Word embedding issue

[uqzhichen]

Hi Junwei, I'm wondering if you are willing to make the word embedding code of the dataset public?

[satyakrishnagorti]

Hi Simon, I am sorry we couldn't document this well. There is a script convert_flowers_to_hd5_script.py that converts the text of flowers data set to skipthought embeddings and a similar script for the birds data set. This script depends on package https://github.com/Cadene/skip-thoughts.torch/tree/master/pytorch. You can get the flower and bird dataset by following https://github.com/reedscot/icml2016

[uqzhichen]

Thank you so much Satya

[dany87kuo]

@uqzhichen Do you solve it? I have the same question right now.
Could you help me? Thanks!