alias-free-torch 0.0.3

alias free torch

Alias-Free-Torch

Simple torch module implementation of Alias-Free GAN.

This repository including

• Alias-Free GAN style lowpass sinc filter @filter.py

• Alias-Free GAN style up/downsample @resample.py

• Alias-Free activation @act.py

• and test codes @./test

Note: Since this repository is unofficial, filter and upsample could be different with official implementation.

Note: 2d lowpass filter is applying sinc instead of jinc (first order Bessel function of the first kind) in paper

UPDATE: You can download alias-free-torch from pip

python -m pip install alias-free-torch

Requirements

Due to torch.kaiser_window and torch.i0 are implemeted after 1.7.0, our repository need torch>=1.7.0.

• Pytorch>=1.7.0

For custom torch users, pip will not check torch version.

TODO

• 2d sinc filter
• 2d resample
• devide 1d and 2d modules
• pip packaging
• rewrite upsample
• apply jinc(torch.special.i1) with updated torch
• provide loadable ckpt for lower version of torch
• documentation

Test results 1d

Filter sine	Filter noise

upsample	downsample

Test results 2d

Filter L1 norm sine	Filter noise

upsample	downsample

Activation

References

• Alias-Free GAN
• adefossez/julius
• A. V. Oppenheim and R. W. Schafer. Discrete-Time Signal Processing. Pearson, International Edition, 3rd edition, 2010

Acknowledgement

This work is done at MINDsLab Inc.

Thanks to teammates at MINDsLab Inc.

• Hyoungkyu Song
• Kang-wook Kim
• Dongho Choi
• Sang Hoon Woo