def test_convolution_with_non_zero_padding():
element_type = Type.f32
image_shape = Shape([1, 1, 10, 10])
filter_shape = Shape([1, 1, 3, 3])
data = Parameter(element_type, image_shape)
filters = Parameter(element_type, filter_shape)
parameter_list = [data, filters]
image_arr = np.arange(100, dtype=np.float32).reshape(1, 1, 10, 10)
filter_arr = (np.ones(9, dtype=np.float32).reshape(1, 1, 3, 3)) * -1
filter_arr[0][0][1][1] = 1
strides = [1, 1]
dilations = [2, 2]
pads_begin = [2, 1]
pads_end = [1, 2]
model = ov.convolution(data, filters, strides, pads_begin, pads_end, dilations)
function = Function([model], parameter_list, "test")
runtime = get_runtime()
computation = runtime.computation(function, *parameter_list)
result = computation(image_arr, filter_arr)[0]
expected = convolution2d(
image_arr[0][0], filter_arr[0][0], strides, dilations, pads_begin, pads_end
).reshape([1, 1, 9, 9])
assert np.allclose(result, expected)
def test_proposal_props():
float_dtype = np.float32
batch_size = 1
post_nms_topn = 20
probs = ov.parameter(Shape([batch_size, 8, 255, 255]),
dtype=float_dtype,
name="probs")
deltas = ov.parameter(Shape([batch_size, 16, 255, 255]),
dtype=float_dtype,
name="bbox_deltas")
im_info = ov.parameter(Shape([4]), dtype=float_dtype, name="im_info")
attrs = {
"base_size": np.uint32(85),
"pre_nms_topn": np.uint32(10),
"post_nms_topn": np.uint32(post_nms_topn),
"nms_thresh": np.float32(0.34),
"feat_stride": np.uint32(16),
"min_size": np.uint32(32),
"ratio": np.array([0.1, 1.5, 2.0, 2.5], dtype=np.float32),
"scale": np.array([2, 3, 3, 4], dtype=np.float32),
}
node = ov.proposal(probs, deltas, im_info, attrs)
assert node.get_type_name() == "Proposal"
assert node.get_output_size() == 2
assert list(node.get_output_shape(0)) == [batch_size * post_nms_topn, 5]
assert list(node.get_output_shape(1)) == [batch_size * post_nms_topn]
assert node.get_output_element_type(0) == Type.f32
assert node.get_output_element_type(1) == Type.f32
def test_convolution_simple():
element_type = Type.f32
image_shape = Shape([1, 1, 16, 16])
filter_shape = Shape([1, 1, 3, 3])
data = Parameter(element_type, image_shape)
filters = Parameter(element_type, filter_shape)
parameter_list = [data, filters]
image_arr = np.arange(-128, 128, 1, dtype=np.float32).reshape(1, 1, 16, 16)
filter_arr = np.ones(9, dtype=np.float32).reshape(1, 1, 3, 3)
filter_arr[0][0][0][0] = -1
filter_arr[0][0][1][1] = -1
filter_arr[0][0][2][2] = -1
filter_arr[0][0][0][2] = -1
filter_arr[0][0][2][0] = -1
strides = [1, 1]
pads_begin = [0, 0]
pads_end = [0, 0]
dilations = [1, 1]
model = ov.convolution(data, filters, strides, pads_begin, pads_end, dilations)
function = Function([model], parameter_list, "test")
runtime = get_runtime()
computation = runtime.computation(function, *parameter_list)
result = computation(image_arr, filter_arr)[0]
expected = convolution2d(image_arr[0][0], filter_arr[0][0]).reshape(1, 1, 14, 14)
assert np.allclose(result, expected)
def test_get_constant_from_source_failed():
dtype = np.int
input1 = ov.opset8.parameter(Shape([5, 5]), dtype=dtype, name="input_1")
input2 = ov.opset8.parameter(Shape([1]), dtype=dtype, name="input_2")
reshape = ov.opset8.reshape(input1, input2, special_zero=True)
folded_const = ov.impl.util.get_constant_from_source(
reshape.input(1).get_source_output())
assert folded_const is None
def test_swish_props_with_beta():
float_dtype = np.float32
data = ov.parameter(Shape([3, 10]), dtype=float_dtype, name="data")
beta = ov.parameter(Shape([]), dtype=float_dtype, name="beta")
node = ov.swish(data, beta)
assert node.get_type_name() == "Swish"
assert node.get_output_size() == 1
assert list(node.get_output_shape(0)) == [3, 10]
assert node.get_output_element_type(0) == Type.f32
def test_get_constant_from_source_success():
dtype = np.int
input1 = ov.opset8.parameter(Shape([5, 5]), dtype=dtype, name="input_1")
input2 = ov.opset8.parameter(Shape([25]), dtype=dtype, name="input_2")
