yolov3-yolov4-matlab icon indicating copy to clipboard operation
yolov3-yolov4-matlab copied to clipboard

Import and export Darknet™ models within MATLAB deep learning networks.

This repo has been deprecated. Please see MATLAB Deep Learning Model Hub, which includes an implementation of YOLOV3/V4.

RUNOOB 图标
RUNOOB 图标
RUNOOB 图标

yoloV3/yolov4 matlab

This respository uses simplified and minimal code to reproduce the yolov3 / yolov4 detection networks and darknet classification networks. The highlights are as follows:

  • Support original version of darknet model
  • Support training, inference, import and export of "* .cfg", "* .weights" models
  • Support the latest yolov3, yolov4 models
  • Support darknet classification model
  • Support all kinds of indicators such as feature map size calculation, flops calculation and so on.

本库代码比pytorch和tensorflow等其他框架更具可读性和精简性!
These code is highly readable and more brief than other frameworks such as pytorch and tensorflow!
但是不包含各种训练数据增强tricks!
But it does not contain various training data augmentation tricks!

Requirements

Matlab R2020a or higher,the newer the better,no other dependencies!!!

How to use

训练使用train.m,推理测试使用detect.m,demo.mlx
百度网盘yolov3/4,weights文件 提取码:dbbo