def test_image_scaler_remover(self): # type: () -> None
inputs = [("input", (1, 3, 50, 50))]
outputs = [("out", (1, 3, 50, 50), TensorProto.FLOAT)]
im_scaler = helper.make_node(
"ImageScaler",
inputs=["input"],
outputs=["scaler_out"],
bias=[10, -6, 20],
scale=3.0,
)
exp = helper.make_node("Exp", inputs=["scaler_out"], outputs=["out"])
onnx_model = _onnx_create_model([im_scaler, exp], inputs, outputs)
graph = Graph.from_onnx(onnx_model.graph, onnx_ir_version=5)
new_graph = graph.transformed([ImageScalerRemover()])
self.assertEqual(len(graph.nodes), 2)
self.assertEqual(len(new_graph.nodes), 1)
self.assertEqual(new_graph.nodes[0].inputs[0], "input")
self.assertEqual(new_graph.nodes[0].outputs[0], "out")
coreml_model = convert(onnx_model)
spec = coreml_model.get_spec()
self.assertEqual(
spec.neuralNetwork.preprocessing[0].scaler.channelScale, 3.0)
self.assertEqual(spec.neuralNetwork.preprocessing[0].scaler.blueBias,
20.0)
self.assertEqual(spec.neuralNetwork.preprocessing[0].scaler.greenBias,
-6.0)
self.assertEqual(spec.neuralNetwork.preprocessing[0].scaler.redBias,
10.0)
def test_dropout_remover(self): # type: () -> None
inputs = [("input", (1, 3, 50, 50))]
outputs = [("out", (1, 5, 50, 50), TensorProto.FLOAT)]
weight = numpy_helper.from_array(_random_array((5, 3, 1, 1)),
name="weight")
conv = helper.make_node(
"Conv",
inputs=["input", "weight"],
outputs=["conv_output"],
kernel_shape=(1, 1),
strides=(1, 1),
)
drop = helper.make_node(
"Dropout",
inputs=["conv_output"],
outputs=["drop_output"],
)
exp = helper.make_node("Exp", inputs=["drop_output"], outputs=["out"])
onnx_model = _onnx_create_model([conv, drop, exp], inputs, outputs)
graph = Graph.from_onnx(onnx_model.graph, onnx_ir_version=5)
new_graph = graph.transformed([DropoutRemover()])
self.assertEqual(len(graph.nodes), 3)
self.assertEqual(len(new_graph.nodes), 2)
self.assertEqual(new_graph.nodes[0].inputs[0], "input")
self.assertEqual(new_graph.nodes[1].inputs[0],
new_graph.nodes[0].outputs[0])
self.assertEqual(new_graph.nodes[1].outputs[0], "out")
def test_fuse_conv_without_bias(self): # type: () -> None
kernel_shape = (3, 2)
strides = (2, 3)
pads = (4, 2, 4, 2)
dilations = (1, 2)
group = 1
weight = numpy_helper.from_array(_random_array((16, 3, 3, 2)),
name="weight")
input_shape = (1, 3, 224, 224)
output_size = _conv_pool_output_size(input_shape, dilations,
kernel_shape, pads, strides)
output_shape = (1, int(weight.dims[0]), output_size[0], output_size[1])
inputs = [("input0", input_shape)]
outputs = [("output0", output_shape, TensorProto.FLOAT)]
conv = helper.make_node(
"Conv",
inputs=[inputs[0][0], "weight"],
outputs=["conv_output"],
dilations=dilations,
group=group,
kernel_shape=kernel_shape,
pads=pads,
strides=strides,
)
b = _random_array((int(weight.dims[0]), ))
bias = numpy_helper.from_array(b, name="bias")
add = helper.make_node(
"Add",
inputs=[conv.output[0], "bias"],
outputs=[outputs[0][0]],
broadcast=1,
axis=1,
)
model = _onnx_create_model([conv, add], inputs, outputs,
[weight, bias])
