Tensors and Dynamic neural networks in Python with strong GPU acceleration

A toolkit for developing and comparing reinforcement learning algorithms.

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

A Deep Learning based project for colorizing and restoring old images (and video!)

Python Implementation of Reinforcement Learning: An Introduction

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Pytorch implementation of convolutional neural network visualization techniques

A faster pytorch implementation of faster r-cnn

Code release for ConvNeXt model

A PyTorch Implementation of Single Shot MultiBox Detector

PyTorch deep learning projects made easy.

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

NVIDIA's Deep Imagination Team's PyTorch Library

StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

computer vision and sports

Robotics Toolbox for Python

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

pip install antialiased-cnns to improve stability and accuracy

Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.

A large-scale benchmark and learning environment.

Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.

Finding the genre of a song with Deep Learning

(CVPR 2021 Oral) Open World Object Detection

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

Python toolbox for optimization on Riemannian manifolds with support for automatic differentiation

Helper functions to create COCO datasets

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning