def test_onnx_example_cdist_bigger(self):
from skl2onnx.algebra.complex_functions import onnx_cdist
data = load_iris()
X, y = data.data, data.target
self.assertNotEmpty(y)
X_train = X[::2]
# y_train = y[::2]
X_test = X[1::2]
# y_test = y[1::2]
onx = OnnxIdentity(onnx_cdist(OnnxIdentity(
'X', op_version=get_opset_number_from_onnx()),
X_train.astype(numpy.float32),
metric="euclidean",
dtype=numpy.float32,
op_version=get_opset_number_from_onnx()),
output_names=['Y'],
op_version=get_opset_number_from_onnx())
final = onx.to_onnx(inputs=[('X', FloatTensorType([None, None]))],
outputs=[('Y', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(final, runtime="python")
res = oinf.run({'X': X_train.astype(numpy.float32)})['Y']
exp = scipy_cdist(X_train, X_train, metric="euclidean")
self.assertEqualArray(exp, res, decimal=6)
res = oinf.run({'X': X_test.astype(numpy.float32)})['Y']
exp = scipy_cdist(X_test, X_train, metric="euclidean")
self.assertEqualArray(exp, res, decimal=6)
def test_onnxrt_string_normalizer_stopwords(self):
corpus = numpy.array([
'This is the first document.',
'This document is the second document.',
'And this is the third one.', 'Is this the first document?'
])
op = OnnxStringNormalizer('text',
op_version=get_opset_number_from_onnx(),
output_names=['out'],
stopwords=['this'])
onx = op.to_onnx(inputs=[('text', StringTensorType())])
oinf = OnnxInference(onx)
res = oinf.run({'text': corpus})
self.assertEqual(list(res['out']),
list(_.replace("this ", "") for _ in corpus))
op = OnnxStringNormalizer('text',
op_version=get_opset_number_from_onnx(),
output_names=['out'],
stopwords=['this'],
case_change_action='LOWER',
is_case_sensitive=0)
onx = op.to_onnx(inputs=[('text', StringTensorType())])
oinf = OnnxInference(onx)
res = oinf.run({'text': corpus})
self.assertEqual(list(res['out']),
list(_.lower().replace("this ", "") for _ in corpus))
def test_pipeline_add(self):
iris = load_iris()
X, y = iris.data, iris.target
pca = PCA(n_components=2)
pca.fit(X)
add = OnnxAdd('X', numpy.full((1, X.shape[1]), 1, dtype=numpy.float32),
output_names=['Yadd'],
op_version=get_opset_number_from_onnx())
onx = add.to_onnx(inputs=[('X', FloatTensorType((None, X.shape[1])))],
outputs=[('Yadd', FloatTensorType((None, X.shape[1])))])
tr = OnnxTransformer(onx)
tr.fit()
pipe = make_pipeline(tr, LogisticRegression())
pipe.fit(X, y)
pred = pipe.predict(X)
self.assertEqual(pred.shape, (150, ))
model_onnx = to_onnx(pipe, X.astype(numpy.float32),
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_onnx)
y1 = pipe.predict(X)
y2 = oinf.run({'X': X.astype(numpy.float32)})
self.assertEqual(list(y2), ['output_label', 'output_probability'])
self.assertEqualArray(y1, y2['output_label'])
y1 = pipe.predict_proba(X)
probas = DataFrame(list(y2['output_probability'])).values
self.assertEqualArray(y1, probas, decimal=5)
def test_pdist(self):
from skl2onnx.algebra.complex_functions import onnx_squareform_pdist
x = numpy.array([1, 2, 4, 5, 5, 4]).astype(numpy.float32).reshape(
(3, 2))
cop = OnnxAdd('input',
'input',
op_version=get_opset_number_from_onnx())
cdist = onnx_squareform_pdist(cop,
dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
cop2 = OnnxIdentity(cdist,
output_names=['cdist'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx({'input': FloatTensorType()},
outputs=[('cdist', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
