flaxmodels
GradCache
flaxmodels | GradCache | |
---|---|---|
1 | 1 | |
222 | 305 | |
- | - | |
3.1 | 4.5 | |
9 months ago | about 1 month ago | |
Python | Python | |
- | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
flaxmodels
-
[P] Training StyleGAN2 in Jax (FFHQ and Anime Faces)
a while ago I posted here regarding a repository containing some pretrained models implemented in Jax/Flax. I decided to add training code for these models. Here is the training code for StyleGAN2: https://github.com/matthias-wright/flaxmodels/tree/main/training/stylegan2
GradCache
-
[D] How to handle absurd batch sizes in SimCLR / OpenAI's CLIP?
Maybe you should try this thing: https://github.com/luyug/GradCache
What are some alternatives?
jax-resnet - Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).
h-former - H-Former is a VAE for generating in-between fonts (or combining fonts). Its encoder uses a Point net and transformer to compute a code vector of glyph. Its decoder is composed of multiple independent decoders which act on a code vector to reconstruct a point cloud representing a glpyh.
stylegan2-pytorch - Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch
jax-models - Unofficial JAX implementations of deep learning research papers
long-range-arena - Long Range Arena for Benchmarking Efficient Transformers
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
EasyLM - Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
ffhq-dataset - Flickr-Faces-HQ Dataset (FFHQ)
fortuna - A Library for Uncertainty Quantification.