def test_MeanVarianceNormalization(tmpdir):
shape = (3, 5, 7)
data = np.reshape(np.arange(np.prod(shape), dtype=np.float32), shape)
input_operand = C.input_variable(shape=shape)
model0 = C.mean_variance_normalization(input_operand,
use_stats_across_channels=False,
do_variance_scaling=True)
verify_one_input(model0, data, tmpdir, 'MVN_0')
model1 = C.mean_variance_normalization(input_operand,
use_stats_across_channels=False,
do_variance_scaling=False)
verify_one_input(model1, data, tmpdir, 'MVN_1')
model2 = C.mean_variance_normalization(input_operand,
use_stats_across_channels=True,
do_variance_scaling=True)
verify_one_input(model2, data, tmpdir, 'MVN_2')
# The test below tests the round trip with epsilon. We loose always the epsilon value when exporting to ONNX
# (because ONNX MeanVarianceNormalization does not have an epsilon attribute). When loading back from ONNX, CNTK
# always uses the default eposilon value (0.00001). That's why test below has the default epsilon value. It is
# not expected to pass with any other epsilon value until something changes.
model3 = C.mean_variance_normalization(input_operand,
epsilon=0.00001,
use_stats_across_channels=False,
do_variance_scaling=True)
verify_one_input(model3, data, tmpdir, 'MVN_3')
def test_MeanVarianceNormalization(tmpdir):
shape = (3, 5, 7)
data = np.reshape(np.arange(np.prod(shape), dtype=np.float32), shape)
input_operand = C.input_variable(shape=shape)
model0 = C.mean_variance_normalization(input_operand,
use_stats_across_channels=False,
do_variance_scaling=True)
verify_one_input(model0, data, tmpdir, 'Pad_0')
model1 = C.mean_variance_normalization(input_operand,
use_stats_across_channels=False,
do_variance_scaling=False)
verify_one_input(model1, data, tmpdir, 'Pad_1')
model2 = C.mean_variance_normalization(input_operand,
use_stats_across_channels=True,
do_variance_scaling=True)
verify_one_input(model2, data, tmpdir, 'Pad_2')
def test_op_mean_variance_normalization(input_operand, use_stats_across_channels, do_variance_scaling, epsilon, output_ref, device_id, precision):
dt_precision = PRECISION_TO_TYPE[precision]
input_ref = AA(input_operand, dtype=dt_precision)
a = C.input_variable(shape=input_ref.shape,
dtype=sanitize_dtype_cntk(precision),
needs_gradient=False,
name='a')
norm_op = C.mean_variance_normalization(a, epsilon=epsilon, use_stats_across_channels=use_stats_across_channels, do_variance_scaling=do_variance_scaling)
output_test = norm_op.eval({a:input_ref}, device=cntk_device(device_id))
assert np.allclose(output_test, output_ref, atol=1e-4)
def test_MeanVarianceNormalization(tmpdir, dtype):
with C.default_options(dtype = dtype):
shape = (3, 5, 7)
data = np.reshape(np.arange(np.prod(shape), dtype = dtype), shape)
input_operand = C.input_variable(shape=shape)
model0 = C.mean_variance_normalization(input_operand, use_stats_across_channels=False, do_variance_scaling=True)
verify_one_input(model0, data, tmpdir, 'MVN_0')
model1 = C.mean_variance_normalization(input_operand, use_stats_across_channels=False, do_variance_scaling=False)
verify_one_input(model1, data, tmpdir, 'MVN_1')
model2 = C.mean_variance_normalization(input_operand, use_stats_across_channels=True, do_variance_scaling=True)
verify_one_input(model2, data, tmpdir, 'MVN_2')
# The test below tests the round trip with epsilon. We loose always the epsilon value when exporting to ONNX
# (because ONNX MeanVarianceNormalization does not have an epsilon attribute). When loading back from ONNX, CNTK
# always uses the default eposilon value (0.00001). That's why test below has the default epsilon value. It is
# not expected to pass with any other epsilon value until something changes.
model3 = C.mean_variance_normalization(input_operand, epsilon=0.00001, use_stats_across_channels=False, do_variance_scaling=True)
verify_one_input(model3, data, tmpdir, 'MVN_3')
