Too slow on backward computation of silhouettes about neural_renderer

[nkolot]

This depends on a lot of factors (i.e. mesh size, rendered image size, GPU model etc.). I don't know if there is a way to speed up significantly the backward computation time. Have you tried to run the original Chainer code released by the authors to see if there are any differences?

[Arthur151]

Yes, I have just tried the original Chainer code with human body mesh (about 7000s vertices, 13000 faces, renderer image size 256*256) , the speed is on the same level (more or less) with yours....

[nkolot]

I am closing this issue for now.

[ypflll]

@Arthur151 Hi, Do you render an smpl model? I get more than 200ms when rasterize a silhouette, with no back computation. I wonder if something wrong in my code...
faces = torch.from_numpy(faces).cuda()
faces = [None,:,:]
ver = torch.from_numpy(ver).cuda()
ver = ver[None,:,:]
faces = nr.vertices_to_faces(ver, faces)
silhouettes = nr.rasterize_silhouettes(faces, 256, True)

If I use rederer like this (change to c++): https://github.com/YadiraF/PRNet/blob/master/utils/render.py
It only takes several ms.
I wonder if I can speed this up.

[DragonZzzz]

@ypflll Have you solve this problem? I alse render the mesh very slowly.