Data structure for input using different dataset

[MRasyidUlwan]

Hello, I'm planning on using the UBFC-rPPG dataset on physnet method, can you explain what is required for using such method? and is it possible to use a dataset that only has bpm as GT and video?

[Oichii]

to use the code split video into separate frames then detect the face on each frame and crop it to a face rectangle.
Sequences should be organised as follows to use the dataloaders:
+--- Database
| +--- sequence1
| | +--- frame_001.png, frame_002.png, ....
| +--- sequence2
| +--- ...

Using the code with BPM data is possible, but physNet was designed to predict the PPG signal instead.