New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I cannot get good loss with yolov4-mish compared with yolov4. #7131
Comments
Training goes well. |
@AlexeyAB |
|
I understood why I can't get better mAP. I will use YOLOv4x-mish when I want to train 640x640 - 832x832 images, and YOLOv4 when the training data is low enough resolution like 416px. I've received enough answers so I close this issue. |
|
I tried yolov4x-mish, but could not get good results.
I use my own data to learn and my losses do not go down from around 20. With YOLOv4, the loss is below 1 at about 5000 iterations, and good detection accuracy can be obtained. I use the same training data and the same PC environment when training with yolov4 and yolov4x-mish.
Why is it that yolov4x-mish is less accurate than yolov4? Am I doing something wrong?
Can anyone give me some ideas?
This is a chart of training my data with yolov4-mish.
classes=1
,filters=18
yolov4x-mish.cfg
bad.list
andbad_label.list
.The text was updated successfully, but these errors were encountered: