YuDeng

Hi, the pre-compiled binary file only works if you install tensorflow 1.12 via pip install and use cuda 9.0. If you install tensorflow via conda with other version of cudatoolkit,...

>  > I have tensorflow v=2.5.0, and cuda 9.0 > But still this error persists. Please let me know, what else can go wrong! Hi, I'm not sure if...

Hi, if you want to generate ears and necks, you need to use the full BFM09 face model. We excluded ear and neck region of original BFM09 to allow the...

Hi, could you check if the output .mat file contains reasonable results?

Hi, if you pass the first test (kernels:rasterize_triangles_impl_test), the library is ready to use. You can find rasterize_triangles_kernel.so following the instruction of our repository and run the demo code as...

Seems that you use the wrong version of tf_mesh_renderer. In our experiment, we use an older version of it. Maybe you can check the instruction in the readme to see...

Hi, for Windows environment, we disable the .mat output because it requires a rendering operator which can only be compiled on Linux. We have an upcoming pytorch version implementation which...

Yes, this is also what I expected. Then the implementation in this repo seems to be wrong.

Hi, I've met the same problem as yours. I follow the instruction in https://github.com/marian42/mesh_to_sdf/issues/8, and the problem is fixed. Hope it can help you, too.

Hi, if you are using a remote computer via SSH or some tools rely on Xserver, the OpenGL in the remote computer may not be able to run correctly. I...