def test_onnxt_runtime_argmin(self):
X = numpy.array([[2, 1], [0, 1]], dtype=float)
onx = OnnxArgMin('X', output_names=['Y'], keepdims=0)
model_def = onx.to_onnx({'X': X.astype(numpy.float32)})
oinf = OnnxInference(model_def)
got = oinf.run({'X': X})
self.assertEqual(list(sorted(got)), ['Y'])
self.assertEqualArray(numpy.argmin(X, axis=0), got['Y'], decimal=6)
onx = OnnxArgMin('X', output_names=['Y'], axis=1, keepdims=0)
model_def = onx.to_onnx({'X': X.astype(numpy.float32)})
oinf = OnnxInference(model_def)
got = oinf.run({'X': X})
self.assertEqual(list(sorted(got)), ['Y'])
self.assertEqualArray(
numpy.argmin(X, axis=1).ravel(), got['Y'].ravel())
onx = OnnxArgMin('X', output_names=['Y'], axis=1, keepdims=1)
model_def = onx.to_onnx({'X': X.astype(numpy.float32)})
oinf = OnnxInference(model_def)
got = oinf.run({'X': X})
self.assertEqual(list(sorted(got)), ['Y'])
self.assertEqualArray(
numpy.argmin(X, axis=1).ravel(), got['Y'].ravel())
def test_algebra_argmin(self):
op = OnnxArgMin('I0', op_version=TARGET_OPSET)
onx = op.to_onnx({'I0': numpy.ones((1, 2), dtype=numpy.float32)})
assert onx is not None
sonx = str(onx)
assert len(sonx) > 0
import onnxruntime as ort
sess = ort.InferenceSession(onx.SerializeToString())
X = numpy.array([[0, 2], [0, -2]])
exp = numpy.array([[0, 1]])
Y = sess.run(None, {'I0': X.astype(numpy.float32)})[0]
assert_almost_equal(exp, Y)
def test_algebra_normalizer_argmin_named_output(self):
op = OnnxArgMin(OnnxNormalizer('I0', norm='L1', output_names=['Y']))
onx = op.to_onnx({'I0': numpy.ones((1, 2), dtype=numpy.float32)})
assert onx is not None
sonx = str(onx)
assert len(sonx) > 0
import onnxruntime as ort
sess = ort.InferenceSession(onx.SerializeToString())
X = numpy.array([[0, 2], [0, -2]])
exp = numpy.array([[0, 1]])
Y = sess.run(None, {'I0': X.astype(numpy.float32)})[0]
assert_almost_equal(exp, Y)