There are 0 repository under optax topic.
Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023
The purpose of this repo is to make it easy to get started with JAX, Flax, and Haiku. It contains my "Machine Learning with JAX" series of tutorials (YouTube videos and Jupyter Notebooks) as well as the content I found useful while learning about the JAX ecosystem.
Experiment with diffusion models that you can run on your local jupyter instances
Simple CIFAR10 ResNet example with JAX.
This is the official repository for the paper "Flora: Low-Rank Adapters Are Secretly Gradient Compressors".
An implementation of adan optimizer for optax
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.
JAX implementation of Classical and Quantum Algorithms for Orthogonal Neural Networks by (Kerenidis et al., 2021)
Direct port of TD3_BC to JAX using Haiku and optax.
Goal-conditioned reinforcement learning like 🔥
The (unofficial) vanilla version of WaveRNN
dm-haiku implementation of hyperbolic neural networks
Neural implicit digital elevation model
A helper library for training dm-haiku models.
Stochastic Weight Averaging (SWA) transforms for Optax with JAX
SQA scottish Science Baccalaureate of Christopher Rae. Improving the preformance of distributed data parallelism of low wifi bandwidths
A library which trains the Fermionic Neural Network to find the ground state wave functions of an atom or a molecule using neural network quantum states.
This repository contains some of the code I wrote for the assignments in DSA4212 - Optimisation for Large-Scale Data-Driven Inference.
An implementation of MNIST classification using LeNet-300-100 in JAX (using Haiku and Optax).
A reimplementation of Parallel DNN Training in JAX by Will Whitney using haiku and optax.