repvgg topic
PaddleClas
A treasure chest for visual classification and recognition powered by PaddlePaddle
YOLOv5-Lite
🍅🍅🍅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~
RMNet
RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.
PytorchNetHub
项目注释+论文复现+算法竞赛+Pytorch实践
awesome-yolo-object-detection
🚀🚀🚀 A collection of some awesome public YOLO object detection series projects.
ZCls
Object Classification Training Framework
SimpleAICV_pytorch_training_examples
SimpleAICV:pytorch training and testing examples.
nanodet
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
Paddle-Image-Models
A PaddlePaddle version image model zoo.
RepVGG_TensorRT_int8
RepVGG TensorRT int8 量化,实测推理不到1ms一帧!