jax-resnet
Flax implementations and pretrained checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX.
What is jax-resnet?
JAX ResNet is a library providing Flax implementations and pretrained checkpoints for various ResNet architecture variants, including ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt. It solves the problem of accessing state-of-the-art computer vision models within the JAX ecosystem by offering modular, accurate implementations with verified pretrained weights converted from PyTorch.
Machine learning researchers and practitioners working with JAX/Flax who need pretrained computer vision models for image classification tasks or as backbones for transfer learning.
Developers choose JAX ResNet for its modular implementations, verified accuracy matching original PyTorch models, and comprehensive coverage of ResNet variants—all within the high-performance JAX framework.
Overview
Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).
Use Cases
Best For
- Image classification tasks using ResNet variants in JAX
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
