Traceback (most recent call last):
File "C:/Users/Administrator/Desktop/bert_crf/train.py", line 191, in
model.fit(train_dataloader, epochs=20, steps_per_epoch=None, callbacks=[evaluator])
File "D:\python36\lib\site-packages\bert4torch\models.py", line 213, in fit
output, loss, loss_detail = self.train_step(train_X, train_y, grad_accumulation_steps)
File "D:\python36\lib\site-packages\bert4torch\models.py", line 131, in train_step
loss_detail = self.criterion(output, train_y)
File "D:\python36\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "C:/Users/Administrator/Desktop/bert_crf/train.py", line 122, in forward
return model.crf.neg_log_likelihood_loss(*outputs, labels)
File "D:\python36\lib\site-packages\bert4torch\layers.py", line 913, in neg_log_likelihood_loss
forward_score, scores = self._forward_alg(feats, mask)
File "D:\python36\lib\site-packages\bert4torch\layers.py", line 862, in _forward_alg
masked_cur_partition = cur_partition.masked_select(mask_idx) # [x * tag_size]
测试运行的脚本是ner任务：
/Tongjilibo/bert4torch/blob/master/examples/sequence_labeling/task_sequence_labeling_ner_crf.py 运行环境 windows10 pycharm 最新版本0.1.6的bert4torch torch==1.10
已经自我修复了 ，不知道是不是只有我自己的问题 还是说所有的都是这样的
已经自我修复了 ，不知道是不是只有我自己的问题 还是说所有的都是这样的
你是用的pip版本吗？pip上的0.1.6版本当时配合的task_sequence_labeling_ner_crf.py也是attention_mask转为bool类型的，后续我在CRF内部自己转bool()类型了，你可以用git上的最新代码试下，应该就没刚刚的问题了
是的用 pip install bert4torch 进行安装
bert4torch copied to clipboard
Tongjilibo
