Jamie Kiros

Hi Fréderic, The pre-trained model on the main page was trained by conditioning on the encoder output at each time step (namely, it used the "gru_cond_simple_layer"). In the training code...

How much memory do you have available? This model requires loading 2 large .npy files (utable and btable) both of which are > 2GB. These consist of almost 1 million...

I haven't done anything different yet. I'll update once I have, probably next week (I've got a paper deadline this week)

It seems that the latest version of Keras does not work with this code. I'll post a fix later.

Are you looking for a pre-trained decoder which decodes the encoded sentence (like an autoencoder?).

I only have one trained on the Romance part of the BookCorpus (that we used for the "neural-storyteller" project). I don't have one on the full BookCorpus though. You could...

As is, probably not :( One thing you can do is replace line 16 of generate.py with: `from lasagne.layers import Conv2DLayer as ConvLayer` This should allow you to import and...

We are working on adding Caffe as an additional option, which works fine on both GPU and CPU. This will be included shortly.