BigDong's repositories
mmdetection
OpenMMLab Detection Toolbox and Benchmark
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
mmocr
OpenMMLab Text Detection, Recognition and Understanding Toolbox
DiffusionDet
PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)
nanodet
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
detectron2
Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.
mmeval
A unified and open cross-framework evaluation library
github-slugger
:octocat: Generate a slug just like GitHub does for markdown headings.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
mm-pre-commit-hooks
open-mmlab pre-commit-hooks
openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
fairscale
PyTorch extensions for high performance and large scale training.
pre-commit-hooks
Some out-of-the-box hooks for pre-commit
mmclassification
OpenMMLab Image Classification Toolbox and Benchmark
mmtracking
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.
DINO
Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"
mmfewshot
OpenMMLab FewShot Learning Toolbox and Benchmark
GroupRCNN
Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
mmcv
OpenMMLab Computer Vision Foundation
bigdetection
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
OpenPCDet
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
UniverseNet
Object detection. EfficientDet-D5 level COCO AP in 20 epochs. SOTA single-stage detector on Waymo Open Dataset.
MegEngine
MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架
mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
UniDet
Object detection on multiple datasets with an automatically learned unified label space.