sess = OnnxInference(model_def)
res = sess.run({'input': x})
self.assertEqual(list(res.keys()), ['cdist'])
exp = squareform(pdist(x * 2, metric="sqeuclidean"))
self.assertEqualArray(exp, res['cdist'])
x = numpy.array([1, 2, 4, 5, 5, 4]).astype(numpy.float32).reshape(
(2, 3))
res = sess.run({'input': x})
self.assertEqual(list(res.keys()), ['cdist'])
def test_onnx_remove_identities2(self):
from skl2onnx.algebra.complex_functions import onnx_squareform_pdist
x = numpy.array([1, 2, 4, 5, 5, 4]).astype(numpy.float32).reshape(
(3, 2))
cop = OnnxIdentity('input', op_version=get_opset_number_from_onnx())
cdist = onnx_squareform_pdist(cop,
dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
cop2 = OnnxIdentity(cdist,
output_names=['cdist'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx({'input': FloatTensorType()},
outputs=[('cdist', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
stats = onnx_statistics(model_def, optim=False)
self.assertIn('subgraphs', stats)
self.assertGreater(stats['subgraphs'], 1)
self.assertGreater(stats['op_Identity'], 2)
new_model = onnx_remove_node_identity(model_def)
stats2 = onnx_statistics(new_model, optim=False)
self.assertEqual(stats['subgraphs'], stats2['subgraphs'])
self.assertLesser(stats2['op_Identity'], 2)
oinf1 = OnnxInference(model_def)
oinf2 = OnnxInference(new_model)
y1 = oinf1.run({'input': x})['cdist']
y2 = oinf2.run({'input': x})['cdist']
self.assertEqualArray(y1, y2)
self.assertLesser(stats2['op_Identity'], 1)
def test_kernel_ker2_def_ort(self):
ker = Sum(
CK(0.1, (1e-3, 1e3)) * RBF(length_scale=10,
length_scale_bounds=(1e-3, 1e3)),
CK(0.1, (1e-3, 1e3)) * RBF(length_scale=1,
length_scale_bounds=(1e-3, 1e3)))
onx = convert_kernel(ker, 'X', output_names=['Y'], dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
model_onnx = onx.to_onnx(
inputs=[('X', FloatTensorType([None, None]))],
outputs=[('Y', FloatTensorType([None, None]))],
target_opset=get_opset_number_from_onnx())
model_onnx.ir_version = get_ir_version_from_onnx()
sess = _capture_output(
lambda: OnnxInference(model_onnx.SerializeToString(),
runtime="onnxruntime2"), 'c')[0]
try:
res = sess.run({'X': Xtest_.astype(numpy.float32)})
except RuntimeError as e:
if "Got invalid dimensions for input" in str(e):
# probable bug somewhere
return
raise e
m1 = res['Y']
m2 = ker(Xtest_)
self.assertEqualArray(m1, m2, decimal=5)
def test_onnxt_idi(self):
idi = numpy.identity(2)
onx = OnnxAdd('X', idi, output_names=['Y'],
op_version=get_opset_number_from_onnx())
model_def = onx.to_onnx({'X': idi.astype(numpy.float32)},
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def)
res = str(oinf)
self.assertIn('op_type: "Add"', res)
sb = model_def.SerializeToString()
oinf = OnnxInference(sb)
res = str(oinf)
self.assertIn('op_type: "Add"', res)
sb = BytesIO(model_def.SerializeToString())
oinf = OnnxInference(sb)
res = str(oinf)
self.assertIn('op_type: "Add"', res)
temp = get_temp_folder(__file__, "temp_onnxrt_idi")
name = os.path.join(temp, "m.onnx")
with open(name, "wb") as f:
f.write(model_def.SerializeToString())
oinf = OnnxInference(name)
res = str(oinf)
self.assertIn('op_type: "Add"', res)
def test_onnx_example_cdist_in_euclidean(self):
x2 = numpy.array([1.1, 2.1, 4.01, 5.01, 5.001, 4.001, 0,
0]).astype(numpy.float32).reshape((4, 2))
cop = OnnxAdd('input',
'input',
op_version=get_opset_number_from_onnx())
cop2 = OnnxIdentity(onnx_cdist(
