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

Not running with TF 2 #8

Open
jvence opened this issue Sep 26, 2019 · 3 comments
Open

Not running with TF 2 #8

jvence opened this issue Sep 26, 2019 · 3 comments

Comments

@jvence
Copy link

jvence commented Sep 26, 2019

Is this suppose to run with TF2? Tried running it in a virtual env on Mac with no success. Any help would be greatly appreciated.

@ghost
Copy link

ghost commented May 4, 2020

Nope, bert-tensorflow is build for tensorflow 1.x execution
For bert tf2 refer to https://github.com/kpe/bert-for-tf2

@jvence
Copy link
Author

jvence commented May 4, 2020

Any plans of making work with TF2?

@ghost
Copy link

ghost commented May 4, 2020

bert-tensorflow is based on https://github.com/google-research/bert, not compatible with tf2, if you want to implement bert in tensorflow 2, there are two ways

  1. Use the individual codes from google-bert and migrate it to tf2
    2.Use https://github.com/kpe/bert-for-tf2. This is based on google-bert implementation and made compatible for tf2. The code could be imported through pip install bert-for-tf2, an example for its implementation- https://www.kaggle.com/jugglingsnakeboarder/realornotnlp-bert-use-svm

I would suggest the use of bert-for-tf2, because its a Keras layer(It also utilizes kpe/params-flow to reduce common Keras boilerplate code ) implementation of the bert, a better utilization of tensorflow 2 potential

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

No branches or pull requests

1 participant