shape_of = ov.opset8.shape_of(input2, name="shape_of")
reshape = ov.opset8.reshape(input1, shape_of, special_zero=True)
folded_const = ov.impl.util.get_constant_from_source(
reshape.input(1).get_source_output())
assert folded_const is not None
assert folded_const.get_vector() == [25]
def test_evaluate():
param1 = ops.parameter(Shape([2, 1]), dtype=np.float32, name="data1")
param2 = ops.parameter(Shape([2, 1]), dtype=np.float32, name="data2")
add = ops.add(param1, param2)
func = Function(add, [param1, param2], "TestFunction")
input1 = np.array([2, 1], dtype=np.float32).reshape(2, 1)
input2 = np.array([3, 7], dtype=np.float32).reshape(2, 1)
out_tensor = Tensor("float32", Shape([2, 1]))
assert func.evaluate([out_tensor], [Tensor(input1), Tensor(input2)])
assert np.allclose(out_tensor.data, np.array([5, 8]).reshape(2, 1))
def test_gather_elements():
indices_type = np.int32
data_dtype = np.float32
data = ov.parameter(Shape([2, 5]), dtype=data_dtype, name="data")
indices = ov.parameter(Shape([2, 100]), dtype=indices_type, name="indices")
axis = 1
expected_shape = [2, 100]
node = ov.gather_elements(data, indices, axis)
assert node.get_type_name() == "GatherElements"
assert node.get_output_size() == 1
assert list(node.get_output_shape(0)) == expected_shape
assert node.get_output_element_type(0) == Type.f32
def test_validate_nodes_and_infer_types():
param1 = ops.parameter(Shape([2, 1]), dtype=np.float32, name="data1")
param2 = ops.parameter(Shape([2, 1]), dtype=np.float32, name="data2")
add = ops.add(param1, param2)
func = Function(add, [param1, param2], "TestFunction")
invalid_shape = Shape([3, 7])
param3 = ops.parameter(invalid_shape, dtype=np.float32, name="data3")
func.replace_parameter(0, param3)
with pytest.raises(RuntimeError) as e:
func.validate_nodes_and_infer_types()
assert "Argument shapes are inconsistent" in str(e.value)
def test_reshape():
element_type = Type.f32
shape = Shape([2, 3])
A = Parameter(element_type, shape)
parameter_list = [A]
function = Function([ov.reshape(A, Shape([3, 2]), special_zero=False)], parameter_list, "test")
runtime = get_runtime()
computation = runtime.computation(function, *parameter_list)
result = computation(np.array(np.array([[1, 2, 3], [4, 5, 6]], dtype=np.float32), dtype=np.float32))[0]
expected = np.reshape(np.array([[1, 2, 3], [4, 5, 6]], dtype=np.float32), (3, 2))
assert np.allclose(result, expected)
def test_evaluate_invalid_input_shape():
param1 = ops.parameter(Shape([2, 1]), dtype=np.float32, name="data1")
param2 = ops.parameter(Shape([2, 1]), dtype=np.float32, name="data2")
add = ops.add(param1, param2)
func = Function(add, [param1, param2], "TestFunction")
with pytest.raises(RuntimeError) as e:
assert func.evaluate(
[Tensor("float32", Shape([2, 1]))],
[
Tensor("float32", Shape([3, 1])),
Tensor("float32", Shape([3, 1]))
],
)
assert "must be compatible with the partial shape: {2,1}" in str(e.value)
def test_node_input():
shape = [2, 2]
parameter_a = ops.parameter(shape, dtype=np.float32, name="A")
parameter_b = ops.parameter(shape, dtype=np.float32, name="B")
model = parameter_a + parameter_b
model_inputs = model.inputs()
assert len(model_inputs) == 2
assert [input_node.get_index() for input_node in model_inputs] == [0, 1]
assert np.equal(
[input_node.get_element_type() for input_node in model_inputs],
model.get_element_type(),
).all()
assert np.equal(
[input_node.get_shape() for input_node in model_inputs], Shape(shape)
).all()
assert np.equal(
[input_node.get_partial_shape() for input_node in model_inputs],
PartialShape(shape),
).all()
input0 = model.input(0)
input1 = model.input(1)
assert [input0.get_index(), input1.get_index()] == [0, 1]
def test_output_shape(device):
core = Core()
func = core.read_model(model=test_net_xml, weights=test_net_bin)
exec_net = core.compile_model(func, device)
output = exec_net.output(0)
expected_shape = Shape([1, 10])
assert str(output.get_shape()) == str(expected_shape)
