Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update layers pull request #14785

Merged
merged 8 commits into from
Dec 21, 2017
Merged

Update layers pull request #14785

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
dfe2aba
Update layers_test.py
shreyneil Oct 21, 2017
3953afc
Update layers_test
shreyneil Nov 22, 2017
b7606e8
Update layers.py
shreyneil Nov 22, 2017
581a6a0
Fix whitespace, revert batchnorm test change
Dec 4, 2017
cadac9f
whitespace fix
Dec 4, 2017
cbe20df
Extra comment indicating this is a graph building test.
Dec 4, 2017
fef93a4
missing colon
Dec 4, 2017
a2d307b
Update layers_test.py
shreyneil Dec 20, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
3 changes: 2 additions & 1 deletion tensorflow/contrib/layers/python/layers/layers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -805,7 +805,8 @@ def _delay_updates():
if data_format == DATA_FORMAT_NCHW:
mean = array_ops.reshape(mean, params_shape_broadcast)
variance = array_ops.reshape(variance, params_shape_broadcast)
beta = array_ops.reshape(beta, params_shape_broadcast)
if beta is not None:
beta = array_ops.reshape(beta, params_shape_broadcast)
if gamma is not None:
gamma = array_ops.reshape(gamma, params_shape_broadcast)

Expand Down
6 changes: 6 additions & 0 deletions tensorflow/contrib/layers/python/layers/layers_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1739,6 +1739,12 @@ def _addBesselsCorrection(self, sample_size, expected_var):
expected_var *= correction_factor
return expected_var, correction_factor

def testBatchNormCenterFalse(self):
a = array_ops.placeholder(dtype=dtypes.float32, shape=(10, 10, 10, 10))
# Test that center=False builds a valid graph.
_layers.batch_norm(a, center=False, data_format='NCHW',
zero_debias_moving_mean=True)

def testUnknownShape(self):
with ops.Graph().as_default() as g, self.test_session(g):
inputs = array_ops.placeholder(dtype=dtypes.float32)
Expand Down