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

Metrics calculation #2

Open
macsmy opened this issue Jul 30, 2021 · 1 comment
Open

Metrics calculation #2

macsmy opened this issue Jul 30, 2021 · 1 comment

Comments

@macsmy
Copy link

macsmy commented Jul 30, 2021

Hi,
What is the metrics calculation strategy for values you have provided in the paper?

  • image, gt resized to 512x512?
  • metrics calculation performed for 512x512 output, gt?
  • output, gt values between 0-1?

Thanks for the dataset!

@ZHKKKe
Copy link
Owner

ZHKKKe commented Aug 1, 2021

Hi, thanks for your attention.

for your questions:
Q1: image, gt resized to 512x512? metrics calculation performed for 512x512 output, gt?
Nope. The original image size is used when calculation metrics.
During training, we composite the image of size 512x512 as the input.
During validation, we resize the short side to 512 (with original width/height ratio) as the input. Then we upsample the predicted alpha matte to the original size and then calculate the metrics.

Q2: output, gt values between 0-1
Yep. All pixel values are between 0-1 during the metrics calculation.

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