Generative Adversarial Networks Projects

The encoder network

The encoder network is the initial network of the generator network and contains eight convolutional blocks with the following configuration:

Layer Name	Hyperparameters	Input Shape	Output Shape
1st 2D Convolution Layer	filters=64, kernel_size=4, strides=2, padding='same',	(256, 256, 1)	(128, 128, 64)
Activation Layer	activation='leakyrelu', alpha=0.2	(128, 128, 64)	(128, 128, 64)
2nd 2D Convolution Layer	filters=128, kernel_size=4, strides=2, padding='same',	(128, 128, 64)	(64, 64, 128)
Batch Normalization Layer	None	(64, 64, 128)	(64, 64, 128)
Activation Layer	activation='leakyrelu', alpha=0.2	(64, 64, 128)	(64, 64, 128)
3rd 2D Convolution Layer	filters=256, ...