def test_const_output_get_shape(device):
core = Core()
func = core.read_model(model=test_net_xml, weights=test_net_bin)
exec_net = core.compile_model(func, device)
node = exec_net.input("data")
expected_shape = Shape([1, 3, 32, 32])
assert str(node.get_shape()) == str(expected_shape)
def test_node_output():
input_array = np.array([0, 1, 2, 3, 4, 5])
splits = 3
expected_shape = len(input_array) // splits
input_tensor = ops.constant(input_array, dtype=np.int32)
axis = ops.constant(0, dtype=np.int64)
split_node = ops.split(input_tensor, axis, splits)
split_node_outputs = split_node.outputs()
assert len(split_node_outputs) == splits
assert [output_node.get_index() for output_node in split_node_outputs] == [0, 1, 2]
assert np.equal(
[output_node.get_element_type() for output_node in split_node_outputs],
input_tensor.get_element_type(),
).all()
assert np.equal(
[output_node.get_shape() for output_node in split_node_outputs],
Shape([expected_shape]),
).all()
assert np.equal(
[output_node.get_partial_shape() for output_node in split_node_outputs],
PartialShape([expected_shape]),
).all()
output0 = split_node.output(0)
output1 = split_node.output(1)
output2 = split_node.output(2)
assert [output0.get_index(), output1.get_index(), output2.get_index()] == [0, 1, 2]
def test_hsigmoid():
float_dtype = np.float32
data = ov.parameter(Shape([3, 10]), dtype=float_dtype, name="data")
node = ov.hsigmoid(data)
assert node.get_type_name() == "HSigmoid"
assert node.get_output_size() == 1
assert list(node.get_output_shape(0)) == [3, 10]
assert node.get_output_element_type(0) == Type.f32
def test_log_softmax():
float_dtype = np.float32
data = ov.parameter(Shape([3, 10]), dtype=float_dtype, name="data")
node = ov.log_softmax(data, 1)
assert node.get_type_name() == "LogSoftmax"
assert node.get_output_size() == 1
assert list(node.get_output_shape(0)) == [3, 10]
assert node.get_output_element_type(0) == Type.f32
def test_select():
element_type = Type.f32
A = Parameter(Type.boolean, Shape([1, 2]))
B = Parameter(element_type, Shape([1, 2]))
C = Parameter(element_type, Shape([1, 2]))
parameter_list = [A, B, C]
function = Function([ov.select(A, B, C)], parameter_list, "test")
runtime = get_runtime()
computation = runtime.computation(function, *parameter_list)
result = computation(
np.array([[True, False]], dtype=np.bool),
np.array([[5, 6]], dtype=np.float32),
np.array([[7, 8]], dtype=np.float32),
)[0]
expected = np.array([[5, 8]])
assert np.allclose(result, expected)
def test_create_IENetwork_from_nGraph():
element_type = Type.f32
param = Parameter(element_type, Shape([1, 3, 22, 22]))
relu = ov.relu(param)
func = Function([relu], [param], "test")
cnnNetwork = IENetwork(func)
assert cnnNetwork is not None
func2 = cnnNetwork.get_function()
assert func2 is not None
assert len(func2.get_ops()) == 3
def test_constant():
element_type = Type.f32
parameter_list = []
function = Function([Constant(element_type, Shape([3, 3]), list(range(9)))], parameter_list, "test")
runtime = get_runtime()
computation = runtime.computation(function, *parameter_list)
result = computation()[0]
expected = np.arange(9).reshape(3, 3)
assert np.allclose(result, expected)
def test_concat():
element_type = Type.f32
A = Parameter(element_type, Shape([1, 2]))
B = Parameter(element_type, Shape([1, 2]))
C = Parameter(element_type, Shape([1, 2]))
parameter_list = [A, B, C]
axis = 0
function = Function([ov.concat([A, B, C], axis)], parameter_list, "test")
a_arr = np.array([[1, 2]], dtype=np.float32)
b_arr = np.array([[5, 6]], dtype=np.float32)
c_arr = np.array([[7, 8]], dtype=np.float32)
runtime = get_runtime()
computation = runtime.computation(function, *parameter_list)
result = computation(a_arr, b_arr, c_arr)[0]
expected = np.concatenate((a_arr, b_arr, c_arr), axis)
assert np.allclose(result, expected)
def make_constant_node(value: NumericData,
dtype: NumericType = None) -> Constant:
"""Return an ngraph Constant node with the specified value."""
