Ye Yuan

No problem! Fixed in commit: https://github.com/NVlabs/GLAMR/commit/f0602fde7b6f3e9c0fbf8624623ad7ba9ec99ea8

Hi, 1. GLAMR doesn't depend on HybrIK and is compatible with most SMPL-based pose estimation methods. 2. Yes, it is possible to pretrain with SMPL poses. Checkout here: https://github.com/NVlabs/GLAMR#motion-infiller

I didn't write anything to res_2d_images. Could it be that the package pyvista is not working on your computer? Could you try pyvista's example (https://docs.pyvista.org/examples/02-plot/gif.html?highlight=off_screen) and see whether it works?

make sure you are using pyvista==0.31.3. Also try to install these: ``` pip install -e 'git+https://github.com/mmatl/pyopengl.git#egg=pyopengl' ``` if this doesn't work, could you also try: ``` # mesa sudo apt...

Could you try not installing this package and see whether it works?

Hi, Could you try to use python >= 3.6 and install the dependencies in this file? https://github.com/Khrylx/RFC/blob/main/requirements.txt You might also want to try if you can train [RFC ](https://github.com/Khrylx/RFC/) instead...

Hi Sadegh, Are you running this command? ``` python motion_pred/eval.py --cfg h36m_nsamp10 --mode vis ``` I'm able to run it without error. This is my matplotlib version: ``` # Name...

Hi, I suggest changing that line to: ``` if world_ver is None or major_ver is None or minor_ver is None: ```