Not running with TF 2 about multi-label-text-classification-using-bert HOT 3 OPEN

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

from multi-label-text-classification-using-bert.

Any plans of making work with TF2?

from multi-label-text-classification-using-bert.

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

from multi-label-text-classification-using-bert.