Jerry.Shi
Jerry.Shi
The error message means you does not have enough candidate responses ,your response number should >= 10
我跑的结果貌似很差，验证码生成为5个字符，34000 step 准确率能到0.96，但这个仅仅是训练准确率，然而进行测试时，准确率很低，感觉严重过拟合，
@roccolocko Have you solved this problem?
@ypwhs Thank you for project and your reply, Got it !
笔记版本，4.11.19 插件版本：v2.7 切换为插件Edit渲染，重启后笔记显示空白，但是编辑状态能看到内容
same issue, details as bellow: Creating 3 layers of 256 units. Traceback (most recent call last): File "D:/github/easy_seq2seq/easy_seq2seq/execute.py", line 310, in train() File "D:/github/easy_seq2seq/easy_seq2seq/execute.py", line 133, in train model =...
我遇到translate提示，“java.util.NoSuchElementException”，应该就是你所说的问题。
@molyswu I found you had run it with python2 but this project was developed with python3, you should make some changes that it can be run with python2
@OYE93 This is OOV( out of vocabulary ) problem, and there are some methods to solve it like average , firtstly use the 'UNK' to replace the word which is...
Use jieba tokenizer to get the location of each character in tokens, location is one feature in this module, #12