basic know of deep learning

Notes from stanford CS231N online course.

I am labelling the image while listening to the online course.

stride, filiter, pad

input: 7x7

F:filter:3x3

stride:N 1

padding:k

OUTPUT=(7-F)/stride+1=(7-3)/1+1=5

IF padding=1;

output=(7-F+2*K)/stride+1=(7-3+2*1)/1+1=7

IF you want to go deeper, see https://adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks-Part-2/