ndarray = get_ndarray(value)
if dtype:
element_type = get_element_type(dtype)
else:
element_type = get_element_type(ndarray.dtype)
return Constant(element_type, Shape(ndarray.shape),
ndarray.flatten().tolist())
def test_partial_shape_equals():
ps1 = PartialShape.dynamic()
ps2 = PartialShape.dynamic()
assert ps1 == ps2
ps1 = PartialShape([1, 2, 3])
ps2 = PartialShape([1, 2, 3])
assert ps1 == ps2
shape = Shape([1, 2, 3])
ps = PartialShape([1, 2, 3])
assert shape == ps
def test_broadcast():
element_type = Type.f32
A = Parameter(element_type, Shape([3]))
parameter_list = [A]
function = Function([ov.broadcast(A, [3, 3])], parameter_list, "test")
runtime = get_runtime()
computation = runtime.computation(function, *parameter_list)
result = computation(np.array([1, 2, 3], dtype=np.float32))[0]
a_arr = np.array([[0], [0], [0]], dtype=np.float32)
b_arr = np.array([[1, 2, 3]], dtype=np.float32)
expected = np.add(a_arr, b_arr)
assert np.allclose(result, expected)
def test_round_away():
float_dtype = np.float32
data = ov.parameter(Shape([3, 10]), dtype=float_dtype, name="data")
node = ov.round(data, "HALF_AWAY_FROM_ZERO")
assert node.get_type_name() == "Round"
assert node.get_output_size() == 1
assert list(node.get_output_shape(0)) == [3, 10]
assert node.get_output_element_type(0) == Type.f32
input_tensor = np.array([-2.5, -1.5, -0.5, 0.5, 0.9, 1.5, 2.3, 2.5, 3.5], dtype=np.float32)
expected = [-3.0, -2.0, -1.0, 1.0, 1.0, 2.0, 2.0, 3.0, 4.0]
result = run_op_node([input_tensor], ov.round, "HALF_AWAY_FROM_ZERO")
assert np.allclose(result, expected)
def unary_op_exec(op_str, input_list):
"""
input_list needs to have deep length of 4
"""
element_type = Type.f32
shape = Shape(np.array(input_list).shape)
A = Parameter(element_type, shape)
parameter_list = [A]
function = Function([unary_op(op_str, A)], parameter_list, "test")
runtime = get_runtime()
computation = runtime.computation(function, *parameter_list)
result = computation(np.array(input_list, dtype=np.float32))[0]
expected = unary_op_ref(op_str, np.array(input_list, dtype=np.float32))
assert np.allclose(result, expected)
def binary_op_comparison(op_str):
element_type = Type.f32
shape = Shape([2, 2])
A = Parameter(element_type, shape)
B = Parameter(element_type, shape)
parameter_list = [A, B]
function = Function([binary_op(op_str, A, B)], parameter_list, "test")
a_arr = np.array([[1, 5], [3, 2]], dtype=np.float32)
b_arr = np.array([[2, 4], [3, 1]], dtype=np.float32)
runtime = get_runtime()
computation = runtime.computation(function, A, B)
result = computation(a_arr, b_arr)[0]
expected = binary_op_ref(op_str, a_arr, b_arr)
assert np.allclose(result, expected)
def roi_pooling(
input: NodeInput,
coords: NodeInput,
output_size: TensorShape,
spatial_scale: NumericData,
method: str,
name: Optional[str] = None,
) -> Node:
"""Return a node which produces an ROIPooling operation.
