coding_nn_reg_L_model.py

def model_with_regularization(
        X, y, layers_dims, learning_rate=0.01,  num_epochs=3000,
        print_cost=False, hidden_layers_activation_fn="relu", lambd=0):
    # get number of examples
    m = X.shape[1]

    # to get consistents output
    np.random.seed(1)

    # initialize parameters
    parameters = initialize_parameters(layers_dims)

    # intialize cost list
    cost_list = []

    # implement gradient descent
    for i in range(num_epochs):
        # compute forward propagation
        AL, caches = L_model_forward(
            X, parameters, hidden_layers_activation_fn)

        # compute regularized cost
        reg_cost = compute_cost_reg(AL, y, parameters, lambd)

        # compute gradients
        grads = L_model_backward_reg(
            AL, y, caches, hidden_layers_activation_fn, lambd)

        # update parameters
        parameters = update_parameters(parameters, grads, learning_rate)

        # print cost
        if (i + 1) % 100 == 0 and print_cost:
            print("The cost after {} iterations: {}".format(
                (i + 1), reg_cost))

        # append cost
        if i % 100 == 0:
            cost_list.append(reg_cost)

    # plot the cost curve
    plt.plot(cost_list)
    plt.xlabel("Iterations (per hundreds)")
    plt.ylabel("Cost")
    plt.title("Cost curve for the learning rate = {}".format(learning_rate))

    return parameters