关于使用自己的训练集发生的错误

[huidemie]

作者您好，我在训练的时候用了自己的数据集，然后程序报了下面这样的错。我找了很久但还是不知道问题出在哪里，不知您是否可以回答，谢谢。

Traceback (most recent call last):
File "D:/PycharmProjects/github/main.py", line 83, in
train(data)
File "D:/PycharmProjects/github/main.py", line 38, in train
loss = model.neg_log_likelihood_loss(*model_input)
File "D:\PycharmProjects\github\model\model.py", line 17, in neg_log_likelihood_loss
outs = self.lstm.get_output_score(*args)
File "D:\PycharmProjects\github\model\model.py", line 55, in get_output_score
lstm_out = self.get_lstm_features(*args)
File "D:\PycharmProjects\github\model\model.py", line 45, in get_lstm_features
pos_lstm_out = self.posBiLSTM.get_lstm_features(tag_inputs, seq_lengths)
File "D:\PycharmProjects\github\model\model.py", line 80, in get_lstm_features
pos_embs = self.pos_embeddings(pos_inputs)
File "H:\Anaconda3\envs\pytorch_cpu\lib\site-packages\torch\nn\modules\module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "H:\Anaconda3\envs\pytorch_cpu\lib\site-packages\torch\nn\modules\sparse.py", line 114, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "H:\Anaconda3\envs\pytorch_cpu\lib\site-packages\torch\nn\functional.py", line 1467, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: index out of range: Tried to access index 46 out of table with 15 rows. at C:\w\1\s\windows\pytorch\aten\src\TH/generic/THTensorEvenMoreMath.cpp:237

[huidemie]

作者您好，我已经找到了错误的地方，应该是您的代码有一点小错误，但是在提供的三个标准数据集上刚好没有触发这个错误。具体是在model.py第75行左右，这个地方
self.pos_embeddings = init_embedding(data.tag_alphabet.size(), self.pos_emb_dim)
您应该是误写成了
self.pos_embeddings = init_embedding(data.dict_alphabet.size(), self.pos_emb_dim)
请您确认一下是不是写错了