Generative Deep Learning by David Foster

Author:David Foster
Language: eng
Format: epub
Publisher: O'Reilly Media
Published: 2019-07-02T16:00:00+00:00

bash ./scripts/download_cyclegan_data.sh monet2photo

This time we will use the parameter set shown in Example 5-7 to build the model:

Example 5-7. Defining the Monet CycleGAN

gan = CycleGAN( input_dim = (256,256,3) , learning_rate = 0.0002 , lambda_validation = 1 , lambda_reconstr = 10 , lambda_id = 5 , generator_type = 'resnet' , gen_n_filters = 32 , disc_n_filters = 64 )

The Generators (ResNet)

In this example, we shall introduce a new type of generator architecture: a residual network, or ResNet.10 The ResNet architecture is similar to a U-Net in that it allows information from previous layers in the network to skip ahead one or more layers. However, rather than creating a U shape by connecting layers from the downsampling part of the network to corresponding upsampling layers, a ResNet is built of residual blocks stacked on top of each other, where each block contains a skip connection that sums the input and output of the block, before passing this on to the next layer. A single residual block is shown in Figure 5-10.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.