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

Distance measure after training #120

Open
Dax009 opened this issue Feb 23, 2023 · 0 comments
Open

Distance measure after training #120

Dax009 opened this issue Feb 23, 2023 · 0 comments

Comments

@Dax009
Copy link

Dax009 commented Feb 23, 2023

Hi,

i have traiened the net how it's specified in https://github.com/richzhang/PerceptualSimilarity#d-using-the-dataset-to-train-the-metric

But, when i calculating distance with test_network.py and loading model /PerceptualSimilarity/lpips/weights/v0.1/alex.pth
the distance will be
Distances: (0.722, 0.138)

But, when i calculating distance with test_network.py and loading model that i have trained /checkpoints/alex_1/latest_net_.pth
the distance will be
Distances: (0.439, 0.088)

Shouldn't the distance be similar?

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