Deep Learning Series in Python: 5-6

In above article from 1 to 4, I use the package Theano to do some code, article 5 use the package numpy to do example code, article 6 use the package keras to make model.

Deep learning has many excited applications.

Let’s look at them.

Computer Vision Task

Object Detection : faster R-CNN

Art in Computer Vision

Deep Dream

In this case we simply feed the network an arbitrary image or photo and let the network analyze the picture. We then pick a layer and ask the network to enhance whatever it detected.

This creates a feedback loop: if a cloud looks a little bit like a bird, the network will make it look more like a bird.

This in turn will make the network recognize the bird even more strongly on the next pass and so forth, until a highly detailed bird appears, seemingly out of nowhere.

This just like a scene in the movie modern time, a man whose job is to screw the screw, he worked hour by hour, day by day, someday, he is a little crazy, whatever he see, he see a screw.

https://github.com/google/deepdream