The main training loop for 2-layer nn

training_loop.py

costs = [] # initially empty list, this will store all the costs after a certian number of epochs

# Start training
for epoch in range(number_of_epochs):
    
    # ------------------------- forward-prop -------------------------
    Z1.forward(X_train)
    A1.forward(Z1.Z)
    
    Z2.forward(A1.A)
    A2.forward(Z2.Z)
    
    # ---------------------- Compute Cost ----------------------------
    cost, dA2 = compute_cost(Y=Y_train, Y_hat=A2.A)
    
    # print and store Costs every 100 iterations.
    if (epoch % 100) == 0:
        #print("Cost at epoch#" + str(epoch) + ": " + str(cost))
        print("Cost at epoch#{}: {}".format(epoch, cost))
        costs.append(cost)
    
    # ------------------------- back-prop ----------------------------
    A2.backward(dA2)
    Z2.backward(A2.dZ)
    
    A1.backward(Z2.dA_prev)
    Z1.backward(A1.dZ)
    
    # ----------------------- Update weights and bias ----------------
    Z2.update_params(learning_rate=learning_rate)
    Z1.update_params(learning_rate=learning_rate)