-
Notifications
You must be signed in to change notification settings - Fork 153
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
deepFM issue with ml-1m dataset #4
Comments
i am not sure if you can receive this message, but i am on a travel to Melbourne now, unfortunately no wifi access. I have to check the code next weekend when i return China
发自我的 iPhone
在 2017年8月17日,02:23,xray1111 <notifications@github.com<mailto:notifications@github.com>> 写道:
Hi, I met with a strange problem while training deepFM model using ml-1m dataset: if enabling "is_use_fm_part" flag to True, the training process won't converge and the loss will become bigger and bigger. But if switching the flag off, just using dnn only, it seems ok. I only change the deepFM.py a little: For comparing the predicted rating with the GT value, I removed the softmax activation function for the last layer, and then output rmse error instead of auc.
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub<#4>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AHIYGOLgi0GWA0FB8vyw8x1Xthsq_MFmks5sYxdmgaJpZM4O5KLj>.
|
@xray1111 hey I am back now. Have you resolved the problem? |
@Leavingseason Sorry for late response, that problem may caused by a wrong when calcuating RMSE, I changed the code then it's fine. Thanks! |
Hi @xray1111 , could you share the code to run the deepFM with ml-1m dataset. I am a unclear on how to create the values. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi, I met with a strange problem while training deepFM model using ml-1m dataset: if enabling "is_use_fm_part" flag to True, the training process won't converge and the rmse value will become bigger and bigger(and the loss does decrease!). But if switching the flag off, just using dnn only, it seems ok. I only change the deepFM.py a little: For comparing the predicted rating with the GT value, I removed the softmax activation function for the last layer, and then output rmse error instead of auc.
The text was updated successfully, but these errors were encountered: