repvgg topic

A treasure chest for visual classification and recognition powered by PaddlePaddle

PaddlePaddle

🍅🍅🍅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~

ppogg

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

fxmeng

项目注释+论文复现+算法竞赛+Pytorch实践

bobo0810

🚀🚀🚀 A collection of some awesome public YOLO object detection series projects.

codingonion

Object Classification Training Framework

ZJCV

SimpleAICV:pytorch training and testing examples.

zgcr

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

RangiLyu

A PaddlePaddle version image model zoo.

AgentMaker

RepVGG TensorRT int8 量化，实测推理不到1ms一帧！

Wulingtian