- neural style transfer
what are deep convnets learning?
- cost function
Content c + Style S = Generated image G
J(G) = alpha * Jcontent(C, G) + beta * Jstyle(S, G)
find the generated image G
- Initiate G randomly
- Use gradient descent to minimize J(G)
- content cost function
say you use hidden layer l to compute content cost
use pre-trained ConvNet.(E.g., VGG network)
Let al and al be the activation of layer l on the images
If al and al are similar, both images have similar content
Jcontent(C,G) = 1/2 ||al - al||^2
Here, nH,nW and nC are the height, width and number of channels of the hidden layer you have chosen, and appear in a normalization term in the cost.
- Style cost function