🍀 Challenge: Building the Discriminator
This task will test your knowledge on building the Fashion MNIST discriminator class.
We'll cover the following
Problem statement
A partial Discriminator
class is provided to you. Your task is to define the:
-
Network architecture
- The input layer should have
784
nodes. - The hidden layer should have
200
nodes with theLeakyReLU
activation applied to the output. The gradient of the left half of the function is . The hidden layer output should be normalized. - The output layer should have
1
node with theSigmoid
activation function applied to the output.
- The input layer should have
-
Loss function as
BCE
. -
Optimiser as
Adam
. The learning rate should be0.0001
.
Get hands-on with 1200+ tech skills courses.