We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
yolov4.weights 和 yolov4-tiny.weights 都不存在 conv_24 层, 下图的第二行代码报错,只存在concat24层而不是 conv_24 层
yolov4.weights
yolov4-tiny.weights
conv_24
concat24
后来我换成 yolov3-tiny.weights ,可以正常训练,不会报这个错,但是在训练过程中报 loss is nan,
yolov3-tiny.weights
The text was updated successfully, but these errors were encountered:
大佬求助
Sorry, something went wrong.
已经 解决,作者实现的代码是针对 yolov3 训练的,yolov4 要自己改,是替换 140,151,162 三个卷积层,但NaN问题依然没有解决
NaN问题依然没有解决,求助,尝试了降低学习率也不行,出现NaN 参数主要是,Prediction Feature 全是NaN
No branches or pull requests
yolov4.weights
和yolov4-tiny.weights
都不存在conv_24
层, 下图的第二行代码报错,只存在concat24
层而不是conv_24
层后来我换成
yolov3-tiny.weights
,可以正常训练,不会报这个错,但是在训练过程中报 loss is nan,The text was updated successfully, but these errors were encountered: