sccn / sound2meg

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Comments on Dataset class

dungscout96 opened this issue · comments

Use transpose instead of reshape in

MEG_Signal = np.reshape(MEG_Signal, (-1, 273, 3600))

Number of segments per recording is custom to each recording, not fixed 147 samples

Turn to local variable:

return len(filename)*147