lpips-j – Minimal JAX/Flax port of `lpips` supporting `vgg16`, with pre-trained weights stored in the 🤗 Hugging Face hub.
Project description
LPIPS-J
This is a minimal JAX/Flax port of lpips
, as implemented in:
Only the essential features have been implemented. Our motivation is to support VQGAN training for DALL•E Mini.
It currently supports the vgg16
backend, leveraging the implementation in flaxmodels
.
Pre-trained weights for the network and the linear layers are downloaded from the 🤗 Hugging Face hub.
Installation
- Install JAX for CUDA or TPU following the instructions at https://github.com/google/jax#installation.
- Install this package from the repository:
pip install --upgrade git+https://github.com/pcuenca/lpips-j.git
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
lpips-j-0.0.6.tar.gz
(7.2 kB
view hashes)