IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[MO] Move reverse input channels before mean/scale (#9182)

Browse Source
This commit is contained in:
Mateusz Tabaka 2021-12-14 22:41:21 +01:00 committed by GitHub
parent 3f6a026ae9
commit 0e4c50e24d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 70 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
docs/MO_DG/prepare_model/convert_model/Converting_Model_General.md
View File

@ -59,11 +59,14 @@ Framework-agnostic parameters:
--reverse_input_channels
Switch the input channels order from RGB to BGR (or
vice versa). Applied to original inputs of the model
if and only if a number of channels equals 3. Applied
after application of --mean_values and --scale_values
options, so numbers in --mean_values and
--scale_values go in the order of channels used in the
original model.
if and only if a number of channels equals 3.
When --mean_values/--scale_values are also specified,
reversing of channels will be applied to user's input
data first, so that numbers in --mean_values and
--scale_values go in the order of channels used in
the original model. In other words, if both options are
specified then the data flow in the model looks as following:
Parameter -> ReverseInputChannels -> Mean/Scale apply -> the original body of the model.
--log_level {CRITICAL,ERROR,WARN,WARNING,INFO,DEBUG,NOTSET}
Logger level
--input INPUT Quoted list of comma-separated input nodes names with

12
tools/mo/openvino/tools/mo/back/preprocessing.py
View File

@ -372,6 +372,12 @@ def apply_preprocessing(ov_function: Model, argv: argparse.Namespace):
else:
prep.output(node_name).tensor().set_layout(Layout(layout_value['target_layout']))
# Apply reverse_input_channels
if need_reverse:
for name, _ in suitable_params_ric:
prep.input(name).preprocess().reverse_channels()
log.debug('reverse_input_channels pre-processing applied to {}'.format(name))
for node_name, node_mean_scale_values in mean_scale_values.items():
# Apply mean first, then scale
if node_mean_scale_values['mean'] is not None:
@ -380,12 +386,6 @@ def apply_preprocessing(ov_function: Model, argv: argparse.Namespace):
prep.input(node_name).preprocess().scale(node_mean_scale_values['scale'])
log.debug('Mean/Scale pre-processing applied to {}'.format(node_name))
# Apply reverse_input_channels
if need_reverse:
for name, _ in suitable_params_ric:
prep.input(name).preprocess().reverse_channels()
log.debug('reverse_input_channels pre-processing applied to {}'.format(name))
# Apply pre-processing builder to a function
ov_function = prep.build()

10
tools/mo/openvino/tools/mo/utils/cli_parser.py
View File

@ -273,10 +273,12 @@ def get_common_cli_parser(parser: argparse.ArgumentParser = None):
'the original input of the model.')
common_group.add_argument('--reverse_input_channels',
help='Switch the input channels order from RGB to BGR (or vice versa). Applied to '
'original inputs of the model if and only if a number of channels equals 3. Applied '
'after application of --mean_values and --scale_values options, so numbers in '
'--mean_values and --scale_values go in the order of channels used in the original '
'model.',
'original inputs of the model if and only if a number of channels equals 3. '
'When --mean_values/--scale_values are also specified, reversing of channels will '
'be applied to user\'s input data first, so that numbers in --mean_values '
'and --scale_values go in the order of channels used in the original model. '
'In other words, if both options are specified, then the data flow in the model '
'looks as following: Parameter -> ReverseInputChannels -> Mean/Scale apply -> the original body of the model.',
action='store_true')
common_group.add_argument('--log_level',
help='Logger level',

64
tools/mo/unit_tests/mo/back/moc_preprocessing_test_actual.py
View File

@ -56,25 +56,23 @@ class TestPreprocessingMOC(unittest.TestCase):
def setUp(self):
pass
def check_constant(self, const_node, expected, shape=None):
self.assertEqual(const_node.get_type_name(), 'Constant')
self.assertTrue(np.allclose(const_node.get_vector(), expected))
if shape is not None:
assert const_node.shape == PartialShape(shape)
def check_scale_constant(self, node, expected, shape=None):
const_node = node.input(1).get_source_output().get_node()
self.assertEqual(const_node.get_type_name(), 'Constant')
if node.get_type_name() == 'Divide':
self.assertTrue(np.allclose(const_node.get_vector(), expected))
else:
self.assertTrue(np.allclose(const_node.get_vector(), 1. / expected))
if shape:
assert const_node.shape == PartialShape(shape)
if node.get_type_name() != 'Divide':
expected = 1. / expected
self.check_constant(const_node, expected, shape)
def check_mean_constant(self, node, expected, shape=None):
const_node = node.input(1).get_source_output().get_node()
self.assertEqual(const_node.get_type_name(), 'Constant')
if node.get_type_name() == 'Subtract':
self.assertTrue(np.allclose(const_node.get_vector(), expected))
else:
self.assertTrue(np.allclose(const_node.get_vector(), -expected.toList()))
if shape:
self.assertEqual(const_node.shape, PartialShape(shape))
if node.get_type_name() != 'Subtract':
expected = -expected.toList()
self.check_constant(const_node, expected, shape)
def test_scale_single_value(self):
argv = Namespace(mean_scale_values=None, scale=2.0)
@ -615,3 +613,41 @@ class TestPreprocessingMOC(unittest.TestCase):
self.assertTrue(op_node0.get_type_name() == 'Relu')
op_node1 = list(function.get_parameters()[1].output(0).get_target_inputs())[0].get_node()
self.assertTrue(op_node1.get_type_name() == 'Relu')
def test_reverse_channels_and_mean_scale(self):
argv = Namespace(reverse_input_channels=True, mean_scale_values={
'input2a': {
'mean': np.array([1., 2., 3.]),
'scale': np.array([2., 4., 8.])}},
scale=None)
function = create_function2(shape2=[1, 3, 224, 224])
process_function(ov_function=function, argv=argv)
# Verify that first is gather, then subtract 'mean', then 'scale'
gather = list(function.get_parameters()[1].output(0).get_target_inputs())[0].get_node()
self.assertTrue(gather.get_type_name() == 'Gather')
range_node = gather.input(1).get_source_output().get_node()
self.assertTrue(range_node.get_type_name() == 'Range')
start = range_node.input(0).get_source_output().get_node()
end = range_node.input(1).get_source_output().get_node()
step = range_node.input(2).get_source_output().get_node()
self.check_constant(start, expected=[2], shape=[])
self.check_constant(end, expected=[-1], shape=[])
self.check_constant(step, expected=[-1], shape=[])
axes = gather.input(2).get_source_output().get_node()
self.check_constant(axes, expected=[1], shape=[1])
op_node = list(gather.output(0).get_target_inputs())[0].get_node()
self.assertTrue(op_node.get_type_name() == 'Subtract' or op_node.get_type_name() == 'Add')
self.check_mean_constant(op_node, expected=[1., 2., 3.], shape=[1, 3, 1, 1])
op_node = list(op_node.output(0).get_target_inputs())[0].get_node()
self.assertTrue(op_node.get_type_name() == 'Divide' or op_node.get_type_name() == 'Multiply')
self.check_scale_constant(op_node, expected=[2., 4., 8.], shape=[1, 3, 1, 1])
# Verify that input1 is not affected
op_node = list(function.get_parameters()[0].output(0).get_target_inputs())[0].get_node()
self.assertEqual(op_node.get_type_name(), 'Relu')
# Verify that guessed layout (?C??) is not appeared in input2
self.assertEqual(function.get_parameters()[1].layout, Layout())