cop,
x2,
dtype=numpy.float32,
metric='euclidean',
op_version=get_opset_number_from_onnx()),
output_names=['cdist'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx(inputs=[('input',
FloatTensorType([None, None]))],
outputs=[('cdist', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
new_model = onnx_remove_node_identity(model_def)
stats = onnx_statistics(model_def, optim=False)
stats2 = onnx_statistics(new_model, optim=False)
self.assertEqual(stats.get('op_Identity', 0), 3)
self.assertEqual(stats2.get('op_Identity', 0), 1)
def test_export_sklearn_kernel_rational_quadratic(self):
def kernel_rational_quadratic_none(X,
length_scale=1.0,
alpha=2.0,
op_version=None):
dists = squareform_pdist(X,
metric='sqeuclidean',
op_version=op_version)
cst = py_pow(length_scale, 2, op_version=op_version)
cst = py_mul(cst, alpha, 2, op_version=op_version)
t_cst = py_make_float_array(cst)
tmp = dists / t_cst
t_one = py_make_float_array(1)
base = tmp + t_one
t_alpha = py_make_float_array(py_opp(alpha, op_version=op_version))
K = numpy.power(base, t_alpha)
return K
x = numpy.array([[1, 2], [3, 4], [5, 6]], dtype=float)
kernel = RationalQuadratic(length_scale=1.0, alpha=2.0)
exp = kernel(x, None)
got = kernel_rational_quadratic_none(
x,
length_scale=1.0,
alpha=2.0,
op_version=get_opset_number_from_onnx())
self.assertEqualArray(exp, got)
fct = translate_fct2onnx(kernel_rational_quadratic_none,
cpl=True,
output_names=['Z'],
dtype=numpy.float32)
r = fct('X',
dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
self.assertIsInstance(r, OnnxIdentity)
inputs = {'X': x.astype(numpy.float32)}
try:
onnx_g = r.to_onnx(inputs)
except RuntimeError as e:
if "Opset number 12 is higher than targeted opset 11" in str(e):
return
raise e
oinf = OnnxInference(onnx_g)
res = oinf.run(inputs)
self.assertEqualArray(exp, res['Z'])
exp = kernel(x.T, None)
got = kernel_rational_quadratic_none(x.T)
self.assertEqualArray(exp, got)
inputs = {'X': x.T.astype(numpy.float32)}
res = oinf.run(inputs)
self.assertEqualArray(exp, res['Z'])
def test_onnxt_json(self):
idi = numpy.identity(2)
idi2 = numpy.identity(2) * 2
onx = OnnxAdd(
OnnxAdd('X', idi, op_version=get_opset_number_from_onnx()),
idi2, output_names=['Y'],
op_version=get_opset_number_from_onnx())
model_def = onx.to_onnx({'X': idi.astype(numpy.float32)},
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def)
js = oinf.to_json()
self.assertIn('"initializers": {', js)
def test_kernel_ker12_def(self):
ker = (Sum(CK(0.1, (1e-3, 1e3)), CK(0.1, (1e-3, 1e3)) *
RBF(length_scale=1, length_scale_bounds=(1e-3, 1e3))))
onx = convert_kernel(ker, 'X', output_names=['Y'], dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
model_onnx = onx.to_onnx(
inputs=[('X', FloatTensorType([None, None]))],
outputs=[('Y', FloatTensorType([None, None]))],
target_opset=get_opset_number_from_onnx())
sess = OnnxInference(model_onnx.SerializeToString())
res = sess.run({'X': Xtest_.astype(numpy.float32)})
m1 = res['Y']
m2 = ker(Xtest_)
self.assertEqualArray(m1, m2)
def test_onnxt_run(self):
idi = numpy.identity(2, dtype=numpy.float32)
idi2 = (numpy.identity(2) * 2).astype(numpy.float32)
onx = OnnxAdd(
OnnxAdd('X', idi, op_version=get_opset_number_from_onnx()),
idi2, output_names=['Y'],
op_version=get_opset_number_from_onnx())
model_def = onx.to_onnx({'X': idi.astype(numpy.float32)},
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def)
