-
Notifications
You must be signed in to change notification settings - Fork 544
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
Loss always stays around 9.3 #7
Comments
I have the same issue,and I think many people have the same issue,maybe it is due to the setting of parameters |
You guys did't train MS-celeb, and use other dataset, right? |
@recordcode you mean its relate to the dataset? |
I set the learning rate is 0.06 ,loss start to converge , RGB picture as the input face, I don't use lmdb as input |
We update the repo to fix some bugs. The pipeline should be okay to run without modifications now. The SphereFace-20 model (described in the paper) is also released. |
The loss computed after margin_inner_product layer is always bigger than the normal inner_product layer. A small trick used in large margin softmax is to use traditional inner_product layer at testing. Sample prototxt:
Then you can observe the accuracy and loss at testing phase to check if the network is training normally. |
@happynear You are right. This trick was also mentioned in L-margin softmax. |
If there are still something wrong with your loss, you guys can reopen this issue or open a new one for further discussion. |
Loss always stays around 9.3, not down
I set the learning rate to 0.01 and 0.06, and loss didn't converge???
How does the training network need to be modified?????
How is the training parameter set?????
Hope to get your help!!thanks!!
@wdwen
The text was updated successfully, but these errors were encountered: