Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history 
the pretrained models zip files now contain a LICENSE.txt file as requested. replace the links to the pretrained model zip files.
  • Loading branch information
@abisee
abisee authored May 1, 2019
1 parent a7317f5 commit b29e986
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,8 @@ The test set output of the models described in the paper can be found [here](htt

## Looking for pretrained model?
A pretrained model is available here:
* [Version for Tensorflow 1.0](https://drive.google.com/file/d/0B7pQmm-OfDv7SHFadHR4RllfR1E/view?usp=sharing)
* [Version for Tensorflow 1.2.1](https://drive.google.com/file/d/0B7pQmm-OfDv7ZUhHZm9ZWEZidDg/view?usp=sharing)
* [Version for Tensorflow 1.0](https://drive.google.com/open?id=0B7pQmm-OfDv7SHFadHR4RllfR1E)
* [Version for Tensorflow 1.2.1](https://drive.google.com/open?id=0B7pQmm-OfDv7ZUhHZm9ZWEZidDg)

(The only difference between these two is the naming of some of the variables in the checkpoint. Tensorflow 1.0 uses `lstm_cell/biases` and `lstm_cell/weights` whereas Tensorflow 1.2.1 uses `lstm_cell/bias` and `lstm_cell/kernel`).

Expand Down

1 comment on commit b29e986

@tohidarehman1988
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Currently I am doing a project on abstractive text summarization with a pointer generator network.
using python 3.7.3
tensorflow version 1.14.0

But getting a problem "DuplicateFlagError: The flag 'data_path' is defined twice. First from run_summarization.py, Second from run_summarization.py. Description from first occurrence: Path expression to tf.Example datafiles. Can include wildcards to access multiple datafiles"

Can you please help me to resolve this issue.
It is very urgent.
please reply
image

Please sign in to comment.