def test_onnxt_array_feature_extractor(self):
onx = OnnxArrayFeatureExtractor(
'X', np.array([1], dtype=np.int64),
output_names=['Y'], op_version=1)
X = np.array([[1, 2], [3, 4]], dtype=np.float32)
model_def = onx.to_onnx({'X': X},
outputs=[('Y', FloatTensorType([2]))])
sess = InferenceSession(model_def.SerializeToString())
got = sess.run(None, {'X': X})[0]
self.assertEqual(got.shape, (2, 1))
assert_almost_equal(X[:, 1:2], got)
def test_onnxt_runtime_array_feature_extractor(self):
onx = OnnxArrayFeatureExtractor('X',
numpy.array([1], dtype=numpy.int64),
output_names=['Y'])
X = numpy.array([[1, 2], [3, 4]], dtype=numpy.float64)
model_def = onx.to_onnx({'X': X.astype(numpy.float32)},
outputs=[('Y', FloatTensorType([2]))])
oinf = OnnxInference(model_def)
got = oinf.run({'X': X})
self.assertEqual(list(sorted(got)), ['Y'])
self.assertEqual(got['Y'].shape, (2, 1))
self.assertEqualArray(X[:, 1:2], got['Y'], decimal=6)
def test_onnxt_runtime_array_feature_extractor_cmp4(self):
X = numpy.random.randn(38, 5).astype( # pylint: disable=E1101
numpy.float32) # pylint: disable=E1101
indices = numpy.ones((38, 1), dtype=numpy.int64)
onx = OnnxArrayFeatureExtractor('X', indices, output_names=['Y'])
model_def = onx.to_onnx({'X': X.astype(numpy.float32)},
outputs=[('Y', FloatTensorType([2]))])
oinf = OnnxInference(model_def)
got = oinf.run({'X': X})['Y']
model_def.ir_version = get_ir_version(TARGET_OPSET)
oinf2 = OnnxInference(model_def, runtime="onnxruntime2")
got2 = oinf2.run({'X': X})['Y']
self.assertEqualArray(got, got2)
def test_onnxt_runtime_array_feature_extractor_cmp3(self):
X = numpy.array(
[3.3626876, 2.204158, 2.267245, 1.297554, 0.97023404, 1.567],
dtype=numpy.float32).reshape((2, 3))
indices = numpy.array([[1, 2]], dtype=numpy.int64).T
onx = OnnxArrayFeatureExtractor('X', indices, output_names=['Y'])
model_def = onx.to_onnx({'X': X.astype(numpy.float32)},
outputs=[('Y', FloatTensorType([2]))])
oinf = OnnxInference(model_def)
got = oinf.run({'X': X})['Y']
model_def.ir_version = get_ir_version(TARGET_OPSET)
oinf2 = OnnxInference(model_def, runtime="onnxruntime2")
got2 = oinf2.run({'X': X})['Y']
self.assertEqualArray(got, got2)
def test_onnxt_runtime_array_feature_extractor_cmp2(self):
X = numpy.array(
[[3.3626876, 2.204158, 2.267245, 1.297554, 0.97023404],
[-3.3626876, -2.204158, -2.267245, -1.297554, -0.97023404]],
dtype=numpy.float32)
indices = numpy.array([[2], [3]], dtype=numpy.int64)
onx = OnnxArrayFeatureExtractor('X', indices, output_names=['Y'])
model_def = onx.to_onnx({'X': X.astype(numpy.float32)},
outputs=[('Y', FloatTensorType([2]))])
oinf = OnnxInference(model_def)
got = oinf.run({'X': X})['Y']
oinf2 = OnnxInference(model_def, runtime="onnxruntime2")
got2 = oinf2.run({'X': X})['Y']
self.assertEqualArray(got, got2)
def nmf_to_onnx(W, H):
"""
The function converts a NMF described by matrices
*W*, *H* (*WH* approximate training data *M*).
into a function which takes two indices *(i, j)*
and returns the predictions for it. It assumes
these indices applies on the training data.
"""
col = OnnxArrayFeatureExtractor(H, 'col')
row = OnnxArrayFeatureExtractor(W.T, 'row')
dot = OnnxMul(col, row)
res = OnnxReduceSum(dot, output_names="rec")
indices_type = np.array([0], dtype=np.int64)
onx = res.to_onnx(inputs={'col': indices_type,
'row': indices_type},
outputs=[('rec', FloatTensorType((None, 1)))])
return onx
def test_onnxt_runtime_array_feature_extractor_cmp(self):
X = numpy.array([3.3626876, 2.204158, 2.267245, 1.297554, 0.97023404],
dtype=numpy.float32)
indices = numpy.array([[
4,
2,
0,
1,
3,
], [0, 1, 2, 3, 4], [0, 1, 2, 3, 4], [3, 4, 2, 0, 1], [0, 2, 3, 4, 1]],
dtype=numpy.int64)
onx = OnnxArrayFeatureExtractor('X', indices, output_names=['Y'])
model_def = onx.to_onnx({'X': X.astype(numpy.float32)},
outputs=[('Y', FloatTensorType([2]))])
model_def.ir_version = get_ir_version_from_onnx()
oinf = OnnxInference(model_def)
got = oinf.run({'X': X})['Y']
model_def.ir_version = get_ir_version_from_onnx()
oinf2 = OnnxInference(model_def, runtime="onnxruntime2")
got2 = oinf2.run({'X': X})['Y']
self.assertEqualArray(got, got2)
