Tensorflow implementation of "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention"
781
stars
351
forks
source link
How to replace the word_embedded layer in the model with a trained word 2vec (512 dimensions per word)? #60
Open
ThatNight opened 5 years ago
but![image](https://user-images.githubusercontent.com/49028624/61472458-0f298780-a9b7-11e9-956b-583a392d9a4a.png)
For help, I'd like to add a trained word 2vec to the model.