def test_auto_image_nhwc_input_names(self):
x_shape = (4, 5, 3)
@make_tf_graph([x_shape])
def build_model(x):
return tf.nn.relu(x)
model, inputs, outputs = build_model
mlmodel = converter.convert(model, inputs=[ImageType()])
assert mlmodel is not None
def test_auto_image_nchw_input_names(self):
x_shape = (3, 4, 5)
@make_tf_graph([x_shape])
def build_model(x):
return tf.nn.relu(x)
model, inputs, outputs = build_model
mlmodel = converter.convert(model, inputs=[ImageType(channel_first=True)])
assert mlmodel is not None
def test_auto_image_nhwc_input_names():
x_shape = (4, 5, 3)
@make_tf_graph([x_shape])
def build_model(x):
return tf.nn.relu(x)
model, inputs, outputs = build_model
mlmodel = converter.convert(model, inputs=[ImageType()])
if mlmodel is None:
raise AssertionError
def test_fusion_with_image_full(self):
@mb.program(input_specs=[mb.TensorSpec(shape=(10, 20, 30, 3))])
def prog(x):
x1 = mb.transpose(x=x, perm=[0, 3, 1, 2])
x2 = mb.relu(x=x)
x3 = mb.transpose(x=x2, perm=[0, 3, 1, 2])
x4 = mb.add(x=x1, y=x3)
return mb.relu(x=x4)
proto = converter._convert(prog, inputs=[ImageType(name="x", shape=(10, 20, 30, 3), channel_first=False)], convert_from="mil", convert_to="nn_proto")
model = models.MLModel(proto)
assert model is not None
assert len(model._spec.neuralNetwork.layers) == 3
def test_fusion_with_image_intermediate_graph(self):
@mb.program(input_specs=[mb.TensorSpec(shape=(10, 20, 30, 3))])
def prog(x):
x1 = mb.transpose(x=x, perm=[0, 3, 1, 2])
x2 = mb.relu(x=x)
x3 = mb.transpose(x=x2, perm=[0, 3, 1, 2])
x4 = mb.add(x=x1, y=x3)
return mb.relu(x=x4)
prog.main_input_types = [ImageType(name="x", shape=(10, 20, 30, 3), channel_first=False)]
prev_prog, prev_block, block = apply_pass_and_basic_check(
prog, "common::image_input_preprocess"
)
self.assertEqual(get_op_types_in_program(prev_prog), ["transpose", "relu", "transpose", "add", "relu"])
self.assertEqual(get_op_types_in_program(prog), ["transpose", "transpose", "relu", "transpose", "add", "relu"])
def test_fusion_with_image_full(self):
from coremltools.converters._converters_entry import convert
@mb.program(input_specs=[mb.TensorSpec(shape=(10, 20, 30, 3))])
def prog(x):
x1 = mb.transpose(x=x, perm=[0, 3, 1, 2])
x2 = mb.relu(x=x)
x3 = mb.transpose(x=x2, perm=[0, 3, 1, 2])
x4 = mb.add(x=x1, y=x3)
return mb.relu(x=x4)
mlmodel = convert(prog,
inputs=[
ImageType(name="x",
shape=(10, 20, 30, 3),
channel_first=False)
],
source="mil",
convert_to="nn_proto")
assert mlmodel is not None
assert len(mlmodel.get_spec().neuralNetwork.layers) == 3
def test_fusion_with_image_full():
@mb.program(input_specs=[mb.TensorSpec(shape=(10, 20, 30, 3))])
def prog(x):
x1 = mb.transpose(x=x, perm=[0, 3, 1, 2])
x2 = mb.relu(x=x)
x3 = mb.transpose(x=x2, perm=[0, 3, 1, 2])
x4 = mb.add(x=x1, y=x3)
return mb.relu(x=x4)
mlmodel = ct.convert(prog,
inputs=[
ImageType(name="x",
shape=(10, 20, 30, 3),
channel_first=False)
],
source="mil",
convert_to="nn_proto")
if mlmodel is None:
raise AssertionError
if len(mlmodel.get_spec().neuralNetwork.layers) != 3:
raise AssertionError
