htoyryla
commented
7 years ago Neural-style does not output any image from the network, it uses the network to develop a new image from noise using the following steps:
- feed the content image into the model and store the output from selected content layers as the content target
- feed the style image into the model and store a style representation (in practice a Gram matrix) from the output of the selected style layers as the style target
- create a new image initialized by noise
- feed this image into the model and make the same measurements as with the content and style images
- calculate the difference with regard to both content and style targets, respectively
- adjust the new image slightly, looking for a minimum of the content and style differences
- continue the process of adjusting and measuring the new image until we are happy with the results or a certain number iterations has been passed (see http://liipetti.net/erratic/2016/05/19/how-neural-style-works/ )
If you are looking for a solution in which the network directly outputs an image, see https://github.com/jcjohnson/fast-neural-style .
Hi, @jcjohnson.
What is the neural style network's training output? and How can we get the test output image? It is from the feature map?
Thanks.