tutorials/mnist_dpsgd_tutorial_keras.py [27:91]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
flags.DEFINE_boolean(
    'dpsgd', True, 'If True, train with DP-SGD. If False, '
    'train with vanilla SGD.')
flags.DEFINE_float('learning_rate', 0.15, 'Learning rate for training')
flags.DEFINE_float('noise_multiplier', 0.1,
                   'Ratio of the standard deviation to the clipping norm')
flags.DEFINE_float('l2_norm_clip', 1.0, 'Clipping norm')
flags.DEFINE_integer('batch_size', 250, 'Batch size')
flags.DEFINE_integer('epochs', 60, 'Number of epochs')
flags.DEFINE_integer(
    'microbatches', 250, 'Number of microbatches '
    '(must evenly divide batch_size)')
flags.DEFINE_string('model_dir', None, 'Model directory')

FLAGS = flags.FLAGS


def compute_epsilon(steps):
  """Computes epsilon value for given hyperparameters."""
  if FLAGS.noise_multiplier == 0.0:
    return float('inf')
  orders = [1 + x / 10. for x in range(1, 100)] + list(range(12, 64))
  sampling_probability = FLAGS.batch_size / 60000
  rdp = compute_rdp(
      q=sampling_probability,
      noise_multiplier=FLAGS.noise_multiplier,
      steps=steps,
      orders=orders)
  # Delta is set to 1e-5 because MNIST has 60000 training points.
  return get_privacy_spent(orders, rdp, target_delta=1e-5)[0]


def load_mnist():
  """Loads MNIST and preprocesses to combine training and validation data."""
  train, test = tf.keras.datasets.mnist.load_data()
  train_data, train_labels = train
  test_data, test_labels = test

  train_data = np.array(train_data, dtype=np.float32) / 255
  test_data = np.array(test_data, dtype=np.float32) / 255

  train_data = train_data.reshape((train_data.shape[0], 28, 28, 1))
  test_data = test_data.reshape((test_data.shape[0], 28, 28, 1))

  train_labels = np.array(train_labels, dtype=np.int32)
  test_labels = np.array(test_labels, dtype=np.int32)

  train_labels = tf.keras.utils.to_categorical(train_labels, num_classes=10)
  test_labels = tf.keras.utils.to_categorical(test_labels, num_classes=10)

  assert train_data.min() == 0.
  assert train_data.max() == 1.
  assert test_data.min() == 0.
  assert test_data.max() == 1.

  return train_data, train_labels, test_data, test_labels


def main(unused_argv):
  logging.set_verbosity(logging.INFO)
  if FLAGS.dpsgd and FLAGS.batch_size % FLAGS.microbatches != 0:
    raise ValueError('Number of microbatches should divide evenly batch_size')

  # Load training and test data.
  train_data, train_labels, test_data, test_labels = load_mnist()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tutorials/mnist_dpsgd_tutorial_keras_model.py [26:90]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
flags.DEFINE_boolean(
    'dpsgd', True, 'If True, train with DP-SGD. If False, '
    'train with vanilla SGD.')
flags.DEFINE_float('learning_rate', 0.15, 'Learning rate for training')
flags.DEFINE_float('noise_multiplier', 0.1,
                   'Ratio of the standard deviation to the clipping norm')
flags.DEFINE_float('l2_norm_clip', 1.0, 'Clipping norm')
flags.DEFINE_integer('batch_size', 250, 'Batch size')
flags.DEFINE_integer('epochs', 60, 'Number of epochs')
flags.DEFINE_integer(
    'microbatches', 250, 'Number of microbatches '
    '(must evenly divide batch_size)')
flags.DEFINE_string('model_dir', None, 'Model directory')

FLAGS = flags.FLAGS


def compute_epsilon(steps):
  """Computes epsilon value for given hyperparameters."""
  if FLAGS.noise_multiplier == 0.0:
    return float('inf')
  orders = [1 + x / 10. for x in range(1, 100)] + list(range(12, 64))
  sampling_probability = FLAGS.batch_size / 60000
  rdp = compute_rdp(
      q=sampling_probability,
      noise_multiplier=FLAGS.noise_multiplier,
      steps=steps,
      orders=orders)
  # Delta is set to 1e-5 because MNIST has 60000 training points.
  return get_privacy_spent(orders, rdp, target_delta=1e-5)[0]


def load_mnist():
  """Loads MNIST and preprocesses to combine training and validation data."""
  train, test = tf.keras.datasets.mnist.load_data()
  train_data, train_labels = train
  test_data, test_labels = test

  train_data = np.array(train_data, dtype=np.float32) / 255
  test_data = np.array(test_data, dtype=np.float32) / 255

  train_data = train_data.reshape((train_data.shape[0], 28, 28, 1))
  test_data = test_data.reshape((test_data.shape[0], 28, 28, 1))

  train_labels = np.array(train_labels, dtype=np.int32)
  test_labels = np.array(test_labels, dtype=np.int32)

  train_labels = tf.keras.utils.to_categorical(train_labels, num_classes=10)
  test_labels = tf.keras.utils.to_categorical(test_labels, num_classes=10)

  assert train_data.min() == 0.
  assert train_data.max() == 1.
  assert test_data.min() == 0.
  assert test_data.max() == 1.

  return train_data, train_labels, test_data, test_labels


def main(unused_argv):
  logging.set_verbosity(logging.INFO)
  if FLAGS.dpsgd and FLAGS.batch_size % FLAGS.microbatches != 0:
    raise ValueError('Number of microbatches should divide evenly batch_size')

  # Load training and test data.
  train_data, train_labels, test_data, test_labels = load_mnist()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -