赞
踩
参考:https://www.kexue.fm/archives/8373
https://github.com/bojone/CLUE-bert4keras(cluener.py)
bert4keras>=0.10.8
数据集下载:
https://github.com/CLUEbenchmark/CLUENER2020/files/6371700/cluener_public.zip
参考:https://github.com/CLUEbenchmark/CLUENER2020/issues/47
模型结构简单说明:
BERT+GlobalPointer
# 建立分词器
tokenizer = Tokenizer(dict_path, do_lower_case=True)
# 预训练模型
base = build_transformer_model(
config_path, checkpoint_path, application='unilm', return_keras_model=False
)
# 模型参数
last_layer = 'Transformer-%s-FeedForward-Norm' % (base.num_hidden_layers - 1)
# 构建模型
output = base.model.get_laye
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。