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

Huge difference between N.A., flipping and multiscale testing #976

Open
pikkuve opened this issue Apr 19, 2022 · 0 comments
Open

Huge difference between N.A., flipping and multiscale testing #976

pikkuve opened this issue Apr 19, 2022 · 0 comments

Comments

@pikkuve
Copy link

pikkuve commented Apr 19, 2022

I've been training on a relatively small dataset starting from COCO-pretrained weights (dataset specs: about 5k images, over 3 classes with approx. 4000, 3000 and 24000 bounding boxes per object class). I focused on object detection, and used a lr =0.0003125 for 140 epochs with reduction at steps 80, 100, 125 and the results for N.A. testing, flipping and multiscale testing are wildly different, with AP50 at about 0.30-0.40 for N.A. and 0.60-70 for flipping and around 0.8-0.9 for multiscale testing. Any idea where this could stem from? Similar setting on a comparable dataset has different behavior: with an improvement from N.A. to F. and M.S. but nothing too drastic.

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

1 participant