def test_kernel_rational_quadratic_diag(self):
ker = RationalQuadratic()
onx = convert_kernel_diag(ker,
'X',
output_names=['Y'],
dtype=np.float32,
op_version=_TARGET_OPSET_)
model_onnx = onx.to_onnx(inputs=[('X', FloatTensorType([None, None]))],
target_opset=_TARGET_OPSET_)
sess = InferenceSession(model_onnx.SerializeToString())
res = sess.run(None, {'X': Xtest_.astype(np.float32)})[0]
m1 = res
m2 = ker.diag(Xtest_)
assert_almost_equal(m1, m2, decimal=4)
def test_kernel_dot_product_diag(self):
ker = DotProduct()
onx = convert_kernel_diag(ker,
'X',
output_names=['Y'],
dtype=np.float32,
op_version=_TARGET_OPSET_)
model_onnx = onx.to_onnx(inputs=[('X', FloatTensorType([None, None]))],
dtype=np.float32)
sess = InferenceSession(model_onnx.SerializeToString())
res = sess.run(None, {'X': Xtest_.astype(np.float32)})[0]
m1 = res
m2 = ker.diag(Xtest_)
assert_almost_equal(m1 / 1000, m2 / 1000, decimal=5)
def test_kernel_exp_sine_squared_diag(self):
ker = ExpSineSquared()
onx = convert_kernel_diag(ker,
'X',
output_names=['Y'],
dtype=np.float32,
op_version=onnx_opset_version())
model_onnx = onx.to_onnx(inputs=[('X', FloatTensorType([None, None]))],
dtype=np.float32)
sess = InferenceSession(model_onnx.SerializeToString())
res = sess.run(None, {'X': Xtest_.astype(np.float32)})[0]
m1 = res
m2 = ker.diag(Xtest_)
assert_almost_equal(m1, m2, decimal=4)