schlampig / opennre_for_chinese Goto Github PK

您好，我使用了自己的中文数据集，运行learn.py出现了如下错误：
Calculated padded input size per channel: (122 x 110). Kernel size: (3 x 210). Kernel size can't be greater than actual input size
请问这个问题怎么解决呢？

运行gen_embed_mat.py脚本生成的与训练数据有关的词向量（word_dictionary_nre.json）只能生成英文和数字的，中文的词一个都没有。还有一个问题就是生成json数据时，中文总是乱码。

Traceback (most recent call last):
File "./learn.py", line 42, in
is_training=True)
File "./learn.py", line 29, in learn
con.train()
File "/home/xiachao/workspace/OpenNRE_for_Chinese-master/config.py", line 251, in train
loss = self.train_one_step()
File "/home/xiachao/workspace/OpenNRE_for_Chinese-master/config.py", line 224, in train_one_step
self.acc_not_NA.add(prediction == self.batch_label[i])
TypeError: eq() received an invalid combination of arguments - got (numpy.int64), but expected one of:

• (Tensor other)
  didn't match because some of the arguments have invalid types: (numpy.int64)
• (Number other)
  didn't match because some of the arguments have invalid types: (numpy.int64)

How to solve this problem？