BERT_TF

produced by Andysin Zhang

Many years ago the great British explorer George Mallory, who was to die on Mount Everest, was asked why did he want to climb it. He said, "Because it is there." Well, space is there, and we're going to climb it, and the moon and the planets are there, and new hopes for knowledge and peace are there. And, therefore, as we set sail we ask God's blessing on the most hazardous and dangerous and greatest adventure on which man has ever embarked. ------President John F. Kennedy

This package will be the foundation on which our platform would be based on, it will be very difficult, however, DO NOT LET THE FAILURE DEFINE US, LET FAILURE TEACH US !

Requirements

Run example

python pre_train.py

Log

Need to ameliorate:

1.When do predict, the maximum length should be identical to the training steps, need to fix this;
2.add start, end tag to the data;

TODO:

1.finish evalutaion metrics; 2.save model as pb in order to deploy on the server; 3. write the interface for serving input;

TODO: <1>data utils; ~~<2>fully train procedure; <3>fine tune tasks;~~

Reference