Some issues when using training and lm_gen

Separius / BERT-keras

Keras implementation of BERT with pre-trained weights

GNU General Public License v3.0

815 stars 197 forks source link

Some issues when using training and lm_gen #12

Closed DUTANGx closed 5 years ago

DUTANGx commented 5 years ago

Hi Separius,

Thank you and really nice work! I think in lm_dataset, the line 118 should be [0] * (len(sent.tokens) + 2) right? I fix this then the lm can run. Many thanks

Separius commented 5 years ago

Yeah, thanks man; I will change that in a moment