search

AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.58k stars 7.95k forks source link

Scaled-YOLOv4:training error when i set flag random=1 in my .cfg-file #7889

Closed only-zzx closed 3 years ago

only-zzx commented 3 years ago

I reand how to improve object detection and change random=1 in my .cfg-file then the error :Assertion "0"failed happend, i think this error about the networksize,during upsample anyone can help me about that?

* show such screenshot with info

2

企业微信截图_1

AlexeyAB commented 3 years ago

Yes, these models are not suitable for training with random=1, because it will require a lot of GPU-memory, and decreasing mini-batch size will reduce accuracy a lot.

only-zzx commented 3 years ago

Yes, these models are not suitable for training with random=1, because it will require a lot of GPU-memory, and decreasing mini-batch size will reduce accuracy a lot.

ok,thanks for your answer