ruby/tensorflow_privacy
1
0
Fork 0
forked from 626_privacy/tensorflow_privacy
Code Pull requests Activity

Closes #16

Browse source 
PiperOrigin-RevId: 235070241
This commit is contained in:
Nicolas Papernot 2019-02-21 14:31:31 -08:00 committed by A. Unique TensorFlower
parent f37c9d1ea1
commit bfba26801d
1 changed files with 4 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
tutorials/mnist_dpsgd_tutorial.py
View file

@ -69,9 +69,10 @@ def cnn_model_fn(features, labels, mode):
if mode == tf.estimator.ModeKeys.TRAIN:
if FLAGS.dpsgd:
# Use DP version of GradientDescentOptimizer. For illustration purposes,
# we do that here by calling optimizer_from_args() explicitly, though DP
# versions of standard optimizers are available in dp_optimizer.
# 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,