Back

Explore Courses Blog Tutorials Interview Questions
0 votes
2 views
in AI and Deep Learning by (50.2k points)

I am interested in a recent blog post by Google that describes the use of NN to make art.

I am particularly interested in one technique:

'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 is detected. Each layer of the network deals with features at a different level of abstraction, so the complexity of features we generate depends on which layer we choose to enhance. For example, lower layers tend to produce strokes or simple ornament-like patterns, because those layers are sensitive to basic features such as edges and their orientations.'

The post is http://googleresearch.blogspot.co.uk/2015/06/inceptionism-going-deeper-into-neural.html?m=1.

My question: the post describes this as a 'simple' case--is there an open-source implementation of an NN that could be used for this purpose in a relatively plug-and-play process? For just the technique described, does the network need to be trained?

No doubt for other techniques mentioned in the paper one needs a network already trained on a large number of images, but for the one, I've described is there already some kind of open-source network layer visualization package?

1 Answer

0 votes
by (108k points)

Yes, the network needs to be trained. Caffe is what they, and a lot of other people, use as a framework for getting started. This framework already contains the trained networks to play with. You want the "plug-and-play process", it's not so easy because, besides the framework, we need the code of the scripts they used and, probably, patch Caffe.

You can refer the following link for the algorithm for Deep Dream using TensorFlow:

https://hackernoon.com/deep-dream-with-tensorflow-a-practical-guide-to-build-your-first-deep-dream-experience-f91df601f479

Browse Categories

...