Dp-sgd-mnist error when running server.py

Flower Help - Beginners
4

I got this solved in the end by upgrading tensorflow-privacy to version 0.9.0 and reworking the calculate_epsilon function as shown here. This was based on the updated code in

def compute_epsilon(
    epochs: int, num_train_examples: int, batch_size: int, noise_multiplier: float
) -> float:
    """Computes epsilon value for given hyperparameters.

    Based on
    github.com/tensorflow/privacy/blob/master/tutorials/mnist_dpsgd_tutorial_keras.py
    """
    if noise_multiplier == 0.0:
        return float("inf")
    steps = epochs * num_train_examples // batch_size
    orders = [1 + x / 10.0 for x in range(1, 100)] + list(range(12, 64))
    accountant = dp_accounting.rdp.RdpAccountant(orders)
    sampling_probability = batch_size / num_train_examples
    event = dp_accounting.SelfComposedDpEvent(
        dp_accounting.PoissonSampledDpEvent(
            sampling_probability, dp_accounting.GaussianDpEvent(noise_multiplier)
        ),
        steps,
    )

    accountant.compose(event)

    # Delta is set to approximate 1 / (number of training points).
    return accountant.get_epsilon(target_delta=1e-4)
1 Like