TensorFlow——调用(bert模型）

import tensorflow as tf
from tensorflow.keras import backend as  K
import tensorflow_hub as hub
# A dependency of the preprocessing for BERT inputs
!pip install tensorflow_text
import tensorflow_text as text

bert_model_preprocess='https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/1'
# bert_preprocess_model = hub.load(bert_model_preprocess)
bert_preprocess_model=hub.KerasLayer(bert_model_preprocess)

text_test = ['this is such an amazing movie!']
text_preprocessed = bert_preprocess_model(text_test)
print(f'Keys       : {list(text_preprocessed.keys())}')
print(f'Shape      : {text_preprocessed["input_word_ids"].shape}')
print(f'Word Ids   : {text_preprocessed["input_word_ids"][0, :12]}')
print(f'Input Mask : {text_preprocessed["input_mask"][0, :12]}')
print(f'Type Ids   : {text_preprocessed["input_type_ids"][0, :12]}')

#调用方法1——生成词向量与句子向量
bert_model="https://hub.tensorflow.google.cn/google/experts/bert/wiki_books/mnli/2"
bert_model=hub.KerasLayer(bert_model)
bert_model(text_preprocessed)

#2
BERT_MODEL = "https://hub.tensorflow.google.cn/google/experts/bert/wiki_books/2" # @param {type: "string"} ["https://hub.tensorflow.google.cn/google/experts/bert/wiki_books/2", "https://hub.tensorflow.google.cn/google/experts/bert/wiki_books/mnli/2", "https://hub.tensorflow.google.cn/google/experts/bert/wiki_books/qnli/2", "https://hub.tensorflow.google.cn/google/experts/bert/wiki_books/qqp/2", "https://hub.tensorflow.google.cn/google/experts/bert/wiki_books/squad2/2", "https://hub.tensorflow.google.cn/google/experts/bert/wiki_books/sst2/2",  "https://hub.tensorflow.google.cn/google/experts/bert/pubmed/2", "https://tfhub.dev/google/experts/bert/pubmed/squad2/2"]
# Preprocessing must match the model, but all the above use the same.

# BERT_MODEL_HUB = "https://tfhub.dev/google/bert_uncased_L-12_H-768_A-12/1"
bert_model=hub.load(BERT_MODEL)
bert_results = bert_model(text_preprocessed)

print(f'Loaded BERT: {tfhub_handle_encoder}')
print(f'Pooled Outputs Shape:{bert_results["pooled_output"].shape}')
print(f'Pooled Outputs Values:{bert_results["pooled_output"][0, :12]}')
print(f'Sequence Outputs Shape:{bert_results["sequence_output"].shape}')
print(f'Sequence Outputs Values:{bert_results["sequence_output"][0, :12]}')