Open shushanxingzhe opened 1 year ago
@youngLBW Sorry to bother you, I hope you can give me a feedback at your convenience time. Very thanks.
Hi, Sorry to bring you the inconvenient experience. we will consider to re-implement the code using only one rendering engine (nvdiffrast or pytorch3d). Before that, if you meet some problems about the environment, you may use the docker images provided by ModelScope (https://www.modelscope.cn/docs/%E7%8E%AF%E5%A2%83%E5%AE%89%E8%A3%85), which provide a complete environment for HRN.
Very thanks for your reply. I have tried to use the docker image, but there are no luck. My problem is that I have no GPU in the environment where I want to use your model. So I want to use pytorch3d to replace nvdiffrast. I will wait your update.
Thank you for your great work! I also find it difficult to replace nvdiffrast with pytorch3D. I know this is a bit forward, could you please fix the render_uv_texture and pred_texture functions for those of us who are inexperienced in the 3D face reconstruction?
Thanks your great work. Could you replace nvdiffrast with pytorch3d or something else in util/nv_diffrast.py. There are some buddy have try to replace it for Deep3DFaceRecon_pytorch in https://github.com/ryanhe312/Deep3DFaceRecon_pytorch, but your version nv_diffrast.py just been more complicated for me since it used dr.texture function in nvdiffrast. Would you please give me some advice or just add a new feature to choose pytorch3d or nvdiffrast in some way. Very very thanks.