-
Notifications
You must be signed in to change notification settings - Fork 126
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
some questions about rnn #2
Comments
Hi, Regarding your first question: Second question: Third one: I hope this helps ! |
Thanks for reply!
I want to confirm some details. |
Hi,
|
Thanks for your reply. In rnn-base.py, your code made input not in form of one-hot encoding. It was like [[23], [35], [57]...]. And the target is like [[60]]. In this case, how does the Theano.categorical_crossentropy calculate error? Does it do automatically same as if the input, target are encoded in one-hot? And I couldn't get sps and others like your paper. I got sps 30% for ml1m dataset, 37% for netflix dataset, which are 3%p lower than those on your paper. What exact model of rnn is used? Thanks. |
Hi, Thanks. |
Hi, Sorry for the late reply. If you want to use multiple targets you have to use the hinge loss, but it is harder to train. Concerning the results that you get, did you tune properly the learning rate and used early stopping to avoid overfitting ? Cheers, |
Hi, It would help me a lot if you upload models you trained. Btw, what do you mean, it's harder to train with hinge loss? Thanks |
Yes it tends to take more time with the hinge loss. |
Hi, And what was the min_user_activity and item popularity set for preprocessing? |
Hi, I tried to add the data and the models to the repo using git lfs, but I couldn't make it work so far. |
Hi, the data you uploaded was greatly helpful. |
Hi, Indeed I used max_length = 30 on movielens as well. The parameters of the models where tuned on a validation set using a random parameter search. We kept the parameters that optimised the sps@10. |
Oh, thanks for answering right away. |
You can find the precise datasets and the training/validation/test splits that we used here: iridia.ulb.ac.be/~rdevooght/rnn_cf_data.zip |
Hi, I've just read your recent paper and got a question. |
Well, I'm training rnn-cce model for RSC15 data. |
hello.
I read your paper and am looking into your codes.
And got some questions about rnn.
in rnn_one_hot.py : _prepare_networks()
at your code :
if not self.use_movies_features:
l_recurrent = self.recurrent_layer(self.l_in, self.l_mask, true_input_size = self.n_items + self.n_optional_features(), only_return_final=True)
there's NOT in if condition.
why did you set true_input_size like above when use_movies_features is false?
self.recurrent_layer() calls __ call __() of recurrent_layers.py
It seems that it only returns 1 layer - prev_layer, though you write for loop in that part.
I think it returns multiple layers when RecurrentLayers.layers is set like 100-50-50 like your example
Does it work as you intended?
what does l_last_slice do?
Should it exist?
TY for your help.
The text was updated successfully, but these errors were encountered: