def _test_one_to_one_operator_coreml(self, keras_model, x):
# Verify Keras-to-CoreML-to-ONNX path
coreml_model = None
try:
coreml_model = coremltools.converters.keras.convert(keras_model)
except (AttributeError, ImportError) as e:
warnings.warn(
"Unable to test due to an error in coremltools '{0}'".format(
e))
onnx_model = None if coreml_model is None else onnxmltools.convert_coreml(
coreml_model)
self.assertTrue(onnx_model or coreml_model is None)
if self._no_available_inference_engine():
return
y_reference = keras_model.predict(x)
y_produced = evaluate_deep_model(onnx_model, x)
self.assertTrue(np.allclose(y_reference, y_produced))
# Verify Keras-to-ONNX path
onnx_model = onnxmltools.convert_keras(keras_model)
y_produced = evaluate_deep_model(onnx_model, x)
self.assertTrue(np.allclose(y_reference, y_produced))
def _test_one_to_one_operator_coreml_channels_last(self, keras_model, x):
'''
There are two test paths. One is Keras-->CoreML-->ONNX and the other one is Keras-->ONNX.
Keras-->CoreML-->ONNX:
Keras computation path:
[N, C, H, W] ---> numpy transpose ---> [N, H, W, C] ---> keras convolution --->
[N, H, W, C] ---> numpy transpose ---> [N, C, H, W]
ONNX computation path:
[N, C, H, W] ---> ONNX convolution ---> [N, C, H, W]
The reason for having extra transpose's in the Keras path is that CoreMLTools doesn't not handle channels_last
flag properly. Precisely, oreMLTools always converts Conv2D under channels_first mode.
Keras-->ONNX
Keras computation path:
[N, C, H, W] ---> numpy transpose ---> [N, H, W, C] ---> keras convolution --->
[N, H, W, C]
ONNX computation path:
[N, C, H, W] ---> numpy transpose ---> [N, H, W, C] ---> ONNX convolution ---> [N, H, W, C]
'''
# Verify Keras-to-CoreML-to-ONNX path
coreml_model = None
try:
coreml_model = coremltools.converters.keras.convert(keras_model)
except (AttributeError, ImportError) as e:
warnings.warn(
"Unable to test due to an error in coremltools '{0}'.".format(
e))
onnx_model_p1 = None if coreml_model is None else onnxmltools.convert_coreml(
coreml_model)
onnx_model_p2 = onnxmltools.convert_keras(keras_model)
self.assertTrue(onnx_model_p1 or coreml_model is None)
self.assertTrue(onnx_model_p2)
if self._no_available_inference_engine():
return
if isinstance(x, list):
x_t = [np.transpose(_, [0, 2, 3, 1]) for _ in x]
else:
x_t = np.transpose(x, [0, 2, 3, 1])
y_reference = np.transpose(keras_model.predict(x_t), [0, 3, 1, 2])
y_produced = evaluate_deep_model(onnx_model_p1, x)
self.assertTrue(np.allclose(y_reference, y_produced))
# Verify Keras-to-ONNX path
y_reference = np.transpose(y_reference, [0, 2, 3, 1])
y_produced = evaluate_deep_model(onnx_model_p2, x_t)
self.assertTrue(np.allclose(y_reference, y_produced, atol=1e-6))
def test_recursive_model(self):
N, C, D = 2, 3, 3
x = create_tensor(N, C)
sub_input1 = Input(shape=(C, ))
sub_mapped1 = Dense(D)(sub_input1)
sub_model1 = Model(inputs=sub_input1, outputs=sub_mapped1)
sub_input2 = Input(shape=(C, ))
sub_mapped2 = Dense(D)(sub_input2)
sub_model2 = Model(inputs=sub_input2, outputs=sub_mapped2)
input1 = Input(shape=(D, ))
input2 = Input(shape=(D, ))
mapped1_2 = sub_model1(input1)
mapped2_2 = sub_model2(input2)
sub_sum = Add()([mapped1_2, mapped2_2])
keras_model = Model(inputs=[input1, input2], output=sub_sum)
try:
coreml_model = coremltools.converters.keras.convert(keras_model)
except (AttributeError, ImportError) as e:
warnings.warn(
"Unable to test due to an error in coremltools '{0}'".format(
e))
return
onnx_model = onnxmltools.convert_coreml(coreml_model)
x = [x, 2 * x]
y_reference = keras_model.predict(x)
y_produced = evaluate_deep_model(onnx_model, x).reshape(N, D)
def _test_one_to_one_operator_core_keras(self, keras_model, x):
y_reference = keras_model.predict(x)
onnx_model = onnxmltools.convert_keras(keras_model)
if find_keras_backend():
y_produced = evaluate_deep_model(onnx_model, x)
self.assertTrue(np.allclose(y_reference, y_produced))
else:
warnings.warn("cntk or caffe2 are not available")
def _test_one_to_one_operator_keras(self, keras_model, x):
y_reference = keras_model.predict(x)
onnx_model = onnxmltools.convert_keras(keras_model)
if not self._no_available_inference_engine():
y_produced = evaluate_deep_model(onnx_model, x)
self.assertTrue(np.allclose(y_reference, y_produced))
else:
self.assertIsNotNone(onnx_model)
warnings.warn("None of onnx inference engine is available.")
if self._no_available_inference_engine():
return
def test_flatten(self):
N, C, H, W, D = 2, 3, 1, 2, 2
x = create_tensor(N, C, H, W)
keras_model = Sequential()
keras_model.add(Flatten(input_shape=(H, W, C)))
keras_model.add(Dense(D))
keras_model.compile(optimizer='adagrad', loss='mse')
try:
coreml_model = coremltools.converters.keras.convert(keras_model)
except ImportError:
warnings.warn("Issue in coremltools.")
return
onnx_model = onnxmltools.convert_coreml(coreml_model)
y_reference = keras_model.predict(np.transpose(x, [0, 2, 3, 1]))
y_produced = evaluate_deep_model(onnx_model, x).reshape(N, D)
self.assertTrue(np.allclose(y_reference, y_produced))
def test_dense(self):
N, C, D = 2, 3, 2
x = create_tensor(N, C)
input = Input(shape=(C, ))
result = Dense(D)(input)
keras_model = Model(inputs=input, outputs=result)
keras_model.compile(optimizer='adagrad', loss='mse')
try:
coreml_model = coremltools.converters.keras.convert(keras_model)
except (AttributeError, ImportError) as e:
warnings.warn(
"Unable to test due to an error in coremltools '{0}'.".format(
e))
return
onnx_model = onnxmltools.convert_coreml(coreml_model)
y_reference = keras_model.predict(x)
y_produced = evaluate_deep_model(onnx_model, x).reshape(N, D)
self.assertTrue(np.allclose(y_reference, y_produced))
