Yolov6 trains its own data set

YOLOv6 It is a target detection framework developed by meituan visual intelligence department , Dedicated to industrial applications . This framework focuses on both detection accuracy and reasoning efficiency , In the dimension model commonly used in industry ：YOLOv6-nano stay COCO The upper precision can reach 35.0% AP, stay T4 The reasoning speed can reach 1242 FPS;YOLOv6-s stay COCO The upper precision can reach 43.1% AP, stay T4 The reasoning speed can reach 520 FPS. In terms of deployment ,YOLOv6 Support GPU（TensorRT）、CPU（OPENVINO）、ARM（MNN、TNN、NCNN） And so on , It greatly simplifies the adaptation work during project deployment .

This topic focuses on operation , Next, we will talk about how to use this yolov4 Algorithm to achieve their own data set training and detection .

Source code address ：

https://github.com/meituan/YOLOv6

The code structure

among ,

 ① assets The test image

 ② configs Configure interface functions

 ③ data Data related configuration files

 ④ deploy Model adapter , Can be pytorch The model is converted to ONNX And OpenVINO Platform model

 ⑤ docs documentation

 ⑥ runs The intermediate process has saved the final model path

 ⑦ tools It mainly includes training , test , Evaluate interface functions

 ⑧ yolov6 The Internet