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

May I ask if the weights in the folder 'weights' have been trained? The results I obtained seem to be inaccurate, is it because I didn't train and used them directly? #16

Open
jungyin opened this issue Oct 8, 2024 · 1 comment

Comments

@jungyin
Copy link

jungyin commented Oct 8, 2024

I tried using the weight file under weights to directly predict heart rate, but the results were not stable. So, I tried following the method in the readme and checked the RPPG signal using the test set. I found a huge difference between the RPPG signal and the label. Is this difference because the model I am using has not been trained?
image
image
image
image

@KegangWangCCNU
Copy link
Owner

I need some details to determine whether you have correctly loaded the pre-trained weights. If possible, you could try testing on the PURE or UBFC-rPPG datasets, as the model usually performs well on these datasets. If you would like more suggestions, you could post your code for loading the weights and conducting the tests.

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