def test_plot_onnx(self):
cst = numpy.array([[1, 2]], dtype=numpy.float32)
onx = OnnxConcat('X', 'Y', cst, output_names=['Z'],
op_version=12)
X = numpy.array([[1, 2], [3, 4]], dtype=numpy.float64)
Y = numpy.array([[8, 9], [10, 11], [12, 13]], dtype=numpy.float64)
model_def = onx.to_onnx({'X': X.astype(numpy.float32),
'Y': Y.astype(numpy.float32)},
outputs=[('Z', FloatTensorType([2]))],
target_opset=12)
import matplotlib.pyplot as plt
_, ax = plt.subplots(1, 1)
try:
plot_onnx(model_def, ax=ax)
except FileNotFoundError as e:
if "No such file or directory: 'dot'" in str(e):
warnings.warn(
"Unable to test the dot syntax, dot is mssing", UserWarning)
return
raise e
if __name__ == "__main__":
temp = get_temp_folder(__file__, "temp_plot_onnx")
img = os.path.join(temp, "img.png")
plt.savefig(img)
plt.show()
plt.close('all')
def pyod_iforest_converter(scope, operator, container):
op = operator.raw_operator
opv = container.target_opset
out = operator.outputs
# We retrieve the unique input.
X = operator.inputs[0]
# In most case, computation happen in floats.
# But it might be with double. ONNX is very strict
# about types, every constant should have the same
# type as the input.
dtype = guess_numpy_type(X.type)
detector = op.detector_ # Should be IForest from scikit-learn.
lab_pred = OnnxSubEstimator(detector, X, op_version=opv)
scores = OnnxIdentity(lab_pred[1], op_version=opv)
# labels
threshold = op.threshold_
above = OnnxLess(scores,
np.array([threshold], dtype=dtype),
op_version=opv)
labels = OnnxCast(above,
op_version=opv,
to=onnx_proto.TensorProto.INT64,
output_names=out[:1])
# probabilities
train_scores = op.decision_scores_
scaler = MinMaxScaler().fit(train_scores.reshape(-1, 1))
scores_ = OnnxMul(scores, np.array([-1], dtype=dtype), op_version=opv)
print(scaler.min_)
print(scaler.scale_)
scaled = OnnxMul(scores_, scaler.scale_.astype(dtype), op_version=opv)
scaled_centered = OnnxAdd(scaled,
scaler.min_.astype(dtype),
op_version=opv)
clipped = OnnxClip(scaled_centered,
np.array([0], dtype=dtype),
np.array([1], dtype=dtype),
op_version=opv)
clipped_ = OnnxAdd(OnnxMul(clipped,
np.array([-1], dtype=dtype),
op_version=opv),
np.array([1], dtype=dtype),
op_version=opv)
scores_2d = OnnxConcat(clipped_,
clipped,
axis=1,
op_version=opv,
output_names=out[1:])
labels.add_to(scope, container)
scores_2d.add_to(scope, container)
def test_plot_onnx2(self):
cst = numpy.array([[1, 2]], dtype=numpy.float32)
onx = OnnxConcat('X', 'Y', cst, output_names=['Z'], op_version=12)
X = numpy.array([[1, 2], [3, 4]], dtype=numpy.float64)
Y = numpy.array([[8, 9], [10, 11], [12, 13]], dtype=numpy.float64)
model_def = onx.to_onnx(
{
'X': X.astype(numpy.float32),
'Y': Y.astype(numpy.float32)
},
outputs=[('Z', FloatTensorType([2]))],
target_opset={
'': 14,
'ai.onnx.ml': 2
})
import matplotlib.pyplot as plt
ax = numpy.array([0])
self.assertRaise(lambda: plot_onnxs(model_def, model_def, ax=ax),
ValueError)
try:
ax = plot_onnxs(model_def, model_def, title=["GRAPH1", "GRAPH2"])
except FileNotFoundError as e:
if "No such file or directory: 'dot'" in str(e):
