Muhammed Kocabas

Any updates @soeaver?

`scores` tensor holds the confidence scores for each detected keypoint. You can think of it as the confidence scores in object detection.

Hi @neherh, loading the weights directly isn't possible. When you change `nJoints` parameter, last conv layers' number of kernels become `nJoints` and it won't accept the weights with different size....

Hi @jiandandian2, We did not test our code on MacOS, so it is a bit difficult to figure out the problem. Windows users had a similar problem and a solution...

Thanks a lot for your PR @x0rzkov! Image is created successfully using it. However, when I try to run the demo using `python demo.py --vid_file sample_video.mp4 --output_folder output/`, it gives:...

It will be downloaded if you run `sh prepare_data.sh`. Here is the link: https://github.com/mkocabas/VIBE/blob/bf5cfb0c437c060b2ade3d56036ed0148cf96587/prepare_data.sh#L3 You can reproduce the same error by trying to `import cv2` inside the image.

@x0rzkov Now, EGL is missing: ``` bash-5.0# python demo.py --vid_file sample_video.mp4 --output_folder output/ Traceback (most recent call last): File "/opt/conda/lib/python3.7/site-packages/OpenGL/platform/egl.py", line 70, in EGL mode=ctypes.RTLD_GLOBAL File "/opt/conda/lib/python3.7/site-packages/OpenGL/platform/ctypesloader.py", line 45, in...

I am not sure, according to [this notebook](https://colab.research.google.com/drive/1rTLHk0qxh4dn8KNe-mCnN8HAWdd2_BEh) installing pyrender should be enough. You may give it a try.

During rendering final video, I got this error: ``` Traceback (most recent call last): File "demo.py", line 347, in main(args) File "demo.py", line 250, in main renderer = Renderer(resolution=(orig_width, orig_height),...

Sorry I closed it by my mistake. You can avoid memory error by running `sudo docker run -it --shm-size 8G vibe`