[BUG] BERT embedding - Githubissues

BrikerMan / Kashgari

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

http://kashgari.readthedocs.io/

Apache License 2.0

2.4k stars 441 forks source link

[BUG] BERT embedding #451

Closed ahmad-alismail closed 3 years ago

ahmad-alismail commented 3 years ago

Hello, I am trying to build a sequence labeling classifier as in tutorials, but I have the following problem with BERT embedding step:

Environment

Mac OS
Python Version: 3.6
Google-Colab

Other Comment

Did I make anything wrong in this step? Maybe it is stupid question but I am a little bit beginner. Thanks in Advance!

BrikerMan commented 3 years ago

You are using the legacy API with Kashgari V2 version. please check out the latest docs https://kashgari.readthedocs.io/