I was training on my own dataset. The backbone was yolov3-tiny.
I added cutmix=1 on the [net] layer, but after I run the command
./darknet detector train ...
The training process just stopped after the sentence
Done! Loaded xx layers from weights-file
was printed on the screen.
No error
If I remove the command cutmix=1, the trainig process can run normally.
I checked the gpu and the memory is sufficient.
I wonder if I didn't edit the .cfg file correctly :(
I was training on my own dataset. The backbone was yolov3-tiny. I added cutmix=1 on the [net] layer, but after I run the command
./darknet detector train ...
The training process just stopped after the sentenceDone! Loaded xx layers from weights-file
was printed on the screen. No error If I remove the command cutmix=1, the trainig process can run normally. I checked the gpu and the memory is sufficient. I wonder if I didn't edit the .cfg file correctly :(