document-level-classification

document-level-classification copied to clipboard

I can not find these there txt file (cnews.train.txt, cnews.val.txt, cnews.test.txt) in the downloading dataset. Are they created by yourself?

zhaobinNF

Help

9

您好，请问在运行xlnet_hierarchical_attn模型时出现TypeError: linear(): argument 'input' (position 1) must be Tensor, not str怎么解决？

wwhss

训练问题

4

请问为什么我训练自己的数据集时会卡在这一步很久，没有开始训练。sample_batch: 4 torch.Size([256, 600]) torch.Size([256, 600]) torch.Size([256, 600]) torch.int64 torch.Size([256]) torch.int64。到这就不输出了

teorzhang

截断问题

1

作者你好，在bert+Overlap tokenizer.batch_encode_plus报错，貌似pad=True？ ValueError: Unable to create tensor, you should probably activate truncation and/or padding with 'padding=True' 'truncation=True' to have batched tensors with the same length. python-BaseException

chengturbo