adaptive_instance_norm
looks up the style
layer (default named 'w') and uses it to perform the adaptive instance norm.linear [outputs] (options)
conv [filters] (options)
conv [filters] filter=5 stride=1
will run set stride to 1 and with a filter size of 5.deconv [filters] (options)
resize_conv [output filters] (options)
reshape [size]
*
delimited dimensions.reshape -1
const [size]
*
delimited dimensionshypergan new mymodel
.hypergan new mymodel -l
.hypergan/losses/standard_gan_loss.py
for details.AutoencoderDiscriminator
.began
configuration template.