PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
OpenMMLab Text Detection, Recognition and Understanding Toolbox
PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.
A unified and open cross-framework evaluation library
:octocat: Generate a slug just like GitHub does for markdown headings.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
PyTorch extensions for high performance and large scale training.
Some out-of-the-box hooks for pre-commit
OpenMMLab Image Classification Toolbox and Benchmark
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"
OpenMMLab FewShot Learning Toolbox and Benchmark
Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
OpenMMLab Computer Vision Foundation
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Object detection. EfficientDet-D5 level COCO AP in 20 epochs. SOTA single-stage detector on Waymo Open Dataset.
OpenMMLab Pose Estimation Toolbox and Benchmark.
Object detection on multiple datasets with an automatically learned unified label space.