[CVPR 2022 Oral] PyTorch re-implementation for "MAXIM: Multi-Axis MLP for Image Processing", with *training code*. Official Jax repo: https://github.com/google-research/maxim
Why did I change the size from 260MB to 105MB after converting the pre training weight to torch weight? Is this normal? Is it because the Torch framework's volume optimization is done better?
Why did I change the size from 260MB to 105MB after converting the pre training weight to torch weight? Is this normal? Is it because the Torch framework's volume optimization is done better?