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

How l2-normalization over feature is implemented ? #30

Closed
ZhuFengdaaa opened this issue Apr 25, 2018 · 2 comments
Closed

How l2-normalization over feature is implemented ? #30

ZhuFengdaaa opened this issue Apr 25, 2018 · 2 comments

Comments

@ZhuFengdaaa
Copy link

this paper states that L2 normalization of the image features is crucial for good performance. However, you just use pool5 data, which is average pooled to become a 2048 vector in generate_tsv.py

I'm wondering if you have implemented L2-normalization over feature or not. If you did, please inform me how you do it. Thanks a lot~

@cengzy14
Copy link

cengzy14 commented May 7, 2018

I guess the L2 normalization is done in the data loading part of the VQA model part, like https://github.com/asdf0982/vqa-mfb.pytorch/blob/d12291e5219ba29615a130829f520880dd69a211/mfh_coatt_glove/utils/data_provider.py#L254

@ZhuFengdaaa
Copy link
Author

ZhuFengdaaa commented May 25, 2018

Thanks. Yes, it does.

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

2 participants