lpips-j 0.0.6

lpips-j – Minimal JAX/Flax port of `lpips` supporting `vgg16`, with pre-trained weights stored in the 🤗 Hugging Face hub.

LPIPS-J

This is a minimal JAX/Flax port of lpips, as implemented in:

• richzhang/PerceptualSimilarity
• Taming Transformers

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

1. Install JAX for CUDA or TPU following the instructions at https://github.com/google/jax#installation.
2. Install this package from the repository:

   pip install --upgrade git+https://github.com/pcuenca/lpips-j.git