skip-thoughts

skip-thoughts copied to clipboard

I had to add "floatX=float32" to the THEANO_FLAGS in order to get the decoder trainer to work. It took me a minute to figure this out, and I've used Theano...

sudo-nim

Hi, from the nltk, I can find the file as following: czech.pickle* danish.pickle* dutch.pickle* english.pickle* estonian.pickle* finnish.pickle* french.pickle* german.pickle* greek.pickle* italian.pickle* norwegian.pickle* portuguese.pickle* README* slovene.pickle* spanish.pickle* swedish.pickle* turkish.pickle* can i...

wllps1988315

I have a bunch of text files, where some of the lines are empty. Now I've seen that, when trying to extract skip-thought vectors, It shuts down without extracting features...

kilickaya

I see that in the trainer function, you catch Nan value of cost, but you just print it out without deal with that. Shouldn't we do something in that occasion?

MilesQLi

#10

mayu-ot

Hi Ryan, I ran your code for image-sentence ranking. I suppose embedded image vectors are not normalized before computing loss. Is it correct? Mayu

mayu-ot

I built a simple encoder-decoder model using [dl4mt project](https://github.com/kyunghyuncho/dl4mt-material). The output model is _.npz_ and _.npz.pkl_ files. Is it possible to leverage this model in skip-thought experiments? Thank you for...

amirj

Github code (decoder GRU layer) different from paper

1

Hi, I'm stepping through the code and noticed that de GRU layer of the decoder doesn't take into account the context provided by the encoder. As stated in the paper,...

FredericGodin

You mentioned in the README that you're working on faster training of skip-thought vectors. Could you shed some light on that?

jli05

nhynes