@param input: Input feature map {N, C, ...}
@param coords: Coordinates of bounding boxes
@param output_size: Height/Width of ROI output features (shape)
@param spatial_scale: Ratio of input feature map over input image size (float)
@param method: Method of pooling - string: "max" or "bilinear"
@return ROIPooling node
"""
method = method.lower()
return _get_node_factory_opset2().create(
"ROIPooling",
as_nodes(input, coords),
{"output_size": Shape(output_size), "spatial_scale": spatial_scale, "method": method},
)
def test_add_with_mul():
element_type = Type.f32
shape = Shape([4])
A = Parameter(element_type, shape)
B = Parameter(element_type, shape)
C = Parameter(element_type, shape)
parameter_list = [A, B, C]
function = Function([ov.multiply(ov.add(A, B), C)], parameter_list, "test")
runtime = get_runtime()
computation = runtime.computation(function, A, B, C)
result = computation(
np.array([1, 2, 3, 4], dtype=np.float32),
np.array([5, 6, 7, 8], dtype=np.float32),
np.array([9, 10, 11, 12], dtype=np.float32),
)[0]
a_arr = np.array([1, 2, 3, 4], dtype=np.float32)
b_arr = np.array([5, 6, 7, 8], dtype=np.float32)
c_arr = np.array([9, 10, 11, 12], dtype=np.float32)
result_arr_ref = (a_arr + b_arr) * c_arr
assert np.allclose(result, result_arr_ref)
def test_partial_shape():
ps = PartialShape([1, 2, 3, 4])
assert ps.is_static
assert not ps.is_dynamic
assert ps.rank == 4
assert repr(ps) == "<PartialShape: {1,2,3,4}>"
assert ps.get_dimension(0) == Dimension(1)
assert ps.get_dimension(1) == Dimension(2)
assert ps.get_dimension(2) == Dimension(3)
assert ps.get_dimension(3) == Dimension(4)
shape = Shape([1, 2, 3])
ps = PartialShape(shape)
assert ps.is_static
assert not ps.is_dynamic
assert ps.all_non_negative
assert ps.rank == 3
assert list(ps.get_shape()) == [1, 2, 3]
assert list(ps.get_max_shape()) == [1, 2, 3]
assert list(ps.get_min_shape()) == [1, 2, 3]
assert list(ps.to_shape()) == [1, 2, 3]
assert repr(shape) == "<Shape: {1, 2, 3}>"
assert repr(ps) == "<PartialShape: {1,2,3}>"
ps = PartialShape(
[Dimension(1),
Dimension(2),
Dimension(3),
Dimension.dynamic()])
assert not ps.is_static
assert ps.is_dynamic
assert ps.all_non_negative
assert ps.rank == 4
assert list(ps.get_min_shape()) == [1, 2, 3, 0]
assert list(ps.get_max_shape())[3] > 1000000000
assert repr(ps) == "<PartialShape: {1,2,3,?}>"
assert ps.get_dimension(0) == Dimension(1)
assert ps.get_dimension(1) == Dimension(2)
assert ps.get_dimension(2) == Dimension(3)
assert ps.get_dimension(3) == Dimension.dynamic()
ps = PartialShape([1, 2, 3, -1])
assert not ps.is_static
assert ps.is_dynamic
assert ps.all_non_negative
assert ps.rank == 4
assert list(ps.get_min_shape()) == [1, 2, 3, 0]
assert list(ps.get_max_shape())[3] > 1000000000
assert repr(ps) == "<PartialShape: {1,2,3,?}>"
ps = PartialShape.dynamic()
assert not ps.is_static
assert ps.is_dynamic
assert ps.rank == Dimension.dynamic()
assert list(ps.get_min_shape()) == []
assert list(ps.get_max_shape()) == []
assert repr(ps) == "<PartialShape: ?>"
ps = PartialShape.dynamic(r=Dimension(2))
assert not ps.is_static
assert ps.is_dynamic
assert ps.rank == 2
assert 2 == ps.rank
assert list(ps.get_min_shape()) == [0, 0]
assert list(ps.get_max_shape())[0] > 1000000000
assert repr(ps) == "<PartialShape: {?,?}>"