X = numpy.array([[1, 1], [3, 3]])
y = oinf.run({'X': X.astype(numpy.float32)})
exp = numpy.array([[4, 1], [3, 6]], dtype=numpy.float32)
self.assertEqual(list(y), ['Y'])
self.assertEqualArray(y['Y'], exp)
def test_constant_of_shape(self):
x = numpy.array([1, 2, 4, 5, 5, 4]).astype(
numpy.float32).reshape((3, 2))
tensor_value = make_tensor(
"value", TensorProto.FLOAT, (1,), [-5]) # pylint: disable=E1101
cop2 = OnnxConstantOfShape(
OnnxShape('input', op_version=get_opset_number_from_onnx()),
value=tensor_value,
output_names=['mat'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx({'input': x},
outputs=[('mat', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def, skip_run=True)
dot = oinf.to_dot()
self.assertIn('ConstantOfShape', dot)
def test_onnxview(self):
idi = numpy.identity(2)
onx = OnnxAdd('X',
idi,
output_names=['Y'],
op_version=get_opset_number_from_onnx())
model_def = onx.to_onnx({'X': idi.astype(numpy.float32)})
mg = OnnxNotebook()
mg.add_context({"model": model_def})
cmd = "--help"
res, out, _ = self.capture(lambda: mg.onnxview(cmd))
self.assertEmpty(res)
self.assertIn("notebook", out)
mg = OnnxNotebook()
mg.add_context({"model": model_def})
cmd = "model"
res = mg.onnxview(cmd)
self.assertNotEmpty(res)
self.assertIn('RenderJsDot', str(res))
mg = OnnxNotebook()
mg.add_context({"model": model_def})
cmd = "-r 1 model"
res = mg.onnxview(cmd)
self.assertNotEmpty(res)
self.assertIn('RenderJsDot', str(res))
def test_onnxt_lrc_iris_run_node_time(self):
iris = load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, _ = train_test_split(X, y, random_state=11)
clr = LogisticRegression(solver="liblinear")
clr.fit(X_train, y_train)
model_def = to_onnx(clr, X_train.astype(numpy.float32),
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def)
_, mt = oinf.run({'X': X_test}, node_time=True)
self.assertIsInstance(mt, list)
self.assertGreater(len(mt), 1)
self.assertIsInstance(mt[0], dict)
rows = []
def myprint(*args):
rows.append(' '.join(map(str, args)))
_, mt = oinf.run({'X': X_test}, node_time=True,
verbose=1, fLOG=myprint)
self.assertIsInstance(mt, list)
self.assertGreater(len(mt), 1)
self.assertIsInstance(mt[0], dict)
def test_onnxrt_tfidf_vectorizer_empty(self):
inputi = numpy.array([[1, 1, 3, 3, 3, 7, 8, 6, 7, 5, 6,
8]]).astype(numpy.int64)
output = numpy.array([[1., 1., 1.]]).astype(numpy.float32)
ngram_counts = numpy.array([0, 0]).astype(numpy.int64)
ngram_indexes = numpy.array([0, 1, 2]).astype(numpy.int64)
pool_int64s = numpy.array([ # unigrams
5, 6, 7, 8, 6, 7
]).astype(numpy.int64) # bigrams
op = OnnxTfIdfVectorizer('tokens',
op_version=get_opset_number_from_onnx(),
mode='TF',
min_gram_length=2,
max_gram_length=2,
max_skip_count=0,
ngram_counts=ngram_counts,
ngram_indexes=ngram_indexes,
pool_int64s=pool_int64s,
output_names=['out'])
onx = op.to_onnx(inputs=[('tokens', Int64TensorType())],
outputs=[('out', FloatTensorType())])
oinf = OnnxInference(onx)
res = oinf.run({'tokens': inputi})
self.assertEqual(output.tolist(), res['out'].tolist())
def test_export_sklearn_kernel_dot_product_default(self):
def kernel_call_ynone(X, sigma_0=2.):
t_sigma_0 = py_make_float_array(py_pow(sigma_0, 2))
K = X @ numpy.transpose(X, axes=[1, 0]) + t_sigma_0
return K
x = numpy.array([[1, 2], [3, 4], [5, 6]], dtype=float)
kernel = DotProduct(sigma_0=2.)
exp = kernel(x, None)
got = kernel_call_ynone(x, sigma_0=2.)
