YOLO ModelCompression MultidatasetTraining
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程！！！😆🚀
Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏
This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO
该仓库用于记录和定期提供各大数据科学竞赛的赛事消息和原创baseline，思路分享以及博主的一些竞赛心得和学习资料等. 主要涵盖：kaggle, 阿里天池，华为云大赛校园赛，百度aistudio，和鲸社区，datafountain等
mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！
model compression and deploy. compression: 1、quantization: quantization-aware-training, 16/8/4/2-bit(dorefa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、ternary/binary value(twn/bnn/xnor-net); post-training-quantization, 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization folding for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.
