🍀 Challenge: Define the Generator

This task will test your knowledge on building the Generator class for the conditional GAN.

We'll cover the following

Problem statement

A partial Generator class for the Fashion MNIST dataset is provided to you. Your task is to define the:

  • Network architecture

    • The input layer should have 100+10 nodes.

    • The hidden layer 1 should have 200 nodes with the LeakyReLU activation applied to the output. The hidden layer 1 output should be normalized.

    • The output layer should have 784 nodes with the Sigmoid activation function applied to the output.

  • Loss function as BCE.

  • Optimiser as Adam. The learning rate should be 0.0001.

Get hands-on with 1400+ tech skills courses.