Skip to content
This repository has been archived by the owner on Dec 11, 2023. It is now read-only.

Cannot replicate English to Vietnamese - on python 2 and 3 #398

Closed
mohammedayub44 opened this issue Oct 3, 2018 · 3 comments
Closed

Cannot replicate English to Vietnamese - on python 2 and 3 #398

mohammedayub44 opened this issue Oct 3, 2018 · 3 comments

Comments

@mohammedayub44
Copy link

Hi,

Using the below configuration:
Python 2.7.15
Tensorflow: 1.10.0

Training Query:
python -m nmt.nmt --src=en --tgt=vi --hparams_path=/home/ubuntu/nmt/standard_hparams/iwslt15.json --vocab_prefix=/home/ubuntu/en_vi_dataset/vocab --train_prefix=/home/ubuntu/en_vi_dataset/train --dev_prefix=/home/ubuntu/en_vi_dataset/tst2012 --test_prefix=/home/ubuntu/en_vi_dataset/tst2013 --out_dir=/home/ubuntu/en_vi_dataset/models/attention_model27

Best Bleu score comes out to be: 1.5698. Not sure whats going wrong, hoping its not encoding as I used that files directly from the download.

Below file contains the Params and the Log for Python 2 run
run1_py_2.7.15.zip

Python 3 Run:
Python 3.6.5
Tensorflow: 1.10.0

Training Query:
python -m nmt.nmt --src=en --tgt=vi --hparams_path=/home/ubuntu/nmt/standard_hparams/iwslt15.json --vocab_prefix=/home/ubuntu/en_vi_dataset/vocab --train_prefix=/home/ubuntu/en_vi_dataset/train --dev_prefix=/home/ubuntu/en_vi_dataset/tst2012 --test_prefix=/home/ubuntu/en_vi_dataset/tst2013 --out_dir=/home/ubuntu/en_vi_dataset/models/attention_model

Best Bleu score comes out to be: 2.18338

Below file contains the Params and the Log for Python 3 run:
run2_py_3.6.5.zip

Appreciate any help.
Lopping some folks who have answered similar questions before.
@bastings @oahziur

Thanks !

Mohammed Ayub

@bastings
Copy link
Contributor

bastings commented Oct 3, 2018

Hi there,

I checked your python 3 logfile and hparams and the parameters that were used for training are quite a bit different from the original https://github.com/tensorflow/nmt/blob/master/nmt/standard_hparams/iwslt15.json

Are you specifying the configuration file correctly? It looks like your run did not use attention and only used 32 units.

@mohammedayub44
Copy link
Author

mohammedayub44 commented Oct 3, 2018

@bastings Thanks.
My bad, silly mistake, the path to the hparams file --hparams_path=/home/ubuntu/nmt/standard_hparams/iwslt15.json was incorrect, it should have been --hparams_path=/home/ubuntu/nmt/nmt/standard_hparams/iwslt15.json
Strangely, the train command did not throw an error but just used a default configuration. (not sure if this is a bug I guess its logged output some where but I did not see it).

I have made the changes and running it now. Will update you in sometime.

-Mohammed Ayub

@mohammedayub44
Copy link
Author

mohammedayub44 commented Oct 3, 2018

@bastings Thanks for you help.
Ran perfectly fine. Bleu score a little off on the test side, but that might generalize with more runs I'm guessing.
image

Mohammed Ayub

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants