Closed Dylan-H-Wang closed 1 year ago
Hi @Dylan-H-Wang,
Not a bug, this has more to do with the EfficientPhys-C implementation utilized having its own normalization module that ultimately calculates difference frames. Check out the two lines here which I believe are relevant.
Not sure if there is some confusion of terminology here, but the reason we use DiffNormalized
as you pointed out is because the data type is DiffNormalized
, whether it's set to that explicitly for pre-processing as an input or it eventually becomes that through a module such as the one mentioned in my first answer above. The 1st derivative of the PPG signal is being predicted.
The output of the models are effectively the 1st derivative of the PPG signal. Check out this section in the README for visualizing the outputs. This should also give you an idea on how to use the .pkl
files mentioned for your own code. You can also consider saving the predicted and ground truth signals just before they're used for HR calculations here.
Hope this helps.
Thank you for the answer. Problem is solved and close.
Hi,
I am trying to understand the logic behind label_type preprocessing:
Standardized
but the label type is set toDiffNormalized
. Is that possibly a bug, since I saw the original paper was usingDiffNormalized
inputs?DiffNormalized
instead ofRaw
orStandardized
. Does is mean asking the model to predict the difference of rPPG is more helpful than directly predicting actual rPPG signals?Thank you!