We will define all the required hyperparameters in hy_param.py and then import it as a module in our other codes. This makes it easy in deployment and it's a good practice to make your code as modular as possible. Let's look into the hyperparameter configurations that we have in our hy_param.py file:
We will be using these values throughout our code and it's totally configurable.
Python Deep Learning Projects Exploration Opportunity! We invite you, our project team-mate and reader to try different values of learning rate and number of hidden layers to experiment and build the better models.
Since the flat vectors of images (as shown in Figure 2.1) are of size [1 x 786] the num_input=784 is fixed in this case. In addition, the class count in MNIST dataset is 10. We have digits from 0-9, so obviously we have num_classes=10.