[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

Convert scikit-learn models and pipelines to ONNX

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

High-quality 3D head model dataset.

Programmer's guide about how to cook at home.

[ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention

A library created to revitalize C++ as a machine learning front end. Per aspera ad astra.

🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~

OpenCompatible provides a standard compatible training benchmark, covering practical training scenarios.

技术面试最后反问面试官的话

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

PyTorch implementation of AnimeGANv2

Pre-trained word vectors of 30+ languages

A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Fast C++ logging library.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"

Code release for ConvNeXt model

Toward Spatially Unbiased Generative Models (ICCV 2021)

CT-Net, OpenPose, LIP_JPPNet, DensePose running with ncnn⚡服装迁移/虚拟试穿⚡ClothingTransfer/Virtual-Try-On⚡

PyTorch implementation of adversarial attacks [torchattacks]

Official Pytorch implementation of the paper "Action-Conditioned 3D Human Motion Synthesis with Transformer VAE", ICCV 2021

[ICCV 2021]Code for the the bias loss and evaluation of SkipblockNet model on ImageNet validation set