marcoabreu closed pull request #11544: [MXNET-620]Fix flaky test batchnorm
training
URL: https://github.com/apache/incubator-mxnet/pull/11544
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/tests/python/mkl/test_mkldnn.py b/tests/python/mkl/test_mkldnn.py
index dad1bd7d615..8c296deef20 100644
--- a/tests/python/mkl/test_mkldnn.py
+++ b/tests/python/mkl/test_mkldnn.py
@@ -234,7 +234,7 @@ def check_batchnorm_training(stype):
mean_std = [mx.nd.array(rolling_mean).tostype(stype),
mx.nd.array(rolling_std).tostype(stype)]
test = mx.symbol.BatchNorm(data, fix_gamma=True)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
stypes = ['row_sparse', 'default']
for stype in stypes:
diff --git a/tests/python/unittest/test_operator.py
b/tests/python/unittest/test_operator.py
index ae5cba21711..faaa45efdb1 100644
--- a/tests/python/unittest/test_operator.py
+++ b/tests/python/unittest/test_operator.py
@@ -1445,7 +1445,6 @@ def test_nearest_upsampling():
check_nearest_upsampling_with_shape(shapes, scale,
root_scale)
[email protected]("test fails intermittently. temporarily disabled till it gets
fixed. tracked at https://github.com/apache/incubator-mxnet/issues/8044";)
@with_seed()
def test_batchnorm_training():
def check_batchnorm_training(stype):
@@ -1466,28 +1465,28 @@ def check_batchnorm_training(stype):
mean_std = [mx.nd.array(rolling_mean).tostype(stype),
mx.nd.array(rolling_std).tostype(stype)]
test = mx.symbol.BatchNorm_v1(data, fix_gamma=True)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
test = mx.symbol.BatchNorm(data, fix_gamma=True)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
test = mx.symbol.BatchNorm_v1(data, fix_gamma=True,
use_global_stats=True)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
test = mx.symbol.BatchNorm(data, fix_gamma=True,
use_global_stats=True)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
test = mx.symbol.BatchNorm_v1(data, fix_gamma=False)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
test = mx.symbol.BatchNorm(data, fix_gamma=False)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
test = mx.symbol.BatchNorm_v1(data, fix_gamma=False,
use_global_stats=True)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
test = mx.symbol.BatchNorm(data, fix_gamma=False,
use_global_stats=True)
- check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-4)
+ check_numeric_gradient(test, in_location, mean_std,
numeric_eps=1e-2, rtol=0.16, atol=1e-2)
# Test varying channel axis
dim = len(shape)
@@ -1527,7 +1526,7 @@ def check_batchnorm_training(stype):
test = mx.symbol.BatchNorm(data, fix_gamma=False,
use_global_stats=True, axis=chaxis)
check_numeric_gradient(test, in_location, xmean_std,
numeric_eps=1e-2, rtol=0.2, atol=0.01)
- stypes = ['row_sparse', 'default']
+ stypes = ['default']
for stype in stypes:
check_batchnorm_training(stype)
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
