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.

Sign up for GitHub

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

Jump to bottom

I trained SCUT-FBP5500 dataset by train_model.py, but the PC (Pearson correlation) mean = 0.18, #9

Open
octaviawfx opened this issue Nov 19, 2020 · 1 comment
Open

I trained SCUT-FBP5500 dataset by train_model.py, but the PC (Pearson correlation) mean = 0.18, #9

octaviawfx opened this issue Nov 19, 2020 · 1 comment

Comments

@octaviawfx
Copy link

I trained SCUT-FBP5500 dataset by train_model.py, but the "PC (Pearson correlation) mean" = 0.18, while "PC (Pearson correlation) " of your released weight file is 0.93. what's wrong?
@octaviawfx
Copy link
Author

I trained SCUT-FBP5500 dataset by train_model.py, but the "PC (Pearson correlation) mean" = 0.18, while "PC (Pearson correlation) " of your released weight file is 0.93. what's wrong?

I changed "model.layers[0].trainable = False" to "model.layers[0].trainable = True", and trained again, and the PC value is "0.87"

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@octaviawfx