GPU needed? ImportError: libcudart.so.10.1

[rcknowles04]

Hi, I have been trying to set up a virtual environment within WSL in order to do kinect point cloud to SMPL model fitting. I was able to get all the requirements installed in my environment and was able to setup the mesh repo and openpose repo within my environment as well. I was trying to test everything by running the "01_rendere_multiview.py" script, but am running into this error:

python utils/keypoints_3d_estimation/01_render_multiview.py ../data/mesh_1/scan.obj -t ../data/mesh_1/scan_tex.jpg -r ../data/mesh_1 Traceback (most recent call last): File "utils/keypoints_3d_estimation/01_render_multiview.py", line 17, in <module> from pytorch3d.renderer import ( File "/home/rcknowles04/miniconda3/envs/SMPL_Fit/lib/python3.7/site-packages/pytorch3d/renderer/__init__.py", line 3, in <module> from .blending import ( File "/home/rcknowles04/miniconda3/envs/SMPL_Fit/lib/python3.7/site-packages/pytorch3d/renderer/blending.py", line 9, in <module> from pytorch3d import _C ImportError: libcudart.so.10.1: cannot open shared object file: No such file or directory

I tried to setup everything on CPU, which has worked up until this point, but now this import related to pytorch3d seems GPU-dependent, so do you know if it is possible to run these scripts only on CPU or do you need GPU?

I have a GPU in my computer, but because of my windows version, I am unable to access it within WSL.

Any help would be greatly appreciated!