-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
Performance on Resnet101 network #32
Comments
I think maybe resnet101 is difficult to train. This maybe helpful.
|
@chenyuntc Thanks, I also fixed the weights for top layers, but the result didn't improve. As you mentioned, it might be the reason of BN and biases. I'll have another try. |
Hi @chenyuntc, I've trained the model with:
And I restrictedly followed the way of training as I did in caffe, while it seems the performance cannot be improved. |
Actually, I only tried VGG16. |
I recently also want to implement resnet structure based on this project. And I found your @twtygqyy codes are very helpful to me. But I have a question about batch normalization. Why we need to fix batch normalization parameters here? |
@blateyang BN only work when batch_size>1 and only work well when batch_size>=16.You can see this paper https://arxiv.org/abs/2002.05712.However,@chenyuntc code only surport batch_size==1 |
Thanks for your reply!
stickOverCarrot <notifications@github.com> 于2020年10月17日周六 下午7:48写道:
… @blateyang <https://github.com/blateyang> BN only work when batch_size>1
and only work well when batch_size>=16.You can see this paper
***@***.*** code only surport
batch_size==1
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#32 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AGHYD4MAIDOBBVEXAMFTZETSLF77NANCNFSM4EZIVDVA>
.
|
Hi, I've implemented the resnet101 structure on the top of vgg16 network, while the mAP on VOC datasets could only reach 0.62 after 20 epochs.
Do you have any idea what the problem would be? You can find the code here. Thank you.
The text was updated successfully, but these errors were encountered: