This is more of a Python question I suppose but considering I have to forward the data into a Theano CNN, I think it's ultimately relevant here.
I have 14k train and 167k test images (vectors) of size 200*200 = 40k. I am trying to pickle this data, tried just the train initially - the process terminates without getting completed. Is this too much? Should i be doing some sort of resizing/dimensionality reduction before trying to train and test this? If so, any recommended methods? Also, my resultant image is the difference of two images (verification for face recognition), so if i apply some sort of dim reduction, should that be done before or after taking the difference? Any help would be appreciated! -- --- You received this message because you are subscribed to the Google Groups "theano-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to theano-users+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.