Generative Adversarial Networks Projects

Discriminator

As mentioned in the Architecture of DCGAN section, the discriminator network has three 2D convolutional layers, each followed by an activation function followed by two max pooling layers. The tail of the network contains two fully-connected (dense) layers that work as a classification layer. Before anything else, let's have a look at the different layers in the discriminator network:

• All convolutional layers have LeakyReLU as the activation function with an alpha value of 0.2
• The convolutional layers have 128, 256, and 512 filters, respectively. Their kernel sizes are (5, 5), (3, 3), and (3, 3), respectively.
• After the convolutional layers, we have a flatten layer, which flattens the input to a one-dimensional tensor.
• Following ...