coding_nn_L_model.py

# Define the multi-layer model using all the helper functions we wrote before
def L_layer_model(
        X, y, layers_dims, learning_rate=0.01, num_iterations=3000,
        print_cost=True, hidden_layers_activation_fn="relu"):
    np.random.seed(1)

    # initialize parameters
    parameters = initialize_parameters(layers_dims)

    # intialize cost list
    cost_list = []

    # iterate over num_iterations
    for i in range(num_iterations):
        # iterate over L-layers to get the final output and the cache
        AL, caches = L_model_forward(
            X, parameters, hidden_layers_activation_fn)

        # compute cost to plot it
        cost = compute_cost(AL, y)

        # iterate over L-layers backward to get gradients
        grads = L_model_backward(AL, y, caches, hidden_layers_activation_fn)

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

        # append each 100th cost to the cost list
        if (i + 1) % 100 == 0 and print_cost:
            print(f"The cost after {i + 1} iterations is: {cost:.4f}")

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

    # plot the cost curve
    plt.figure(figsize=(10, 6))
    plt.plot(cost_list)
    plt.xlabel("Iterations (per hundreds)")
    plt.ylabel("Loss")
    plt.title(f"Loss curve for the learning rate = {learning_rate}")

    return parameters


def accuracy(X, parameters, y, activation_fn="relu"):
    probs, caches = L_model_forward(X, parameters, activation_fn)
    labels = (probs >= 0.5) * 1
    accuracy = np.mean(labels == y) * 100
    return f"The accuracy rate is: {accuracy:.2f}%."