SGDClassifier - ~b-cl-64 - log - {‘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.linear_model._stochastic_gradient.SGDClassifier'>={'zipmap': False}.

SGDClassifier(loss='log', n_jobs=8, random_state=0)

index

0

skl_nop

1

skl_ncoef

1

skl_nlin

1

onx_size

832

onx_nnodes

9

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_

14

onx_ai.onnx.ml

1

onx_op_Cast

1

onx_op_Reshape

1

onx_size_optim

832

onx_nnodes_optim

9

onx_ninits_optim

5

fit_coef_.shape

(1, 4)

fit_intercept_.shape

1

fit_classes_.shape

2
%0 X X double((0, 4)) MatMul MatMul (MatMul) X->MatMul label label int64((0,)) probabilities probabilities double((0, 2)) ArgMax ArgMax (ArgMax) axis=1 probabilities->ArgMax classes classes int32((2,)) [0 1] ArrayFeatureExtractor ArrayFeatureExtractor (ArrayFeatureExtractor) classes->ArrayFeatureExtractor coef coef float64((4, 1)) [[ -9.82522642] [-21.46155283] [ 36.79361722] [ 15.48582153]] coef->MatMul intercept intercept float64((1,)) [-4.98009924] Add Add (Add) intercept->Add unity unity float64((1,)) [1.] Sub Sub (Sub) unity->Sub shape_tensor shape_tensor int64((1,)) [-1] Reshape Reshape (Reshape) shape_tensor->Reshape matmul_result matmul_result matmul_result->Add MatMul->matmul_result score score Sigmoid Sigmoid (Sigmoid) score->Sigmoid Add->score sigmoid sigmoid sigmoid->Sub Concat Concat (Concat) axis=1 sigmoid->Concat Sigmoid->sigmoid sigmo_0 sigmo_0 sigmo_0->Concat Sub->sigmo_0 Concat->probabilities predicted_label predicted_label predicted_label->ArrayFeatureExtractor ArgMax->predicted_label final_label final_label final_label->Reshape ArrayFeatureExtractor->final_label reshaped_final_label reshaped_final_label Cast Cast (Cast) to=7 reshaped_final_label->Cast Reshape->reshaped_final_label Cast->label

previous

SGDClassifier - m-cl - log - {‘zipmap’: False}

next

SGDRegressor - b-reg - default -