zeta7337

inversion result is not good ,but the sim is high.

5

 hello, i trained on e4e my own dataset and pretrained stylegan2 model,but the result looks totally different with source img,can you give me some suggestion.

running in cpu is ok,but when running the code in gpu c10 error happens at box_a.select(2, 0) = prediction.select(2, 0) - prediction.select(2, 2).div(2) in darknet.cpp.how can i fix it?

the rasterize_triangles in mesh_numpy is so slow,but the rasterize_triangles in mesh dosnt work

1

when i use c++ rasterize_triangles in mesh,error occurs,the File "mesh_core_cython.pyx", line 49, in mesh_core_cython.rasterize_triangles_core ValueError: Buffer has wrong number of dimensions (expected 2, got 3)

I want to train boundary with w_plus latent ,how can i generate w_plus?

Train custom dataset

1

hello I want to train sp-gan on my own point cloud data,what kind of dataset shoud I prepare?what is the data form of your h5 file?