self.assertEqualArray(exp, got)
fct = translate_fct2onnx(kernel_call_ynone,
cpl=True,
output_names=['Z'])
r = fct('X', op_version=get_opset_number_from_onnx())
self.assertIsInstance(r, OnnxIdentity)
inputs = {'X': x.astype(numpy.float32)}
onnx_g = r.to_onnx(inputs)
oinf = OnnxInference(onnx_g)
res = oinf.run(inputs)
self.assertEqualArray(exp, res['Z'])
exp = kernel(x.T, None)
got = kernel_call_ynone(x.T)
self.assertEqualArray(exp, got)
inputs = {'X': x.T.astype(numpy.float32)}
res = oinf.run(inputs)
self.assertEqualArray(exp, res['Z'])
def test_onnxt_reduce_size(self):
idi = numpy.identity(2)
onx = OnnxAdd('X', idi, output_names=['Y'],
op_version=get_opset_number_from_onnx())
model_def = onx.to_onnx({'X': idi.astype(numpy.float32)})
oinf = OnnxInference(model_def, runtime="python_compiled")
res = oinf.run({'X': idi.astype(numpy.float32)})
self.assertEqual(idi * 2, res['Y'])
oinf.reduce_size(False)
res = oinf.run({'X': idi.astype(numpy.float32)})
self.assertEqual(idi * 2, res['Y'])
st = BytesIO()
try:
pickle.dump(oinf, st)
except AttributeError:
# missing obj
pass
oinf = OnnxInference(model_def, runtime="python_compiled")
res = oinf.run({'X': idi.astype(numpy.float32)})
self.assertEqual(idi * 2, res['Y'])
oinf.reduce_size(True)
res = oinf.run({'X': idi.astype(numpy.float32)})
self.assertEqual(idi * 2, res['Y'])
st = BytesIO()
pickle.dump(oinf, st)
val = st.getvalue()
oinf2 = pickle.load(BytesIO(val))
self.assertNotEmpty(oinf2)
def test_onnx_remove_two_outputs(self):
dtype = numpy.float32
x = numpy.array([1, 2, 4, 5, 5, 4]).astype(numpy.float32).reshape(
(3, 2))
cop = OnnxAdd('X',
numpy.array([1], dtype=dtype),
op_version=get_opset_number_from_onnx())
cop2 = OnnxAdd('X',
numpy.array([1], dtype=dtype),
output_names=['keep'],
op_version=get_opset_number_from_onnx())
cop3 = OnnxAdd('X',
numpy.array([2], dtype=dtype),
op_version=get_opset_number_from_onnx())
cop4 = OnnxSub(OnnxMul(cop,
cop3,
op_version=get_opset_number_from_onnx()),
cop2,
output_names=['final'],
op_version=get_opset_number_from_onnx())
model_def = cop4.to_onnx({'X': x},
outputs=[('keep', FloatTensorType([None, 2])),
('final', FloatTensorType([None,
2]))])
c1 = model_def.SerializeToString()
self.assertEqual(len(model_def.graph.output), 2)
c2 = model_def.SerializeToString()
self.assertEqual(c1, c2)
stats = onnx_statistics(model_def, optim=True)
new_model = onnx_remove_node_redundant(model_def, max_hash_size=10)
stats2 = onnx_statistics(model_def, optim=True)
stats3 = onnx_statistics(new_model, optim=False)
self.assertEqual(stats['ninits'], 2)
self.assertEqual(stats2['ninits'], 2)
self.assertEqual(stats3['ninits'], 2)
self.assertEqual(stats2['nnodes'], 6)
self.assertEqual(stats3['nnodes'], 6)
oinf1 = OnnxInference(model_def)
y1 = oinf1.run({'X': x})
oinf2 = OnnxInference(new_model)
y2 = oinf2.run({'X': x})
self.assertEqualArray(y1['final'], y2['final'])
self.assertEqualArray(y1['keep'], y2['keep'])
def test_onnxt_pdist_dot(self):
from skl2onnx.algebra.complex_functions import onnx_squareform_pdist # pylint: disable=E0401,E0611
x = numpy.array([1, 2, 4, 5, 5, 4]).astype(
numpy.float32).reshape((3, 2))
cop = OnnxAdd('input', 'input',
op_version=get_opset_number_from_onnx())
cdist = onnx_squareform_pdist(cop, dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
cop2 = OnnxIdentity(cdist, output_names=['cdist'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx(
{'input': x}, outputs=[('cdist', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def, skip_run=True)
dot = oinf.to_dot(recursive=True)
self.assertIn("B_next_out", dot)
self.assertIn("cluster", dot)
def test_onnxt_pickle_check(self):
idi = numpy.identity(2)
onx = OnnxAdd('X', idi, output_names=['Y'],
op_version=get_opset_number_from_onnx())
model_def = onx.to_onnx({'X': idi.astype(numpy.float32)},
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def)
shape = oinf.shape_inference()
self.assertNotEmpty(shape)
if not sys.platform.startswith('win'):
