bl6g6 Goto Github PK

awesome_lightweight_networks

The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，etc. ⭐⭐⭐⭐⭐

cvpr_2021_papers

CVPR2021最新论文汇总，主要包括：Transformer, NAS，模型压缩，模型评估，图像分类，检测，分割，跟踪，GAN，超分辨率，图像恢复，去雨，去雾，去模糊，去噪，重建等等

ece-143-group14

FINAL PROJECT

ece-143-project

This repo contains the code, data, and approach for the ECE 143 Project at UCSD

lite.ai.toolkit

Lite.AI.ToolKit 🚀🚀🌟: A lite C++ toolkit of awesome AI models(一个开箱即用的C++ AI工具箱，支持ONNXRuntime/NCNN/MNN/TNN), RobustVideoMatting🔥, YOLOX🔥, YOLOP🔥 etc. https://github.com/DefTruth/lite.ai.toolkit

mobile-yolov5-pruning-distillation

mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！

nanodet

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

nanodet_ir

ncnn-assets

slimyolov3

This page is for the SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications

yolov5-lite

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.9M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

yolov5_prune

yolov5 prune，Support V2, V3, V4 and V6 versions of yolov5