convnetjs
convnetjs copied to clipboard
Question: Multiple outputs..
I would like to know how to design CNN(this modules) to handle multiple outputs instead of binary outputs. For example, I would like to retrieve relevant words (not a word) given an image. Any idea?
Thanks
@wfidditch cut each letter in image to separate image, then determine each separate letter and combine back to word
@wfidditch did you have in mind here generating matrix of classes as opposed to a binary vector?