Assignment 4: Neural Style Transfer

Part 1: Content Reconstruction

As the reconstruction comes from deeper layers it becomes noisy. More noise can be seen in the reconstreced Image

Original Image	Conv_1	Conv_3	Conv_4	Conv_5

Noise 1	Noise 2	Reconstructed 1 (Conv_2)	Reconstructed 2 (Conv_2)

Part 2: Texture Synthesis

Texture Synthesis varies alot with the use of different layers for reconstruction. I found that Conv_Layers: 1,2,5,9,13 gives the best result.

Original Image	ConvLayers 1 to 5	Layers: 1,6,14	Layers: 1,2,5,9,13	ConvLayers 15 to 19

Selected layer: 1,2,5,9,13

Noise	Texture Synthesis

Part 3.1: Hyperparameter tuning

The style loss is also normalized with the number of feature layers used to calculate the style loss. Best results with style_weight = 1000000 and content_weight = 1

Content Image	Style Image

style_weight = 10000 and content_weight = 1	style_weight = 100000 and content_weight = 1

style_weight = 1000000 and content_weight = 1	style_weight = 1000000 and content_weight = 2

Part 3.2: Optimized two content images mixing with two style images accordingly:

Content Image	Style Image

style_weight = 10000 and content_weight = 1	style_weight = 100000 and content_weight = 1

style_weight = 1000000 and content_weight = 1	style_weight = 1000000 and content_weight = 2

Content Image	Style Image

style_weight = 10000 and content_weight = 1	style_weight = 100000 and content_weight = 1

style_weight = 1000000 and content_weight = 1	style_weight = 1000000 and content_weight = 2

Result differs with for combinations of content loss and style loss parameters. style_weight = 1000000 and content_weight = 1 or 2 seems to give the best output. Style loss is normalized with respect to number of terms in gram matrix and number of feature layers used for loss.