运行问题 about pytorch_bert_bilstm_crf_ner HOT 6 CLOSED

作者您好 在用高版本torch运行您的代码时出现了和楼上一样的错误 在第89轮训练报错 ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (32,) + inhomogeneous part. 更换低版本后 并修改这句代码后attention_masks = torch.from_numpy(np.array(encode_dict['attention_mask'])).long().unsqueeze(0).to(device) 还是会出现 大佬可以指点一下吗 谢谢！

你predict里面代码是这样的吗：

try:
    attention_masks = torch.from_numpy(np.array(encode_dict['attention_mask'], dtype=np.uint8)).unsqueeze(0).to(device)
except Exception as e:
    attention_masks = torch.from_numpy(np.array(encode_dict['attention_mask'])).long().unsqueeze(0).to(device)

from pytorch_bert_bilstm_crf_ner.

作者您好，问题同上，更改你刚才给出的代码依然报错，请问哪里出问题了，烦请解答

from pytorch_bert_bilstm_crf_ner.

作者您好，问题同上，更改你刚才给出的代码依然报错，请问哪里出问题了，烦请解答

方便发下你的torch和transformers版本么

from pytorch_bert_bilstm_crf_ner.

作者您好，问题同上，更改你刚才给出的代码依然报错，请问哪里出问题了，烦请解答

改下这个试试：

token_ids = torch.from_numpy(np.array(encode_dict['input_ids'])).long().unsqueeze(0).to(device)

from pytorch_bert_bilstm_crf_ner.

谢谢大佬，好了！

from pytorch_bert_bilstm_crf_ner.

from pytorch_bert_bilstm_crf_ner.