Skip to content
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

进行yolov4稀疏化训练 #172

Open
mingwz opened this issue Jan 1, 2022 · 3 comments
Open

进行yolov4稀疏化训练 #172

mingwz opened this issue Jan 1, 2022 · 3 comments

Comments

@mingwz
Copy link

mingwz commented Jan 1, 2022

RTX 3090,ubuntu18.04服务器
-batch-size 4 -sr --s 0.0005

再进行darknet训练出来的yolov4上进行稀疏化训练时,总是会在某个epoch停住,之后显存占比会慢慢的上升。最开始占比为39%,如果你不主动停止程序,他会一直上升。

这是怎么一回事呢?

@mingwz
Copy link
Author

mingwz commented Jan 1, 2022

难道是我的数据的原因吗?

@wuyexingkong
Copy link

python train.py --cfg cfg\yolov4_digital.cfg --data data\digital.data --weights weights\yolov4_digital.weights --epochs 20 --batch-size 4 -sr --s 0.001 --prune 1

训练到第18个epochs报错内存不够,如下所示:
image
楼主你这个问题解决了吗?

@sticktotheend
Copy link

@wuyexingkong 您好,请问使用yolov4/yolov4-tiny,需要修改哪些部分呢?我刚接触这方面的学习,希望您不吝赐教。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants