-
Notifications
You must be signed in to change notification settings - Fork 1
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
Test error does not decrease #3
Comments
I looked into it and I belive the culprit was the line
|
Hmm or actually maybe that line should be there. The "state" is just the recurrent state, not the parameters. The real problem might be that the network never learns to get out of a "zero" initial state (because it only does so once in training - at the very beginning). |
Well, no time to look into it now, but yeah I think it's something to do with the way the state of the model is reset before the offline test. The full model state has two parts - (1) the weights and biases, and (2) the "online" recurrent activations. Only part (2) should be reset before the offline test (and set back again after). |
Hi Peter,
I set the
offline_test_mode='cold_test'
andn_test_steps=1000
. Then, I ran the demo_uoro_abnb.py.I notice that the training error (online recent error) decreases over time. However, the test error does not decrease. It is fixed at
Test: 1.73
.Have you noticed the same?
Does it suppose to work like this?
Thanks
The text was updated successfully, but these errors were encountered: