I met some troubles when using bert

yongzhuo / Keras-TextClassification

中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN

https://blog.csdn.net/rensihui

MIT License

1.78k stars 405 forks source link

I met some troubles when using bert #75

Closed Fino2020 closed 2 years ago

Fino2020 commented 2 years ago

AttributeError: 'tuple' object has no attribute 'layer'
when executing inbound_layers = nest.map_structure(lambda t: t._keras_history.layer, input_tensors)

yongzhuo commented 2 years ago

You'd better use the following package version. do not pip install keras-xlnet==0.16.0 tensorflow==1.14 keras==2.2.4 bert-keras==0.41.0