# Crashes (onnx crashes).
try:
oinf.check_model()
except ValidationError as e:
warnings.warn("Why? " + str(e)) # pylint: disable=E1101
pkl = pickle.dumps(oinf)
obj = pickle.loads(pkl)
self.assertEqual(str(oinf), str(obj))
def test_onnx_example_cdist_in(self):
from skl2onnx.algebra.complex_functions import onnx_cdist
x = numpy.array([1, 2, 4, 5, 5, 4]).astype(numpy.float32).reshape(
(3, 2))
x2 = numpy.array([1.1, 2.1, 4.01, 5.01, 5.001, 4.001, 0,
0]).astype(numpy.float32).reshape((4, 2))
cop = OnnxAdd('input',
'input',
op_version=get_opset_number_from_onnx())
cop2 = OnnxIdentity(onnx_cdist(
cop,
x2,
dtype=numpy.float32,
op_version=get_opset_number_from_onnx()),
output_names=['cdist'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx(inputs=[('input',
FloatTensorType([None, None]))],
outputs=[('cdist',
FloatTensorType(None, None))],
target_opset=get_opset_number_from_onnx())
sess = OnnxInference(model_def)
res = sess.run({'input': x})
exp = scipy_cdist(x * 2, x2, metric="sqeuclidean")
self.assertEqualArray(exp, res['cdist'], decimal=5)
x = numpy.array(
[[6.1, 2.8, 4.7, 1.2], [5.7, 3.8, 1.7, 0.3], [7.7, 2.6, 6.9, 2.3],
[6., 2.9, 4.5, 1.5], [6.8, 2.8, 4.8, 1.4], [5.4, 3.4, 1.5, 0.4],
[5.6, 2.9, 3.6, 1.3], [6.9, 3.1, 5.1, 2.3]],
dtype=numpy.float32)
cop = OnnxAdd('input',
'input',
op_version=get_opset_number_from_onnx())
cop2 = OnnxIdentity(onnx_cdist(
cop,
x,
dtype=numpy.float32,
op_version=get_opset_number_from_onnx()),
output_names=['cdist'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx(inputs=[('input',
FloatTensorType([None, None]))],
outputs=[('cdist', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
sess = OnnxInference(model_def)
res = sess.run({'input': x})
exp = scipy_cdist(x * 2, x, metric="sqeuclidean")
self.assertEqualArray(exp, res['cdist'], decimal=4)
def test_onnxt_dot(self):
idi = numpy.identity(2)
idi2 = numpy.identity(2) * 2
onx = OnnxAdd(
OnnxAdd('X', idi, op_version=get_opset_number_from_onnx()),
idi2, output_names=['Y'],
op_version=get_opset_number_from_onnx())
model_def = onx.to_onnx({'X': idi.astype(numpy.float32)},
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def)
dot = oinf.to_dot()
self.assertIn('Add [', dot)
self.assertIn('Add1 [', dot)
self.assertIn('Add\\n(Ad_Add)', dot)
self.assertIn('Add\\n(Ad_Add1)', dot)
self.assertIn('X -> Ad_Add;', dot)
self.assertIn('Ad_Addcst1 -> Ad_Add1;', dot)
self.assertIn('Ad_Addcst -> Ad_Add;', dot)
self.assertIn('Ad_Add1 -> Y;', dot)
def test_onnxt_graph(self):
idi = numpy.identity(2)
idi2 = numpy.identity(2) * 2
onx = OnnxAdd(
OnnxAdd('X', idi, op_version=get_opset_number_from_onnx()),
idi2, output_names=['Y'],
op_version=get_opset_number_from_onnx())
model_def = onx.to_onnx({'X': idi.astype(numpy.float32)},
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def)
js = oinf.to_sequence()
self.assertIn('inits', js)
self.assertIn('inputs', js)
self.assertIn('outputs', js)
self.assertIn('intermediate', js)
self.assertIn('nodes', js)
self.assertIn('sequence', js)
self.assertEqual(len(js['sequence']), 2)
self.assertEqual(len(js['intermediate']), 2)
def test_onnxrt_string_normalizer(self):
corpus = numpy.array([
'This is the first document.',
'This document is the second document.',
'And this is the third one.', 'Is this the first document?'
