GaussianProcessRegressor - ~b-reg-NF-cov-64 - expsine - cdist#

Fitted on a problem type ~b-reg-NF-cov-64 (see find_suitable_problem), method predict matches output . Model was converted with additional parameter: <class 'sklearn.gaussian_process._gpr.GaussianProcessRegressor'>={'optim': 'cdist'}.

GaussianProcessRegressor(alpha=20.0,
                     kernel=ExpSineSquared(length_scale=1, periodicity=1),
                     random_state=42)

index

0

skl_nop

1

onx_size

1407

onx_nnodes

18

onx_ninits

5

onx_doc_string

onx_ir_version

8

onx_domain

ai.onnx

onx_model_version

0

onx_producer_name

skl2onnx

onx_producer_version

1.11.1

onx_

15

onx_op_Identity

3

onx_subgraphs

1

onx_op_Identity_optim

1

onx_subgraphs_optim

1

onx_size_optim

1282

onx_nnodes_optim

16

onx_ninits_optim

5
%0 cluster_Scan139930303312128_139930469640752 Scan (Sc_Scan) body=node {  input: 'next_in'... num_scan_inputs=1 X X double((0, 4)) Sh_Shape Shape (Sh_Shape) X->Sh_Shape B_next_in next_in double((0, 0)) X->B_next_in B_next next double((0,)) X->B_next Sc_Scan Sc_Scan X->Sc_Scan X->Sc_Scan GPmean GPmean double((0, 1)) GPcovstd GPcovstd double(('?',)) Re_ReduceSumcst Re_ReduceSumcst int64((1,)) [1] Re_ReduceSum ReduceSum (Re_ReduceSum) keepdims=1 Re_ReduceSumcst->Re_ReduceSum Di_Divcst Di_Divcst float64((1,)) [1.] Di_Div Div (Di_Div) Di_Divcst->Di_Div Di_Div1 Div (Di_Div1) Di_Divcst->Di_Div1 Mu_Mulcst Mu_Mulcst float64((1,)) [3.14159265] Mu_Mul Mul (Mu_Mul) Mu_Mulcst->Mu_Mul Po_Powcst Po_Powcst float64((1,)) [2.] Po_Pow Pow (Po_Pow) Po_Powcst->Po_Pow Mu_Mulcst1 Mu_Mulcst1 float64((1,)) [-2.] Mu_Mul1 Mul (Mu_Mul1) Mu_Mulcst1->Mu_Mul1 Sh_shape0 Sh_shape0 Co_ConstantOfShape ConstantOfShape (Co_ConstantOfShape) value=[0.] Sh_shape0->Co_ConstantOfShape Sh_Shape->Sh_shape0 UU002UU UU002UU UU003UU UU003UU Tr_Transpose Transpose (Tr_Transpose) perm=[1 0] UU003UU->Tr_Transpose B_cdistd_2_Identity Identity (cdistd_2_Identity) B_next_in->B_cdistd_2_Identity B_cdistdf_2_Sub Sub (cdistdf_2_Sub) B_next_in->B_cdistdf_2_Sub B_next->B_cdistdf_2_Sub B_next_out next_out double((0, 0)) B_next_out->UU002UU B_scan_out scan_out double((0,)) B_scan_out->UU003UU B_cdistd_2_Identity->B_next_out B_cdistdf_2_C0 cdistdf_2_C0 B_cdistdf_2_ReduceSumSquare ReduceSumSquare (cdistdf_2_ReduceSumSquare) axes=[1] keepdims=0 B_cdistdf_2_C0->B_cdistdf_2_ReduceSumSquare B_cdistdf_2_Sub->B_cdistdf_2_C0 B_cdistdf_2_reduced0 cdistdf_2_reduced0 B_cdistdf_2_Identity Identity (cdistdf_2_Identity) B_cdistdf_2_reduced0->B_cdistdf_2_Identity B_cdistdf_2_ReduceSumSquare->B_cdistdf_2_reduced0 B_cdistdf_2_Identity->B_scan_out Sc_Scan->UU002UU Sc_Scan->UU003UU Sc_Scan->B_cdistd_2_Identity Co_output0 Co_output0 Co_output0->Re_ReduceSum Co_ConstantOfShape->Co_output0 Tr_transposed0 Tr_transposed0 Sq_Sqrt Sqrt (Sq_Sqrt) Tr_transposed0->Sq_Sqrt Tr_Transpose->Tr_transposed0 Re_ReduceSum->GPmean Sq_Y0 Sq_Y0 Sq_Y0->Di_Div Sq_Sqrt->Sq_Y0 Di_C01 Di_C01 Di_C01->Mu_Mul Di_Div->Di_C01 Mu_C01 Mu_C01 Si_Sin Sin (Si_Sin) Mu_C01->Si_Sin Mu_Mul->Mu_C01 Si_output0 Si_output0 Si_output0->Di_Div1 Si_Sin->Si_output0 Di_C0 Di_C0 Di_C0->Po_Pow Di_Div1->Di_C0 Po_Z0 Po_Z0 Po_Z0->Mu_Mul1 Po_Pow->Po_Z0 Mu_C0 Mu_C0 Ex_Exp Exp (Ex_Exp) Mu_C0->Ex_Exp Mu_Mul1->Mu_C0 Ex_output0 Ex_output0 Id_Identity Identity (Id_Identity) Ex_output0->Id_Identity Ex_Exp->Ex_output0 Id_Identity->GPcovstd

previous

GaussianProcessRegressor - ~b-reg-NF-64 - rbf - cdist

next

GaussianProcessRegressor - ~b-reg-NF-cov-64 - dotproduct -