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

If I understand your code correctly... #3

Closed
chengchu88 opened this issue Sep 19, 2019 · 2 comments
Closed

If I understand your code correctly... #3

chengchu88 opened this issue Sep 19, 2019 · 2 comments

Comments

@chengchu88
Copy link

Hello sir,

In the file 'auxiliaries.py', line 391:

sample_idxs = np.random.choice(np.arange(len(gallery_feature_matrix_all)), n_image_samples)

If I understand your code correctly, should 'gallery_feature_matrix_all' be 'query_feature_matrix_all'?

Thanks

@Confusezius
Copy link
Owner

Hi there!

You are right! Going by meaning and to avoid errors on datasets with similar layout that are not the In-Shop dataset, it should be len(query_feature_matrix_all). I will adjust this.

However as a sidenote: This does not change any previously computed results, the numerical results are computed correctly (just checked again), and the qualitative results are still showing the closest gallery images given a query image, its just the random selection of query images to visualize that could change.

Thanks for pointing that out :).

@chengchu88
Copy link
Author

chengchu88 commented Sep 20, 2019 via email

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