CNN's training data about cnns-on-chb-mit HOT 3 CLOSED

In the training why did you choose that it be be for each patient apart I mean why didn't you collect the spectrograms for all patients and use it as input for CNN.

Because each patient has his characteristic so it's necessary a specific model for each patient.

How could I know the number of the training data used?

I'm not understanding the question, could you explain it better?

from cnns-on-chb-mit.

I mean the number of training samples(X-train) used as inputs to the CNN model. If I want to load these samples as well as Y-train how can I do that?
Thank You!

from cnns-on-chb-mit.

I mean the number of training samples(X-train) used as inputs to the CNN model

I don't know the actual number of training samples but it's possible to recover them from the following table.

For example patient 1 has 14.49 hours of interictal data. Each sample contain 30 seconds of data so 14.49 hours = 53340 seconds / 30seconds=1778 samples for interictal data. The preictal are almost the same number so in total for patient 1 almost 3500 sampled where used.
The training set was 75% of the total set of samples so I used almost 2625 samples for training.

If I want to load these samples as well as Y-train how can I do that?

You have to create the spectograms, here more information are provided.

from cnns-on-chb-mit.