In case of 1D signal generally they tend to be around 1000s of sample points for each trial especially for biomedical signal. The time-frequency spectrum then can have shape like [256,1000] or [50,1000] etc. However most popular image classification CNN models tend to take input in the shape of [224,224] etc. In that case what is the proper procedure of resizing the time-frequency spectrum?
Asked
Active
Viewed 14 times
