您好，请问您在运行原代码时有出现过这样的错误吗？

[yujh123]

log如下所示：

CuDNN: True
GPU available: True
Status: train
Seg: True
Train file: data/ResumeNER/train.char.bmes
Dev file: data/ResumeNER/dev.char.bmes
Test file: data/ResumeNER/test.char.bmes
Raw file: None
Char emb: data/gigaword_chn.all.a2b.uni.ite50.vec
Bichar emb: None
Gaz file: data/ctb.50d.vec
Model saved to: data/model/saved_model.lstmcrf.
Load gaz file:
gaz alphabet size: 9462
gaz alphabet size: 10095
gaz alphabet size: 10714
build word pretrain emb...
Embedding:
pretrain word:11327, prefect match:1884, case_match:0, oov:10, oov%:0.005277044854881266
build biword pretrain emb...
Embedding:
pretrain word:0, prefect match:0, case_match:0, oov:21407, oov%:0.999953288490284
build gaz pretrain emb...
Embedding:
pretrain word:704368, prefect match:10712, case_match:0, oov:1, oov%:9.333582228859437e-05
Training model...
DATA SUMMARY START:
Tag scheme: BMES
MAX SENTENCE LENGTH: 250
MAX WORD LENGTH: -1
Number normalized: True
Use bigram: False
Word alphabet size: 1895
Biword alphabet size: 21408
Char alphabet size: 1895
Gaz alphabet size: 10714
Label alphabet size: 29
Word embedding size: 50
Biword embedding size: 50
Char embedding size: 30
Gaz embedding size: 50
Norm word emb: True
Norm biword emb: True
Norm gaz emb: False
Norm gaz dropout: 0.5
Train instance number: 3821
Dev instance number: 463
Test instance number: 477
Raw instance number: 0
Hyperpara iteration: 100
Hyperpara batch size: 1
Hyperpara lr: 0.015
Hyperpara lr_decay: 0.05
Hyperpara HP_clip: 5.0
Hyperpara momentum: 0
Hyperpara hidden_dim: 200
Hyperpara dropout: 0.5
Hyperpara lstm_layer: 1
Hyperpara bilstm: True
Hyperpara GPU: True
Hyperpara use_gaz: True
Hyperpara fix gaz emb: False
Hyperpara use_char: False
DATA SUMMARY END.
Data setting saved to file: data/model/saved_model.lstmcrf..dset
build batched lstmcrf...
build batched bilstm...
build LatticeLSTM... forward , Fix emb: False gaz drop: 0.5
load pretrain word emb... (10714, 50)
E:\论文\问答系统\Lattice LSTM\LatticeLSTM\model\latticelstm.py:105: UserWarning: nn.init.orthogonal is now deprecated in favor of nn.init.orthogonal_.
init.orthogonal(self.weight_ih.data)
E:\论文\问答系统\Lattice LSTM\LatticeLSTM\model\latticelstm.py:106: UserWarning: nn.init.orthogonal is now deprecated in favor of nn.init.orthogonal_.
init.orthogonal(self.alpha_weight_ih.data)
E:\论文\问答系统\Lattice LSTM\LatticeLSTM\model\latticelstm.py:120: UserWarning: nn.init.constant is now deprecated in favor of nn.init.constant_.
init.constant(self.bias.data, val=0)
E:\论文\问答系统\Lattice LSTM\LatticeLSTM\model\latticelstm.py:121: UserWarning: nn.init.constant is now deprecated in favor of nn.init.constant_.
init.constant(self.alpha_bias.data, val=0)
E:\论文\问答系统\Lattice LSTM\LatticeLSTM\model\latticelstm.py:37: UserWarning: nn.init.orthogonal is now deprecated in favor of nn.init.orthogonal_.
init.orthogonal(self.weight_ih.data)
E:\论文\问答系统\Lattice LSTM\LatticeLSTM\model\latticelstm.py:44: UserWarning: nn.init.constant is now deprecated in favor of nn.init.constant_.
init.constant(self.bias.data, val=0)
build LatticeLSTM... backward , Fix emb: False gaz drop: 0.5
load pretrain word emb... (10714, 50)
build batched crf...
finished built model.
Epoch: 0/100
Learning rate is setted as: 0.015

Traceback (most recent call last):
File "E:/论文/LatticeLSTM/main.py", line 443, in
train(data, save_model_dir, seg)
File "E:/论文/LatticeLSTM/main.py", line 279, in train
instance, gpu)
File "E:/论文/LatticeLSTM/main.py", line 195, in batchify_with_label
mask[idx, :seqlen] = torch.Tensor([1]*seqlen)
TypeError: mul(): argument 'other' (position 1) must be Tensor, not list

[GabrielThompson]

好像是pytorch版本的问题 改成np.repeat([1],seqlen)就好了