🍀 Challenge: Building the Generator

Problem statement

A partial Generator class is provided to you. Your task is to define the:

• Network architecture

  • The input layer should have 100 nodes.
  • The hidden layer should have 200 nodes with the LeakyReLU activation applied to the output. The gradient of the left half of the function should be $0.02$. The hidden layer output should be normalized before it enters the final layer.
  • The output layer should have 784 nodes with the Sigmoid activation function applied to the output.

• Optimiser as Adam. Note that the learning rate should be 0.0001.