diff options
author | A. Unique TensorFlower <gardener@tensorflow.org> | 2017-01-10 12:59:31 -0800 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2017-01-10 13:08:14 -0800 |
commit | a762b0a0de067036dc799ac37127142a9ac2fed3 (patch) | |
tree | 5e9f3f4e9afef2eddf3451a8d4e6d6812609e0a0 /tensorflow/g3doc/api_docs/python/nn.md | |
parent | fdbd02c8d7f07bd1207938662716fad8857dcd55 (diff) |
Update generated Python Op docs.
Change: 144117353
Diffstat (limited to 'tensorflow/g3doc/api_docs/python/nn.md')
-rw-r--r-- | tensorflow/g3doc/api_docs/python/nn.md | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/tensorflow/g3doc/api_docs/python/nn.md b/tensorflow/g3doc/api_docs/python/nn.md index fcc73663ef..983f68f855 100644 --- a/tensorflow/g3doc/api_docs/python/nn.md +++ b/tensorflow/g3doc/api_docs/python/nn.md @@ -1932,6 +1932,9 @@ The mean and variance are calculated by aggregating the contents of `x` across `axes`. If `x` is 1-D and `axes = [0]` this is just the mean and variance of a vector. +Note: for numerical stability, when shift=None, the true mean +would be computed and used as shift. + When using these moments for batch normalization (see `tf.nn.batch_normalization`): @@ -1946,8 +1949,9 @@ When using these moments for batch normalization (see * <b>`axes`</b>: Array of ints. Axes along which to compute mean and variance. * <b>`shift`</b>: A `Tensor` containing the value by which to shift the data for - numerical stability, or `None` if no shift is to be performed. A shift - close to the true mean provides the most numerically stable results. + numerical stability, or `None` in which case the true mean of the data is + used as shift. A shift close to the true mean provides the most + numerically stable results. * <b>`name`</b>: Name used to scope the operations that compute the moments. * <b>`keep_dims`</b>: produce moments with the same dimensionality as the input. |