649453932 Bert-Chinese-Text-Classification-Pytorch issues

649453932 / Bert-Chinese-Text-Classification-Pytorch

使用Bert，ERNIE，进行中文文本分类

MIT License

4.03k stars 899 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

bert文本二分类测试集都分为了一类

#203 libo-go opened 2 days ago
0
构建自己的数据集

#202 cucude opened 2 months ago
0
构建自己的数据集

#201 cucude opened 2 months ago
0
RuntimeError: cublas runtime error : the GPU program failed to execute at C:/w/1/s/windows/pytorch/aten/src/THC/THCBlas.cu:450怎么解决呢

#200 yongbucai opened 2 months ago
0
hidden_size可以修改吗？

#199 whyseu opened 2 months ago
0
AttributeError: 'NoneType' object has no attribute 'tokenize'

#198 Cgetier520990 opened 3 months ago
3
vocab.txt生成

#197 zihao2018023 opened 3 months ago
0
vocab.txt生成

#196 zihao2018023 opened 3 months ago
0
添加 poetry 的 pyproject.toml 文件。支持了 apple mps GPU 加速训练。

#195 GuoDapeng opened 4 months ago
1
长文本

#194 TheNorthOne opened 5 months ago
0
词表txt文件

#193 zhangzhaoxia opened 6 months ago
2
求大佬解答，按照词分割，具体怎么改

#192 zgzis opened 6 months ago
1
小白想问下能否用这个代码训练Roberta模型

#191 uygnohil opened 7 months ago
1
能否通过调接口的方式来进行训练，每次启动都要训练好久

#190 Wwwwwzzzzbbbb opened 7 months ago
0
词表下载链接好像不太对，无法下载

#189 XiaoluJiayou opened 8 months ago
4
请问有人使用ernie在自己数据集上做训练的时候loss无法下降，准确率上不来嘛？同样的数据bert很正常

#188 lcneyc opened 10 months ago
0
请问在调用模型预测时出现这个报错是为什么？且预测的结果不太准，跟这个报错有关系吗

#187 zhangwenjie4426260 opened 10 months ago
0
我加载了微调之后的权重模型bert.ckpt用他来进行短文本预测但是每次运行文件时的预测结果都会变化且预测效果不好应该怎么解决呀？

#186 zhangwenjie4426260 closed 10 months ago
0
为什么预测的结果不太准呀？而且每预测一次，得到的分类结果不一样

#185 zhangwenjie4426260 opened 11 months ago
6
已经微调好的模型调用不了怎么办？只生成一个bert.ckpt文件

#184 zhangwenjie4426260 closed 11 months ago
0
模型准确率

#183 guocxian opened 11 months ago
1
OSError: Can't load the model for 'D:\Bert-Chinese-Text-Classification-Pytorch-master\THUCNews\saved_dicert.ckpt'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'D:\Bert-Chinese-Text-Classification-Pytorch-master\THUCNews\saved_dicert.ckpt' is the correct path to a di rectory containing a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.

#182 zhangwenjie4426260 opened 11 months ago
0
请问一下，模型跑出来的结果，只有准确率丢失率等等这些吗？具体的每个句子的用bert进行分类的标签，在哪里可以看到呀？

#181 zhangwenjie4426260 opened 11 months ago
7
字向量维度是768吗

#180 Josoope opened 11 months ago
0
python: can't open file 'D:\Bert-Chinese-Text-Classification-Pytorch-master\run.py': [Errno 2] No such file or directory

#179 zhangwenjie4426260 opened 11 months ago
0
训练的准确率过低

#178 Eachen11 opened 1 year ago
2
如何改繁體訓練

#177 arthurj58 opened 1 year ago
0
Question about masked language model

#176 paprika0741 opened 1 year ago
0
怎么测试自己的数据

#175 zhuizi1 opened 1 year ago
1
加载模型预训练权重报错

#174 Sunnycl opened 1 year ago
1
add ERNIE_DPCNN.py,change the old "pytorch_pretrained" into new "transformers", change self.bert_path into "bert-base-chinese" to fetch online models

#173 zcongfly opened 1 year ago
1
运行问题

#172 komixe opened 1 year ago
0
同样的代码和数据集，只是调通而已，为啥我的精度只有10%

#171 duolaOmeng closed 1 year ago
0
放在colab上的问题

#170 SuCao-university opened 1 year ago
1
报错：RuntimeError: Parent directory THUCNews/saved_dict does not exist

#169 nonoback1 closed 1 year ago
2
Oneflow

#168 ShawnXuan closed 1 year ago
0
二分类问题

#167 endgraduate opened 1 year ago
0
如果我的训练文本是一串数字，那数字之间需要空格空开吗，顺便文下每个文本的最大长度有限制吗

#166 upup01 opened 1 year ago
0
result

#165 dhl961123 opened 1 year ago
0
RuntimeError: CUDA error: device-side assert triggered

#164 blueyeee opened 1 year ago
0
请新增conda的requirement.txt环境配置文件

#163 allrobot opened 1 year ago
3
更换数据集后，precision_recall_fscore和混淆矩阵的值都是0

#162 longkf opened 1 year ago
1
bert训练时候用的2080ti是多大显存的呢

#161 namenotexist opened 1 year ago
0
模型分类概率结果在哪里可以看到呢？

#160 liyueyang165 closed 1 year ago
0
关于准确率，我训练了5000步后

#159 liangcaihua opened 1 year ago
1
大佬，请问依赖的安装包版本分别是什么？

#158 maqian765 opened 1 year ago
0
Test

#157 guodongxiaren closed 1 year ago
0
训练开始后进度条不动

#156 Yukimini opened 1 year ago
7
英文文本

#155 Qiwozuo opened 1 year ago
0
关于更换预训练模型的问题

#154 xjDUAN184 opened 1 year ago
0