graph_ = Graph.from_onnx(model.graph, onnx_ir_version=5)
fused_graph = graph_.transformed([ConvAddFuser()])
self.assertEqual(len(fused_graph.nodes), 1)
node = fused_graph.nodes[0]
self.assertEqual(len(node.inputs), 3)
npt.assert_equal(node.input_tensors[node.inputs[2]], b)
self.assertEqual(fused_graph.nodes[0].outputs[0], outputs[0][0])
def test_cast_op_remover(self):
inputs = [("input", (1, 16, 224, 224))]
outputs = [("output", (1, 1, 224, 224), TensorProto.FLOAT)]
conv = helper.make_node(
"Conv",
name="Conv_1",
inputs=["input", "weight"],
outputs=["conv_output"],
kernel_shape=(3, 3),
strides=(1, 1),
)
cast_1 = helper.make_node(
"Cast",
name="Cast_1",
inputs=["conv_output"],
outputs=["cast_1_output"],
to=1
)
sigmoid = helper.make_node(
"Sigmoid",
name="Sigmoid_1",
inputs=["cast_1_output"],
outputs=["sigmoid_output"],
)
cast_2 = helper.make_node(
"Cast",
name="Cast_2",
inputs=["sigmoid_output"],
outputs=["output"],
to=1
)
value_info = [
("input", (1, 16, 224, 224), TensorProto.FLOAT),
("conv_output", (1, 1, 224, 224), TensorProto.FLOAT),
("cast_1_output", (1, 1, 224, 224), TensorProto.FLOAT),
("sigmoid_output", (1, 1, 224, 224), TensorProto.FLOAT),
]
onnx_model = _onnx_create_model([conv, cast_1, sigmoid, cast_2], inputs, outputs, value_info=value_info)
graph = Graph.from_onnx(onnx_model.graph, onnx_ir_version=5)
new_graph = graph.transformed([CastOpRemover()])
# The last Cast operation should not be removed
self.assertEqual(len(graph.nodes), 4)
self.assertEqual(len(new_graph.nodes), 3)
self.assertEqual(new_graph.nodes[0].inputs[0], "input")
self.assertEqual(new_graph.nodes[1].inputs[0], new_graph.nodes[0].outputs[0])
self.assertEqual(new_graph.nodes[2].outputs[0], "output")
def test_create_graph(self): # type: () -> None
kernel_shape = (3, 2)
strides = (2, 3)
pads = (4, 2, 4, 2)
dilations = (1, 2)
group = 1
weight = numpy_helper.from_array(_random_array((16, 3, 3, 2)),
name="weight")
input_shape = (1, 3, 224, 224)
output_size = _conv_pool_output_size(input_shape, dilations,
kernel_shape, pads, strides)
output_shape = (1, int(weight.dims[0]), output_size[0], output_size[1])
inputs = [("input0", input_shape)]
outputs = [("output0", output_shape, TensorProto.FLOAT)]
conv = helper.make_node(
"Conv",
inputs=[inputs[0][0], "weight"],
outputs=["conv_output"],
dilations=dilations,
group=group,
kernel_shape=kernel_shape,
pads=pads,
strides=strides,
)
relu = helper.make_node("Relu",
inputs=[conv.output[0]],
outputs=[outputs[0][0]])
model = _onnx_create_model([conv, relu], inputs, outputs, [weight])
graph_ = Graph.from_onnx(model.graph, onnx_ir_version=5)
self.assertTrue(len(graph_.inputs) == 1)
self.assertEqual(graph_.inputs[0][2], input_shape)
self.assertTrue(len(graph_.outputs) == 1)
self.assertEqual(graph_.outputs[0][2], output_shape)
self.assertTrue(len(graph_.nodes) == 2)
self.assertEqual(len(graph_.nodes[0].parents), 0)
self.assertEqual(len(graph_.nodes[1].parents), 1)
self.assertEqual(len(graph_.nodes[0].children), 1)
self.assertEqual(len(graph_.nodes[1].children), 0)