Stars
The fastai book, published as Jupyter Notebooks
Deep reinforcement learning without experience replay, target networks, or batch updates.
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Object detection, 3D detection, and pose estimation using center point detection:
Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)
Infinite Photorealistic Worlds using Procedural Generation
TensorDict is a pytorch dedicated tensor container.
Official Implementation of SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation (CVPRW 2024)
Foundation Policies with Hilbert Representations (ICML 2024)
Extensible, parallel implementations of t-SNE
Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
Official Implementation of Rectified Flow (ICLR2023 Spotlight)
Implementation of rectified flow and some of its followup research / improvements in Pytorch
High-Resolution Image Synthesis with Latent Diffusion Models
Code to implement "Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation"
A collection of resources and papers on Diffusion Models
Simple single-file baselines for Q-Learning in pure-GPU setting