tutorials/mnist_dpsgd_tutorial.py [41:72]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
FLAGS = flags.FLAGS


def cnn_model_fn(features, labels, mode, params):  # pylint: disable=unused-argument
  """Model function for a CNN."""

  # Define CNN architecture.
  logits = common.get_cnn_model(features)

  # Calculate loss as a vector (to support microbatches in DP-SGD).
  vector_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
      labels=labels, logits=logits)
  # Define mean of loss across minibatch (for reporting through tf.Estimator).
  scalar_loss = tf.reduce_mean(input_tensor=vector_loss)

  # Configure the training op (for TRAIN mode).
  if mode == tf.estimator.ModeKeys.TRAIN:
    if FLAGS.dpsgd:
      # Use DP version of GradientDescentOptimizer. Other optimizers are
      # available in dp_optimizer. Most optimizers inheriting from
      # tf.train.Optimizer should be wrappable in differentially private
      # counterparts by calling dp_optimizer.optimizer_from_args().
      optimizer = dp_optimizer.DPGradientDescentGaussianOptimizer(
          l2_norm_clip=FLAGS.l2_norm_clip,
          noise_multiplier=FLAGS.noise_multiplier,
          num_microbatches=FLAGS.microbatches,
          learning_rate=FLAGS.learning_rate)
      opt_loss = vector_loss
    else:
      optimizer = tf.train.GradientDescentOptimizer(
          learning_rate=FLAGS.learning_rate)
      opt_loss = scalar_loss
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tutorials/mnist_dpsgd_tutorial_tpu.py [43:74]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
FLAGS = flags.FLAGS


def cnn_model_fn(features, labels, mode, params):  # pylint: disable=unused-argument
  """Model function for a CNN."""

  # Define CNN architecture using tf.keras.layers.
  logits = common.get_cnn_model(features)

  # Calculate loss as a vector (to support microbatches in DP-SGD).
  vector_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
      labels=labels, logits=logits)
  # Define mean of loss across minibatch (for reporting through tf.Estimator).
  scalar_loss = tf.reduce_mean(input_tensor=vector_loss)

  # Configure the training op (for TRAIN mode).
  if mode == tf.estimator.ModeKeys.TRAIN:
    if FLAGS.dpsgd:
      # Use DP version of GradientDescentOptimizer. Other optimizers are
      # available in dp_optimizer. Most optimizers inheriting from
      # tf.train.Optimizer should be wrappable in differentially private
      # counterparts by calling dp_optimizer.optimizer_from_args().
      optimizer = dp_optimizer.DPGradientDescentGaussianOptimizer(
          l2_norm_clip=FLAGS.l2_norm_clip,
          noise_multiplier=FLAGS.noise_multiplier,
          num_microbatches=FLAGS.microbatches,
          learning_rate=FLAGS.learning_rate)
      opt_loss = vector_loss
    else:
      optimizer = tf.train.GradientDescentOptimizer(
          learning_rate=FLAGS.learning_rate)
      opt_loss = scalar_loss
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -