Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

初学者求lstm+cnn/tensorflow代码?|New beginner for "lstm+cnn/tensorflow" #3

Open
WaveLi123 opened this issue Sep 27, 2016 · 8 comments

Comments

@WaveLi123
Copy link

No description provided.

@pcgreat
Copy link

pcgreat commented Jul 12, 2017

这是我试着写的,希望能帮到你https://github.com/pcgreat/insuranceQA-cnn-lstm/tree/master/lstm_cnn/tensorflow

@chenzhi1992
Copy link

tf版本的lstm+cnn的代码,怎么还是cnn的代码啊?@ pcgreat

@pcgreat
Copy link

pcgreat commented Jul 21, 2017

@chenzhi1992 抱歉,上传代码的时候弄错了,现在更正了

@chenzhi1992
Copy link

chenzhi1992 commented Jul 21, 2017 via email

@chenzhi1992
Copy link

你的lstm+cnn 大概训练多少step后loss收敛?我训练到1000step,acc一直在0.1到0.2之间.@pcgreat
@ pcgreat

@pcgreat
Copy link

pcgreat commented Jul 24, 2017 via email

@zifengwen
Copy link

cnn/tensorflow/insqa_cnn 中:
with tf.name_scope("accuracy"):
self.correct = tf.equal(zero, self.losses)
self.accuracy = tf.reduce_mean(tf.cast(self.correct, "float"), name="accuracy")
这几行不足以评估模型的好坏吧,只是统计训练数据中“一个正确答案跟一个错误答案”选对正确答案的比例。。

@zifengwen
Copy link

cnn/tensorflow/insqa_train 中,模型评估的方法dev_step()中,实际上只评估了20条数据吧。
为什么不是直接所有答案的向量计算出来,,然后对于新的问题,计算向量,匹配所有答案向量,得到最佳答案,跟真实的答案比较得到准确率呢??
现在这样写有什么好处??

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants