Hi,1) I am in the process of testing a trained and validated CNN with images 
from ILSVRC2012. 2) My question is the following: What is the img_mean.npy file 
and what is reason for subtracting the img_mean (shape = 3L, 256L, 256L) when 
loading the images?  3) Interestingly, I obtain quite different results related 
to the top-5 probabilities, whether I subtract the mean or not in the loading 
process, e.g., when I use a .hkl file (shape = 3L, 256L, 256L, 256L) containing 
256 images. 4) For each new (single) image that I load and test, do I need to 
generate and subtract a img_mean? Any comments that you may offer would be 
helpful.Best,Arnold

-- 

--- 
You received this message because you are subscribed to the Google Groups 
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to