Please see the following picture.
The right hand side is the model that we are working.
STYLE_LAYERS = [
('block1_conv1', 0.2),
('block2_conv1', 0.2),
('block3_conv1', 0.2),
('block4_conv1', 0.2),
('block5_conv1', 0.2)]
:
content_layer = [('block5_conv4', 1)]
vgg_model_outputs = get_layer_outputs(vgg, STYLE_LAYERS + content_layer)
We merge 5 layers as a style layer, and define the last layer as the content layer.
Hope this helps.