warnings.warn("Unable to test the dot syntax, dot is mssing",
UserWarning)
return
raise e
self.assertNotEmpty(ax)
try:
ax = plot_onnxs(model_def, model_def, title="GRAPH1")
except FileNotFoundError as e:
if "No such file or directory: 'dot'" in str(e):
warnings.warn("Unable to test the dot syntax, dot is mssing",
UserWarning)
return
raise e
self.assertNotEmpty(ax)
try:
ax = plot_onnxs(model_def, model_def, title="GRAPH1", ax='new')
except FileNotFoundError as e:
if "No such file or directory: 'dot'" in str(e):
warnings.warn("Unable to test the dot syntax, dot is mssing",
UserWarning)
return
raise e
self.assertNotEmpty(ax)
if __name__ == "__main__":
temp = get_temp_folder(__file__, "temp_plot_onnx2")
img = os.path.join(temp, "img.png")
plt.savefig(img)
plt.show()
plt.close('all')
def test_onnxt_runtime_concat(self):
cst = numpy.array([[1, 2]], dtype=numpy.float32)
onx = OnnxConcat('X', 'Y', cst, output_names=['Z'])
X = numpy.array([[1, 2], [3, 4]], dtype=numpy.float64)
Y = numpy.array([[8, 9], [10, 11], [12, 13]], dtype=numpy.float64)
model_def = onx.to_onnx(
{
'X': X.astype(numpy.float32),
'Y': Y.astype(numpy.float32)
},
outputs=[('Z', FloatTensorType([2]))])
oinf = OnnxInference(model_def)
got = oinf.run({'X': X, 'Y': Y})
self.assertEqual(list(sorted(got)), ['Z'])
self.assertEqual(got['Z'].shape, (6, 2))
exp = numpy.vstack([X, Y, cst])
self.assertEqualArray(exp, got['Z'])
def test_plot_onnx(self):
cst = numpy.array([[1, 2]], dtype=numpy.float32)
onx = OnnxConcat('X', 'Y', cst, output_names=['Z'], op_version=12)
X = numpy.array([[1, 2], [3, 4]], dtype=numpy.float64)
Y = numpy.array([[8, 9], [10, 11], [12, 13]], dtype=numpy.float64)
model_def = onx.to_onnx(
{
'X': X.astype(numpy.float32),
'Y': Y.astype(numpy.float32)
},
outputs=[('Z', FloatTensorType([2]))],
target_opset={
'': 14,
'ai.onnx.ml': 2
})
import matplotlib.pyplot as plt
self.assertRaise(lambda: plot_onnxs(*[]), ValueError)
try:
ax = plot_onnxs(model_def, title="GRAPH")
except FileNotFoundError as e:
if "No such file or directory: 'dot'" in str(e):
warnings.warn("Unable to test the dot syntax, dot is mssing",
UserWarning)
return
raise e
self.assertNotEmpty(ax)
try:
ax = plot_onnxs(model_def, title="GRAPH", ax='new')
except FileNotFoundError as e:
if "No such file or directory: 'dot'" in str(e):
warnings.warn("Unable to test the dot syntax, dot is mssing",
UserWarning)
return
raise e
self.assertNotEmpty(ax)
plt.close('all')
def custom_classifier_converter(scope, operator, container):
op = operator.raw_operator
X = operator.inputs[0]
outputs = operator.outputs
opv = container.target_opset
y_list = [
OnnxReshape(
OnnxSubEstimator(est, X, op_version=opv)[1],
np.array([-1, 1], dtype=np.int64), op_version=opv)
for est in op.estimators_]
y_matrix = OnnxConcat(*y_list, axis=1, op_version=opv)
probs = OnnxSoftmax(y_matrix, axis=1, op_version=opv,
output_names=[outputs[1]])
probs.add_to(scope, container)
labels = OnnxArgMax(probs, axis=1, keepdims=0, op_version=opv,
output_names=[outputs[0]])
labels.add_to(scope, container)