Closed knoopx closed 2 years ago
I had the same problem while trying to use original code from Deep3DFaceRecon_pytorch.
RuntimeError: The size of tensor a (35709) must match the size of tensor b (53215) at non-singleton dimension 1
In the latest commit, I replaced the topology with full-face topology. Thus this problem should be fixed. Can you try again?
And please use my forked repo for Deep3DFaceRecon_pytorch
I believe this issue has now been solved. Please re-open if it is not.
Hello, I tried to capture the trimesh generated by
Operator#run
:and then export it using menpo3d io:
but the generated mesh is corrupt:
any idea why? is there a proper way to do so? tried using original code from Deep3DFaceRecon_pytorch and the mesh is ok but it fails to generate texture due tensor size missmatch.