def test_cast(self):
if legacy_onnx_pre_ver(1, 2) or legacy_opset_pre_ver(6):
test_cases = [("FLOAT", tf.float32), ("UINT8", tf.uint8),
("INT8", tf.int8), ("UINT16", tf.uint16),
("INT16", tf.int16), ("INT32", tf.int32),
("INT64", tf.int64), ("BOOL", tf.bool),
("FLOAT16", tf.float16), ("DOUBLE", tf.float64),
("COMPLEX64", tf.complex64),
("COMPLEX128", tf.complex128)]
else:
test_cases = [(TensorProto.FLOAT, tf.float32),
(TensorProto.UINT8, tf.uint8),
(TensorProto.INT8, tf.int8),
(TensorProto.UINT16, tf.uint16),
(TensorProto.INT16, tf.int16),
(TensorProto.INT32, tf.int32),
(TensorProto.INT64, tf.int64),
(TensorProto.BOOL, tf.bool),
(TensorProto.FLOAT16, tf.float16),
(TensorProto.DOUBLE, tf.float64),
(TensorProto.COMPLEX64, tf.complex64),
(TensorProto.COMPLEX128, tf.complex128)]
for ty, tf_type in test_cases:
node_def = helper.make_node("Cast", ["input"], ["output"], to=ty)
vector = [2, 3]
output = run_node(node_def, [vector])
np.testing.assert_equal(output["output"].dtype, tf_type)
def test_tile(self):
if legacy_onnx_pre_ver(1, 2):
raise unittest.SkipTest(
"The current version of ONNX does not record correctly the opset of Tile."
)
node_def = helper.make_node("Tile", ["X1", "X2"], ["Z"])
x = self._get_rnd([3, 5, 5, 3])
repeats = [1, 1, 2, 1]
output = run_node(node_def, [x, repeats])
np.testing.assert_allclose(output["Z"], np.tile(x, repeats), rtol=1e-3)
def test_convert_to_tf(self):
if legacy_onnx_pre_ver(1, 2, 1):
raise unittest.SkipTest(
"The current version of ONNX uses dead model link.")
for model_name, url in _ONNX_MODELS:
model_dir = self.prepare_model(model_name, url)
subprocess.check_call([
"onnx-tf",
"convert",
"-i",
os.path.join(model_dir, '{}.onnx'.format(model_name)),
"-o",
os.path.join(model_dir, '{}.pb'.format(model_name)),
])
def prepare_model(model_name, url):
if legacy_onnx_pre_ver(1, 5, 0):
prepare_model_data = Runner._prepare_model_data
else:
prepare_model_data = Runner.prepare_model_data
if IS_PYTHON3:
params = list(
inspect.signature(prepare_model_data).parameters.keys())
else:
params = inspect.getargspec(prepare_model_data).args
runner_class = Runner
if params[0] == "self":
runner_class = Runner(TensorflowBackend)
if legacy_onnx_pre_ver(1, 5, 0):
prepare_model_data = runner_class._prepare_model_data
else:
prepare_model_data = runner_class.prepare_model_data
if legacy_onnx_pre_ver(1, 4, 0):
tc = TestCase(name="test_{}".format(model_name),
model_name=model_name,
url=url,
model_dir=None,
model=None,
data_sets=None,
kind='real')
else:
tc = TestCase(name="test_{}".format(model_name),
model_name=model_name,
url=url,
model_dir=None,
model=None,
data_sets=None,
kind='real',
rtol=1e-3,
atol=1e-7)
return prepare_model_data(model_test=tc)
def test_initializer(self):
if legacy_onnx_pre_ver(1, 2):
raise unittest.SkipTest(
"The current version of ONNX does not record correctly the opset of Cast."
)
X = np.array([[1, 2], [3, 4]]).astype(np.float32)
Y = np.array([[1, 2], [3, 4]]).astype(np.float32)
weight = np.array([[1, 0], [0, 1]])
graph_def = helper.make_graph(
[
helper.make_node("Add", ["X", "Y"], ["Z0"]),
helper.make_node("Cast", ["Z0"], ["Z"], to=TensorProto.FLOAT),
helper.make_node("Mul", ["Z", "weight"], ["W"]),
helper.make_node("Tanh", ["W"], ["W1"]),
helper.make_node("Sigmoid", ["W1"], ["W2"])
],
name="test_initializer",
inputs=[
helper.make_tensor_value_info("X", TensorProto.FLOAT, (2, 2)),
helper.make_tensor_value_info("Y", TensorProto.FLOAT, (2, 2)),
helper.make_tensor_value_info("weight", TensorProto.FLOAT,
(2, 2)),
],
outputs=[
helper.make_tensor_value_info("W2", TensorProto.FLOAT, (2, 2))
],
initializer=[
helper.make_tensor("weight", TensorProto.FLOAT, [2, 2],
weight.flatten().astype(float))
])
def sigmoid(x):
return 1 / (1 + np.exp(-x))
W_ref = sigmoid(np.tanh((X + Y) * weight))
tf_rep = prepare(helper.make_model(graph_def))
output = tf_rep.run({"X": X, "Y": Y})
np.testing.assert_almost_equal(output["W2"], W_ref)
# TF session run does not support sequence/RaggedTensor as model inputs
backend_test.exclude(r'test_loop13_seq[a-z,_]*')
# TF minimum/maximum do not support uint64 when auto-cast is False (default)
backend_test.exclude(r'test_min_uint64_[a-z,_]*')
backend_test.exclude(r'test_max_uint64_[a-z,_]*')
if legacy_opset_pre_ver(7):
backend_test.exclude(r'[a-z,_]*Upsample[a-z,_]*')
if 'TRAVIS' in os.environ:
backend_test.exclude('test_vgg19')
backend_test.exclude('zfnet512')
if legacy_onnx_pre_ver(1, 2):
# These following tests fails by a tiny margin with onnx<1.2:
backend_test.exclude('test_operator_add_broadcast_cpu')
backend_test.exclude('test_operator_add_size1_broadcast_cpu')
backend_test.exclude('test_operator_add_size1_right_broadcast_cpu')
backend_test.exclude('test_operator_add_size1_singleton_broadcast_cpu')
backend_test.exclude('test_averagepool_3d_default_cpu')
# Do not support consumed flag:
backend_test.exclude('test_batch_normalization')
# Do not support RNN testing on onnx<1.2 due to incorrect tests:
backend_test.exclude(r'test_operator_rnn_cpu')
backend_test.exclude(r'test_operator_lstm_cpu')
backend_test.exclude(r'test_operator_rnn_single_layer_cpu')
# The onnx test for cast, float to string, does not work
if not legacy_opset_pre_ver(9):