You want to map every possible image of size 64 x 64 to a binary category (cat or non-cat). Each image has 3 channels and each pixel in each channel can take an integer value between (and including) 0 and 255. Source: http://cs230.stanford.edu/files/cs230exam_win18.pdf
I would have assumed that each pixel value takes 8 bit times 64^2 pixels for each image times 3 for each channel PLUS 1 for the respective category in total: 8*64^2*3+1.
However, the correct solution is 256^{3×64×64}. What am I missing? Thanks in advance.