PyTorch package for the discrete VAE used for DALL·E.

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Count the MACs / FLOPs of your PyTorch model.

NVIDIA's Deep Imagination Team's PyTorch Library

3D ResNets for Action Recognition (CVPR 2018)

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

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

An open-source toolbox for action understanding based on PyTorch

PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.

An artificial intelligence platform for the StarCraft II with large-scale distributed training and grand-master agents.

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

北大选课网补退选阶段自动选课小工具

Decision Intelligence Platform for Autonomous Driving simulation.

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped, CVPR 2022

United Perception

[ ECCV 2020 Spotlight ] Pytorch implementation for "Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets"

3.41% and 17.11% error on CIFAR-10 and CIFAR-100

DI-engine docs (Chinese and English)

OpenDILab RL HPC OP Lib, including CUDA and Triton kernel

[CVPR 2021] Actor-Context-Actor Relation Network for Spatio-temporal Action Localization

General Vision Benchmark, GV-B, a project from OpenGVLab

Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]

Code for our nips19 paper: You Only Propagate Once: Accelerating Adversarial Training Via Maximal Principle

A Re-implementation of Fixed-update Initialization

Repository containing Pytorch code for EKFAC and K-FAC perconditioners.

Project page for our paper: Interpreting Adversarially Trained Convolutional Neural Networks

Code of the STAGE module for video action detection

MACER: MAximizing CErtified Radius (ICLR 2020)