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.
These code is highly readable and more brief than other frameworks such as pytorch and tensorflow!
But it does not contain various training data augmentation tricks!
Matlab R2020a or higher,the newer the better,no other dependencies!!!
Use train.m for training, detect.m and demo.mlx for inference testing