Skip to content
This repository has been archived by the owner on Jan 15, 2024. It is now read-only.

Update model description #55

Merged
merged 4 commits into from
Apr 22, 2018
Merged

Conversation

cgraywang
Copy link
Contributor

Description

  1. update model description with reference to paper
  2. add table and numbers of the pretrained model to the page

Checklist

Essentials

  • Changes are complete (i.e. I finished coding on this PR)
  • All changes have test coverage
  • Code is well-documented

Changes

  • Feature1, tests, (and when applicable, API doc)
  • Feature2, tests, (and when applicable, API doc)

Comments

  • If this change is a backward incompatible change, why must this change be made.
  • Interesting edge cases to note here

@cgraywang cgraywang requested a review from szha as a code owner April 21, 2018 23:13
@cgraywang
Copy link
Contributor Author

Please help to resolve this issue: #56

@szha @leezu @sxjscience

@mli
Copy link
Member

mli commented Apr 22, 2018

Job PR-55/4 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-55/4/index.html


Use the following command to run the AWDRNN language model setting
All the language models are trained with this script: :download:`this example script <word_language_model.py>`.
Copy link
Member

Choose a reason for hiding this comment

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

Link is broken. <language_model/word_language_model.py>



+----------------+-----------------------------+----------------------------+----------------------------------+---------------------------------+-------------------------------+
| Model | awd_lstm_lm_1150_wikitext-2 | awd_lstm_lm_600_wikitext-2 | standard_lstm_lm_1500_wikitext-2 | standard_lstm_lm_650_wikitext-2 | standard_lstm_lm_200_wikitext | | ssd_512_vgg16_atrous_voc |
Copy link
Member

Choose a reason for hiding this comment

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


.. code-block:: bash

$ python word_language_model.py --gpus 0 --tied --save awd_lstm_lm_1150_wikitext-2 # Val PPL 73.32 Test PPL 69.74
Copy link
Member

Choose a reason for hiding this comment

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

You can put the performance along with [1] awd_lstm_lm_1150_wikitext-2, such as [1] awd_lstm_lm_1150_wikitext-2 (Val PPL 73.32 Test PPL 69.74):

@mli
Copy link
Member

mli commented Apr 22, 2018

Job PR-55/5 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-55/5/index.html


Use the following command to run the AWDRNN language model setting (emsize=400, nhid=1,150)
Merity, S., et al. "`Regularizing and optimizing LSTM language models <https://openreview.net/pdf?id=SyyGPP0TZ>`_". ICLR 2018
----------------------------------------------------------------------------------------------------------
Copy link
Member

Choose a reason for hiding this comment

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

use ~~~~~~~

@mli
Copy link
Member

mli commented Apr 22, 2018

Job PR-55/7 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-55/7/index.html

@szha szha merged commit 2df6f87 into dmlc:master Apr 22, 2018
cgraywang added a commit to cgraywang/gluon-nlp-1 that referenced this pull request May 2, 2018
* update model description with reference to paper, add table and numbers to clarity

* update table

* update table

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

Successfully merging this pull request may close these issues.

None yet

3 participants