Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature request] To add the ability to use own data during the training a RNN network for translation by the translate.py script #748

Closed
b0noI opened this issue Dec 13, 2016 · 1 comment

Comments

@b0noI
Copy link

b0noI commented Dec 13, 2016

This is the copy of the original issue from: tensorflow/tensorflow#6071

Right now the script translate.py does not allow to use own data for training. At the moment it works only with the data, that the script downloads from the Internet (en/fr). Also there is not any documentation on the format of the input data that it expects in the input. In order to have the ability to train the model with own data 2 changes need to be made to the script:

  • to document the format of the input data;
  • enable the ability to pass an own input file path via the script arguments, the file path should be used for training instead of downloading the data from the internet.
@b0noI
Copy link
Author

b0noI commented Jan 15, 2017

fixed in #806

@b0noI b0noI closed this as completed Jan 15, 2017
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants