lufferWang

@macanv 是这样的，运行bert_lstm_ner.py，已经按照readme，在代码中修改了data_dir、checkpoint_dir等路径： if os.name == 'nt': #windows path config bert_path = '{your BERT model path}' root_path = '{project path}' else: # linux path config bert_path = '{your BERT model path}'...

有知道为什么结果的loss很大，都是十几呢？正确率却挺高的。 - loss: 17.5805 - crf_viterbi_accuracy: 0.9911 - val_loss: 15.6539 - val_crf_viterbi_accuracy: 0.8773 - loss: 17.5799 - crf_viterbi_accuracy: 0.9915 - val_loss: 15.6227 - val_crf_viterbi_accuracy: 0.8833 - loss: 17.5801 - crf_viterbi_accuracy:...