lucas-maes / nano-simsiam
Minimalistic, hackable PyTorch implementation of SimSiam in ~400 lines. Achieves good performance on ImageNet with ResNet50. Features distributed training, real-time KNN eval, and AMP. Perfect for research prototyping.
☆19Updated 4 months ago
Alternatives and similar repositories for nano-simsiam:
Users that are interested in nano-simsiam are comparing it to the libraries listed below
- ☆30Updated 4 months ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- ☆31Updated 11 months ago
- A selection of neural network models ported from torchvision for JAX & Flax.☆44Updated 4 years ago
- Graph neural networks in JAX.☆67Updated 9 months ago
- Implementation of Denoising Diffusion Probabilistic Models (DDPM) in JAX and Flax.☆20Updated last year
- ☆52Updated 6 months ago
- Jax/Flax rewrite of Karpathy's nanoGPT☆57Updated 2 years ago
- The Energy Transformer block, in JAX☆56Updated last year
- ☆60Updated 3 years ago
- Code for A General Recipe for Likelihood-free Bayesian Optimization, ICML 2022☆44Updated 2 years ago
- Lightning-like training API for JAX with Flax☆38Updated 4 months ago
- Implementation of PSGD optimizer in JAX☆30Updated 3 months ago
- A JAX implementation of stochastic addition.☆14Updated 2 years ago
- ☆17Updated 7 months ago
- A simple library for scaling up JAX programs☆134Updated 5 months ago
- GPT implementation in Flax☆18Updated 3 years ago
- An implementation of the Llama architecture, to instruct and delight☆21Updated 2 months ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- Lightweight Cluster/Cloud VM Job Management 🚀☆41Updated 7 months ago
- Running Jax in PyTorch Lightning☆93Updated 3 months ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆30Updated 3 months ago
- Pytorch-like dataloaders for JAX.☆80Updated 5 months ago
- Building blocks for productive research☆51Updated 2 months ago
- Open source code for EigenGame.☆30Updated last year
- Euclidean Wasserstein-2 optimal transportation☆47Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆32Updated last year
- ☆24Updated 6 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆83Updated last year
- Code for "Meta Learning Backpropagation And Improving It" @ NeurIPS 2021 https://arxiv.org/abs/2012.14905☆31Updated 3 years ago