discriminator.py

class Discriminator(nn.Module):
    def __init__(self, image_size, hidden_size):
        super(Discriminator, self).__init__()
        # Instead of linear layer one can also use 2d convolution.
        #Imapge_size -> 784 for MNIST, hidden size is hyperparameter
        self.fc1 = nn.Linear(image_size, hidden_size) 
        self.relu = nn.LeakyReLU(0.2) #this is the negative slope. 
        self.fc2 = nn.Linear(hidden_size, hidden_size)
        #the final output is of shape 1, to classify real or fake
        self.fc3 = nn.Linear(hidden_size, 1) 
        self.sigmoid = nn.Sigmoid()
        
    def forward(self, x):
        out_fc1 = self.fc1(x)
        out_relu = self.relu(out_fc1)
        out_fc2 = self.fc2(out_relu)
        out_relu2 = self.relu(out_fc2)
        out_fc3 = self.fc3(out_relu2)
        out = self.sigmoid(out_fc3)
        return (out)