Basic concept for feature extraction, used in Convolutional Neural Netwrok

Create image with numpy

Loading output library...
Loading output library...

Perform Convolution Operation with kernel size-->3*3 and stride=1

If used convolve2d--->Note that the kernal has to be reversed. Otherwise usesignal.correlate2d.

Loading output library...

Perfrom pooling operation(in this case maxpool) with size--->2*2 and stride=2

Loading output library...

Make a single vector for futher processing

Loading output library...

Pass Vector to artificial neural network..... Thanks for Viewing this notebook. Hope this provide a basic concept for feature extraction, used in Convolutional Neural Network