diff options
Diffstat (limited to 'tensorflow/python/layers/normalization.py')
| -rw-r--r-- | tensorflow/python/layers/normalization.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/tensorflow/python/layers/normalization.py b/tensorflow/python/layers/normalization.py index 323a9f8ee3..d83292b809 100644 --- a/tensorflow/python/layers/normalization.py +++ b/tensorflow/python/layers/normalization.py @@ -94,8 +94,8 @@ class BatchNormalization(base.Layer): and should be neither too small (which would add noise) nor too large (which would give stale estimates). Note that `momentum` is still applied to get the means and variances for inference. - fused: if `True`, use a faster, fused implementation if possible. - If `None`, use the system recommended implementation. + fused: if `None` or `True`, use a faster, fused implementation if possible. + If `False`, use the system recommended implementation. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see tf.Variable). virtual_batch_size: An `int`. By default, `virtual_batch_size` is `None`, @@ -729,8 +729,8 @@ def batch_normalization(inputs, and should be neither too small (which would add noise) nor too large (which would give stale estimates). Note that `momentum` is still applied to get the means and variances for inference. - fused: if `True`, use a faster, fused implementation if possible. - If `None`, use the system recommended implementation. + fused: if `None` or `True`, use a faster, fused implementation if possible. + If `False`, use the system recommended implementation. virtual_batch_size: An `int`. By default, `virtual_batch_size` is `None`, which means batch normalization is performed across the whole batch. When `virtual_batch_size` is not `None`, instead perform "Ghost Batch |