I am learning R-CNN with this slides. On slide 63 one warped image region is specified by 224x224 pixel. Is this just a random value or from where is the value coming from? I cannot see any correlation.
Slide
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.
Sign up to join this communityI am learning R-CNN with this slides. On slide 63 one warped image region is specified by 224x224 pixel. Is this just a random value or from where is the value coming from? I cannot see any correlation.
Slide
224x224 is just the chosen input size of the RCNN "head" network. It's chosen somewhat arbitrarily, although you don't want it to be so small that you lose too much information and can't recognize objects anymore, nor too big that you waste a lot of computation.