])
op = OnnxStringNormalizer('text',
op_version=get_opset_number_from_onnx(),
output_names=['out'])
onx = op.to_onnx(inputs=[('text', StringTensorType())])
oinf = OnnxInference(onx)
res = oinf.run({'text': corpus})
self.assertEqual(list(res['out']), list(corpus))
res = oinf.run({'text': corpus.reshape((2, 2))})
self.assertEqual(res['out'].tolist(), corpus.reshape((2, 2)).tolist())
op = OnnxStringNormalizer('text',
op_version=get_opset_number_from_onnx(),
output_names=['out'],
case_change_action='LOWER')
onx = op.to_onnx(inputs=[('text', StringTensorType())])
oinf = OnnxInference(onx)
res = oinf.run({'text': corpus})
self.assertEqual(list(res['out']), list(_.lower() for _ in corpus))
op = OnnxStringNormalizer('text',
op_version=get_opset_number_from_onnx(),
output_names=['out'],
case_change_action='UPPER')
onx = op.to_onnx(inputs=[('text', StringTensorType())])
oinf = OnnxInference(onx)
res = oinf.run({'text': corpus})
self.assertEqual(list(res['out']), list(_.upper() for _ in corpus))
op = OnnxStringNormalizer('text',
op_version=get_opset_number_from_onnx(),
output_names=['out'],
case_change_action='UPPER2')
onx = op.to_onnx(inputs=[('text', StringTensorType())])
oinf = OnnxInference(onx)
self.assertRaise(lambda: oinf.run({'text': corpus}), RuntimeError)
def test_onnxt_lreg(self):
pars = dict(coefficients=numpy.array([1., 2.]), intercepts=numpy.array([1.]),
post_transform='NONE')
onx = OnnxLinearRegressor('X', output_names=['Y'], **pars)
model_def = onx.to_onnx({'X': pars['coefficients'].astype(numpy.float32)},
outputs=[('Y', FloatTensorType([1]))],
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def)
dot = oinf.to_dot()
self.assertIn('coefficients=[1. 2.]', dot)
self.assertIn('LinearRegressor', dot)
def test_onnx_stat_recursive(self):
from skl2onnx.algebra.complex_functions import onnx_squareform_pdist
cop = OnnxAdd(OnnxIdentity('input',
op_version=get_opset_number_from_onnx()),
'input',
op_version=get_opset_number_from_onnx())
cdist = onnx_squareform_pdist(cop,
dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
cop2 = OnnxIdentity(cdist,
output_names=['cdist'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx({'input': FloatTensorType()},
outputs=[('cdist', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
stats = onnx_statistics(model_def)
self.assertIn('subgraphs', stats)
self.assertGreater(stats['subgraphs'], 1)
self.assertGreater(stats['op_Identity'], 2)
def test_onnxt_knn_iris_dot(self):
iris = load_iris()
X, y = iris.data, iris.target
X_train, __, y_train, _ = train_test_split(X, y, random_state=11)
clr = KNeighborsClassifier()
clr.fit(X_train, y_train)
model_def = to_onnx(clr, X_train.astype(numpy.float32),
target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(model_def, skip_run=True)
dot = oinf.to_dot()
self.assertNotIn("class_labels_0 -> ;", dot)
def test_onnx_remove_redundant_subgraphs_full(self):
from skl2onnx.algebra.complex_functions import onnx_squareform_pdist
cop = OnnxAdd(OnnxIdentity('input',
op_version=get_opset_number_from_onnx()),
'input',
op_version=get_opset_number_from_onnx())
cdist = onnx_squareform_pdist(cop,
dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
cdist2 = onnx_squareform_pdist(cop,
dtype=numpy.float32,
op_version=get_opset_number_from_onnx())
cop2 = OnnxAdd(cdist,
cdist2,
output_names=['cdist'],
op_version=get_opset_number_from_onnx())
model_def = cop2.to_onnx({'input': FloatTensorType()},
outputs=[('cdist', FloatTensorType())],
target_opset=get_opset_number_from_onnx())
stats = onnx_statistics(model_def, optim=False)
new_model = onnx_optimisations(model_def)
stats2 = onnx_statistics(new_model, optim=False)
self.assertLess(stats2['size'], stats['size'])
self.assertLess(stats2['nnodes'], stats['nnodes'])
self.assertLess(stats2['op_Identity'], stats['op_Identity'])
def test_onnxrt_python_count_vectorizer(self):
corpus = numpy.array([
'This is the first document.',
'This document is the second document.',
'And this is the third one.', 'Is this the first document?'
])
vect = CountVectorizer()
vect.fit(corpus)
exp = vect.transform(corpus)
onx = to_onnx(vect, corpus, target_opset=get_opset_number_from_onnx())
oinf = OnnxInference(onx)
got = oinf.run({'X': corpus})
self.assertEqualArray(exp.todense(), got['variable'])
