Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

PyTorch implementations of deep reinforcement learning algorithms and environments

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …

A Python framework for accelerated simulation, data generation and spatial computing.

Learning to See in the Dark. CVPR 2018

Model interpretability and understanding for PyTorch

A simple, fully convolutional model for real-time instance segmentation.

Image augmentation library in Python for machine learning.

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

A PyTorch Library for Accelerating 3D Deep Learning Research

Demo desktop apps built with Python & Qt. With examples for PyQt6, PySide6, PyQt5 & PySide2

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

Massively Parallel Deep Reinforcement Learning. 🔥

LPIPS metric. pip install lpips

Actions gestures on your touchpad using libinput

NVIDIA's Deep Imagination Team's PyTorch Library

A highly efficient implementation of Gaussian Processes in PyTorch

Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

Best practice and tips & tricks to write scientific papers in LaTeX, with figures generated in Python or Matlab.

StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

[CVPR2020] Adversarial Latent Autoencoders

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

A dark style sheet for QtWidgets application

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

An optimizer that trains as fast as Adam and as good as SGD.

View model summaries in PyTorch!