訓練 Model
摘要
In this section, you will train your model locally using TensorFlow.
Note: This lab adapts and extends the official TensorFlow BERT text classification tutorial to utilize Vertex AI services.
See the tutorial for additional coverage on fine-tuning BERT models using TensorFlow.
Build and compile a TensorFlow BERT sentiment classifier
- Fill out the
#TODOsection to add ahub.KerasLayerfor BERT text preprocessing. - Fill out the
#TODOsection to add ahub.KerasLayerfor BERT text encoding. - Fill out the
#TODOsection to save your BERT sentiment classifier locally.
You should save it to the./bert-sentiment-classifier-localdirectory.
實作
1. Fill out the #TODO section to add a hub.KerasLayer for BERT text preprocessing.
※ 這邊要搜尋 # TODO 而不是 #TODO 否則會找不到正確位置 (我這邊是找 TODO)
參照
