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
B model does not converge. #36
Comments
As far as I am concerned, the loss is incorrect. The training loss is about 9.2~9.3 at the beginning for CASIA-WebFace dataset. |
Yeah, i trained my network, what you are saying is correct. |
// train_val.prototxt
// solver
|
It seems that the training data preparation is incorrect. |
Besides, the training batch size is too small which could lead to the slow convergence for the CNN. |
Yes, data augmentation is not important to whether net converge or not but to accuracy. You are right, small batch size tends to lead diverge, but i havn't way to increase because i am using 1G GPU. |
Too small batch size may be influenced for my network because the non-linear activation function is more complex than ReLU. I set the batch size about 30~100 and the network can be converged. I am sorry that I am on business now, therefore I don't have GPU to check your network configuration. |
Thanks Alfred. |
I solved my problem. |
|
BTW, the MSRA paper [1] analyzes the disadvantages of gaussian initialization. [1]. He, K., Zhang, X., Ren, S. and Sun, J., 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1026-1034). |
Thank you. |
@cheer37 I'm having the same issue. The value of loss 87.33 and it doesn't converge. The change of the filter from Gaussian to Xavier doesn't make a difference. Could you or @AlfredXiangWu share the train_val.proto as well as the solver.proto with me? Thanks |
@afshindn |
@cheer37 |
@cheer37 |
I am trying to train with lightened_B model in CASIA.
I followed the training methodology in paper, But it does not converge.
At beginning, accuracy is 0, and loss is 87.3365.
What's the problem?
I am using caffe-windows-master of happynear(Feng Wang).
Thanks.
The text was updated successfully, but these errors were encountered: