Question about Convolutional neural network.
- by Nhu Phuong
I readed few book and acticles about Convolutional neural network, it seem I understand the concept but I don't know how to put it up like in image below:
from 28x28 normalized pixel INPUT we get 4 feature map 24x24. but how to get them ? size the INPUT image ? or perform image transformation? but what kind of transformation? or cut up the input image to 4 piece 24x24 by 4 corner? I don't understand the process to me it seem they cut up or resize the image to more smaller at each step. please help thanks.