search

DeepsMoseli / Bidirectiona-LSTM-for-text-summarization-

A bidirectional encoder-decoder LSTM neural network is trained for text summarization on the cnn/dailymail dataset. (MIT808 project)
MIT License
81 stars 36 forks source link

cnn_daily_load.py #1

Closed sanjayb678 closed 6 years ago

sanjayb678 commented 6 years ago
  1. local variables 'filenames' referenced before assignment in cnn_daily_load.py
  2. Also, should the location be pointing to questions folder like below: CNN_data="C:\Users\moseli\Documents\Masters of Information technology\Masters project\text mining\data\new CNN\cnn\questions"
DeepsMoseli commented 6 years ago

Hi @sanjayb678 ,

thanks

on 1) , that shouldnt be the case as all function definitions are before their calls and 'filenames' is assigned for the first time on line 97, then used on line 100

on 2) the version of the data i use isn't split is questions & answers folders. they are all in one folder named to sit one after the other like below image

let me know if this makes sense

sanjayb678 commented 6 years ago

Thanks. Sorted this out. Got access to the correct data