DongjunLee/conversation-tensorflow

Issues

• ValueError: Expected state to be a tuple of length 1, but received: Tensor("decoder/decoder/while/Identity_3:0", shape=(?, 1024), dtype=float32)

  #14 opened 4 years ago by JacomusP
  2

• 在你的代码中为什么直接去掉左边一个字符，这个有什么讲究

  #15 opened 6 years ago by zcqiand
  0

• Error when run in tensorflow 1.6+

  #12 opened 7 years ago by nguyenvulebinh
  2

• New error on train, possibly caused by beam-search-decoder bugfix

  #10 opened 7 years ago by lk251
  4

• Significant overfit on default hyperparameters on cornell-movie-dialogs config

  #11 opened 7 years ago by lk251
  2

• Error during training (following default usage described in the readme.md)

  #9 opened 7 years ago by lk251
  8

• chat issue

  #1 opened 7 years ago by abhishekkritarth
  2

• KeyError when training

  #7 opened 7 years ago by dianad96
  1

• Is it possible to use customer service conversation as data set with this model ?

  #5 opened 7 years ago by genz10
  7

• System configurations

  #6 opened 7 years ago by abhishekkritarth
  2

• adding stacked bidirectional

  #3 opened 7 years ago by junbeomlee
  1