OneVsRestClassifier - ~b-cl-64 - logreg - {‘zipmap’: False}#

Fitted on a problem type ~b-cl-64 (see find_suitable_problem), method predict_proba matches output . Model was converted with additional parameter: <class 'sklearn.multiclass.OneVsOneClassifier'>={'zipmap': False}.

OneVsRestClassifier(estimator=LogisticRegression(random_state=0,
                                             solver='liblinear'),
                n_jobs=8)

index

0

skl_nop

2

skl_ncoef

2

skl_nlin

2

onx_size

1918

onx_nnodes

23

onx_ninits

7

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_ai.onnx.ml

1

onx_op_Cast

5

onx_op_ZipMap

1

onx_op_Reshape

2

onx_size_optim

1552

onx_nnodes_optim

18

onx_ninits_optim

7

fit_classes_.shape

2

fit_n_classes_

2

fit_estimators_.size

1

fit_estimators_.n_iter_.shape

1

fit_estimators_.coef_.shape

(1, 4)

fit_estimators_.classes_.shape

2

fit_estimators_.intercept_.shape

1
%0 X X double((0, 4)) MatMul MatMul (MatMul) X->MatMul output_label output_label int64((0,)) output_probability output_probability [{int64, {'kind': 'tensor', 'elem': 'double', 'shape': }}] starts starts int64((1,)) [1] ReduceSum ReduceSum (ReduceSum) keepdims=1 starts->ReduceSum Slice Slice (Slice) starts->Slice starts->Slice ends ends int64((1,)) [2] ends->Slice unit_float_tensor unit_float_tensor float64(()) 1.0 Sub Sub (Sub) unit_float_tensor->Sub classes classes int32((2,)) [0 1] ArrayFeatureExtractor1 ArrayFeatureExtractor (ArrayFeatureExtractor1) classes->ArrayFeatureExtractor1 ArrayFeatureExtractor ArrayFeatureExtractor (ArrayFeatureExtractor) classes->ArrayFeatureExtractor shape_tensor shape_tensor int64((1,)) [-1] Reshape1 Reshape (Reshape1) shape_tensor->Reshape1 Reshape Reshape (Reshape) shape_tensor->Reshape coef coef float64((4, 2)) [[ 0.45876741 -0.45876741] [ 1.29302622 -1.29302622] [-2.30693933  2.30693933] [-0.6970415   0.6970415 ]] coef->MatMul intercept intercept float64((1, 2)) [[ 0.28357965 -0.28357965]] Add Add (Add) intercept->Add multiplied multiplied multiplied->Add MatMul->multiplied raw_scores raw_scores Sigmoid Sigmoid (Sigmoid) raw_scores->Sigmoid ArgMax1 ArgMax (ArgMax1) axis=1 raw_scores->ArgMax1 Add->raw_scores raw_scoressig raw_scoressig Abs Abs (Abs) raw_scoressig->Abs NormalizerNorm Div (NormalizerNorm) raw_scoressig->NormalizerNorm Sigmoid->raw_scoressig label1 label1 label1->ArrayFeatureExtractor1 ArgMax1->label1 array_feature_extractor_result1 array_feature_extractor_result1 Cast3 Cast (Cast3) to=11 array_feature_extractor_result1->Cast3 ArrayFeatureExtractor1->array_feature_extractor_result1 norm_abs norm_abs norm_abs->ReduceSum Abs->norm_abs cast2_result1 cast2_result1 cast2_result1->Reshape1 Cast3->cast2_result1 norm norm norm->NormalizerNorm ReduceSum->norm proba_0 proba_0 proba_0->Slice NormalizerNorm->proba_0 reshaped_result1 reshaped_result1 Cast4 Cast (Cast4) to=7 reshaped_result1->Cast4 Reshape1->reshaped_result1 label_0 label_0 Cast4->label_0 probY_0 probY_0 Concat Concat (Concat) axis=1 probY_0->Concat Slice->probY_0 concatenated concatenated concatenated->Sub Concat1 Concat (Concat1) axis=1 concatenated->Concat1 Concat->concatenated zeroth_col zeroth_col zeroth_col->Concat1 Sub->zeroth_col merged_prob merged_prob LpNormalization LpNormalization (LpNormalization) axis=1 p=1 merged_prob->LpNormalization ArgMax ArgMax (ArgMax) axis=1 merged_prob->ArgMax Concat1->merged_prob probabilities probabilities ZipMap ZipMap (ZipMap) classlabels_int64s=[0 1] probabilities->ZipMap LpNormalization->probabilities label_name label_name label_name->ArrayFeatureExtractor ArgMax->label_name ZipMap->output_probability array_feature_extractor_result array_feature_extractor_result Cast Cast (Cast) to=11 array_feature_extractor_result->Cast ArrayFeatureExtractor->array_feature_extractor_result cast2_result cast2_result cast2_result->Reshape Cast->cast2_result reshaped_result reshaped_result Cast1 Cast (Cast1) to=7 reshaped_result->Cast1 Reshape->reshaped_result label label Cast2 Cast (Cast2) to=7 label->Cast2 Cast1->label Cast2->output_label

previous

OneVsRestClassifier - b-cl - logreg - {‘zipmap’: False}

next

OneVsRestClassifier - m-cl - logreg - {‘zipmap’: False}