search

AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.72k stars 7.96k forks source link

How do calculate map with my own dataset? #1795

Open ASPL-pod opened 6 years ago

ASPL-pod commented 6 years ago

Hello, I'm training my own dataset with yolo_mark. After I stop training 100,000 iterations, is there any solutions to continue training after 100,000 iteraions?

AlexeyAB commented 6 years ago

@ASPL-pod Hi,

Yes, just use this command to continue training: ./darknet.exe detector train data/obj.data yolo-obj.cfg backup/yolo-obj_2000.weights

https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects

After each 100 iterations you can stop and later start training from this point. For example, after 2000 iterations you can stop training, and later just copy yolo-obj_2000.weights from build\darknet\x64\backup\ to build\darknet\x64\ and start training using: darknet.exe detector train data/obj.data yolo-obj.cfg yolo-obj_2000.weights