laomao0
laomao0
我也遇到了这个问题,不知道是不是torch版本的问题
PSNR = 25.523451, SSIM = 0.781016 Bad Bad Bad
u can find more information about NIE in middlebury dataset. http://vision.middlebury.edu/stereo/data/
If you do not want to build CUDA programs. We provide the CUPY version of those packages. The cupy files do not need to be built. please refer to: https://github.com/laomao0/cupy_packages
If you do not want to build CUDA programs. We provide the CUPY version of those packages. The cupy files do not need to be built. please refer to: https://github.com/laomao0/cupy_packages
If you do not want to build CUDA programs. We provide the CUPY version of those packages. The cupy files do not need to be built. please refer to: https://github.com/laomao0/cupy_packages
The figure is wrong.
If you do not want to build CUDA programs. We provide the CUPY version of those packages. The cupy files do not need to be built. please refer to: https://github.com/laomao0/cupy_packages
I think you do not load the trained weights correctly.
> I think you do not load the trained weights correctly. check render_utils.py --> print('LOADING SF MODEL!!!!')