Question concerning visualising convent filters
PelFritz opened this issue · 2 comments
PelFritz commented
Hi @fchollet ,
I have a small question concerning the code in post processing of images to visualise convent filters. Somewhere in the code we scaled the image by 64 and shifted it by 128
image *= 64
image +=128
Is there a reason to choose 64 and 128 ?
MohammedHAlali commented
I'm assuming you're referring to Listing 9.11 on page 265, which is here:
PelFritz commented
Hi @MohammedHAlali ,
yes that. This function
def deprocess_image(image):
I wish to know why we scaled by 64 and shifted by 128