef/INFERENCE_EN.md) on how to run our model on custom videos. In this...

Hi~ You can use up-sampling or down-sampling to reduce or increase the number of output joint points. Reference: Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks

Hi~ sorry for not reply promptly. If the joints are occluded, the coordinates of the keypoints obtained by the 2D detector will have a large deviation, which will seriously affect...

Get it. Thanks for the suggestions.

Hi~ I also met the same problem. Could you please tell me how to solve it. ``` te/utils.py", line 844, in assert_array_compare raise AssertionError(msg) AssertionError: Not equal to tolerance rtol=1e-05,...

Hi~ thanks for sharing your great work! However, I have met the same problem. Could you please tell me the reason?