CrossLee1
CrossLee1
How long did it take you to train only a single epoch?
@sunsq-blue I also met the same problem with you. Did you succeed to make it work using the above solutions? Thanks
@canqin001 when evaluating, how to process the GT images for evaluation? only resize each image to 256x256; or resize the shot edge of the image to 256 and center crop...
@busning sorry i still didn't figure it out. It seems Maya could achieve this process, but i am new to Maya and still learn it.
Thanks for your relpy. Sorry Im new for SMPL, it seems it needs .fbx file for MAYA. how to change .obj file to .fbx file
@shadow2496 do you succeed to reproduce the result.? I met the same problem with you ..
@rinongal one more question: in the enviroments_freeze.txt you provide above, transformers==4.3.1 but in https://github.com/rinongal/textual_inversion/blob/main/environment.yaml, transformers==4.18.0 which one is correct
> In fact, we also can get a decoder to reconstruct image pixels. But the aim is solely for visualization. Specially, we add an extra decoder to reconstruct pixels while...
@ZilinIB I also met this problem, seems not learn the style at all with enough steps. Have you solved this?
@asanakoy This is the result of step_150600. Is it in line with expectations？ 