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

ResNeXt-101 pre-trained model & post-processing #6

Closed
JohannesTK opened this issue Apr 1, 2020 · 2 comments
Closed

ResNeXt-101 pre-trained model & post-processing #6

JohannesTK opened this issue Apr 1, 2020 · 2 comments

Comments

@JohannesTK
Copy link

Hi,

Thank you for such a well-written paper & open-sourcing your work! 🤗

  1. Do you also plan to open-source the pre-trained model with ResNeXt-101 backbone?

  2. In the paper it's stated

Here the post processing technique we adopt is BLR [7], which is done by finding optimal paths in the whole video and then re-score detection boxes in each path. Table 2 summarizes the results of state of-the-art methods with different post-processing techniques.

Is the score MEGA (ours) ResNeXt-101 85.4 combination of SeqNMS, Tube Rescoring, BLR or only BLR?

Thanks & stay healthy,
Johannes

@Scalsol
Copy link
Owner

Scalsol commented Apr 2, 2020

Thank you for your interest!

  1. Since we have changed our model structure so there is no ResNeXt weight available now (we haven't retrained it). So recently we will not release the ResNeXt-101 weight. They may be available someday :)
  2. We only use BLR.

@JohannesTK
Copy link
Author

Thanks for the reply!

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