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

关于bilistm提取特征再reverse? #1

Open
sheirving opened this issue Aug 13, 2018 · 3 comments
Open

关于bilistm提取特征再reverse? #1

sheirving opened this issue Aug 13, 2018 · 3 comments

Comments

@sheirving
Copy link

您好!想问下在共享卷积层提取特征后,采用BiLstm将特征序列化,水平和垂直特征分别再reverse出不同方向的特征,有个疑问是BiLstm本身具有双向性,bw为fw的reverse,这里的再reverse是否有些多余?谢谢!

@dabenzhong-wang
Copy link

个人理解,是为了得到ABC和CBA两种输出,解决对180°翻转图片的识别。

@MnmohanSinghThakur
Copy link

Please share how to create_tfrecord & supply input image fro demo.py? Also, these files are missing '/share/zhui/mnt/demo_20.tfrecord' from input_data.py

Anybody solved this issue?

@gzhcv
Copy link

gzhcv commented Mar 14, 2019

@sheirving bilstm与特征reverse不是一回事。bilstm是考虑了上文和下文的信息,最重要的还是利用当前帧的(设为t)Input信息x_t来做预测;而特征reverse后,当前帧的Input信息其实来自于x_t和x_{L-t}(设特征序列长度为L)。

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