Skip to content
This repository was archived by the owner on Jul 7, 2023. It is now read-only.

Feature/new model for scalar regression. In the models/transformer.py, a model called Transformer Regressor was created. #1332

Conversation

kyoheikoyama
Copy link
Contributor

@kyoheikoyama kyoheikoyama commented Dec 29, 2018

In the models/transformer.py, a model called Transformer Regressor was created.

A new class called Transformer Regressor was created with the registry decoder in the models/transformer.py, in order to conduct a regression method such as sentiment analysis.

This is done by inheriting from Transformer Encoder and will be supposed to produce a real number as an output tensor with the shape of (N, 1,1,1) from input tensor.

@googlebot
Copy link

We found a Contributor License Agreement for you (the sender of this pull request), but were unable to find agreements for all the commit author(s) or Co-authors. If you authored these, maybe you used a different email address in the git commits than was used to sign the CLA (login here to double check)? If these were authored by someone else, then they will need to sign a CLA as well, and confirm that they're okay with these being contributed to Google.
In order to pass this check, please resolve this problem and have the pull request author add another comment and the bot will run again. If the bot doesn't comment, it means it doesn't think anything has changed.

@googlebot googlebot added the cla: no PR author has not signed CLA label Dec 29, 2018
@kyoheikoyama
Copy link
Contributor Author

I signed it again!

@googlebot
Copy link

CLAs look good, thanks!

@googlebot googlebot added cla: yes PR author has signed CLA and removed cla: no PR author has not signed CLA labels Dec 29, 2018
@kyoheikoyama kyoheikoyama changed the title Feature/new model for scalar regression. In the models/transformer.py, a model called Transformer Encoder was created. Feature/new model for scalar regression. In the models/transformer.py, a model called Transformer Regressor was created. Dec 29, 2018
@kyoheikoyama
Copy link
Contributor Author

Travis CI build is failed due to this #1319

ImportError while importing test module '/home/travis/build/tensorflow/tensor2tensor/tensor2tensor/rl/trainer_model_based_test.py'. Hint: make sure your test modules/packages have valid Python names. Traceback: ../../../virtualenv/python2.7.14/lib/python2.7/site-packages/six.py:709: in exec_ exec("""exec _code_ in _globs_, _locs_""") tensor2tensor/rl/trainer_model_based_test.py:21: in <module> from tensor2tensor.rl import trainer_model_based tensor2tensor/rl/trainer_model_based.py:42: in <module> from tensor2tensor.rl import rl_utils tensor2tensor/rl/rl_utils.py:27: in <module> from tensor2tensor.rl.dopamine_connector import DQNLearner tensor2tensor/rl/dopamine_connector.py:25: in <module> from dopamine.discrete_domains import run_experiment E ImportError: No module named discrete_domains

@afrozenator
Copy link
Contributor

Thanks @Kotober -- this is really good, thanks!

@afrozenator afrozenator merged commit 9f267c3 into tensorflow:master Jan 4, 2019
tensorflow-copybara pushed a commit that referenced this pull request Jan 4, 2019
PiperOrigin-RevId: 227913757
@kyoheikoyama
Copy link
Contributor Author

Thanks for merging :)

kpe pushed a commit to kpe/tensor2tensor that referenced this pull request Mar 2, 2019
…, a model called Transformer Regressor was created. (tensorflow#1332)

* A model called Transformer Encoder was created in the model.

* solved an inheriting issue.
kpe pushed a commit to kpe/tensor2tensor that referenced this pull request Mar 2, 2019
PiperOrigin-RevId: 227913757
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
cla: yes PR author has signed CLA
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants