May I know the command line parameter when running LSTM_weight_tying(dim:100)

kwonmha / Improving-RNN-recommendation-model

Applied weight tying technique to RNN based recommendation model. Implemented with Tensorflow and Keras.

53 stars 13 forks source link

Open shwangdev opened 5 years ago

shwangdev commented 5 years ago

May I know the command line parameter when running LSTM_weight_tying(dim:100)

kwonmha commented 5 years ago

Just add --tying and set --r_emb, --r_l with same size. Sorry for bad README lol.

shwangdev commented 5 years ago

And what is your value for --r_emb and --r_l? dim 100?

kwonmha commented 5 years ago

Depends on the dataset but 100 worked best on MovieLens 1M.

shwangdev commented 5 years ago

You did not change --max_length value?

kwonmha commented 5 years ago

I didn't