Oana Camburu

Hi, Sorry to hear this. I also had a 12GB GPU and it was filling the memory at the limit but didn't crash. Are you able to reproduce the results...

The architecture is very straightforward: the encoder is a BiLSTM, the decoder is an LSTM (of course, at training time you input the correct tokens and at test time you...

No worries, please reach out if you are unsure about any details in the architecture.

Hi vibhavagarwal5, Thanks a lot for doing this! I wouldn't be able to have a detailed look soon, but if you'd like to place it in another branch (something like...

Hi Nikul, I'm afraid you will need the previous versions. I'm sorry for the inconvenience. Best, Oana

Thanks for the answer, @rodgzilla, but that shouldn't be the main reason. Just to be able to tie the weights, we can use the sub-part of the embedding matrix that...

Will it be on PyPl soon? I was trying to adapt it but i'm still searching for some modules inside the code. shall i wait for it to go on...

OK, thanks! looking forward for when it's ready :)

Thanks, Seth-Park. In https://visualqa.org/download.html I can only see the versions of 2015 and 2017, and you mentioned the 2014 version in the repo. I could find some 2014 files here...