Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
sklearn-onnx 1.18.0 documentation
Logo
sklearn-onnx 1.18.0 documentation
  • Introduction
  • Tutorial
    • The easy case
      • Train and deploy a scikit-learn pipeline
      • Benchmark ONNX conversion
      • What is the opset number?
      • One model, many possible conversions with options
      • Choose appropriate output of a classifier
      • Black list operators when converting
      • Issues when switching to float
      • Intermediate results and investigation
      • Store arrays in one onnx graph
      • Dataframe as an input
      • Modify the ONNX graph
    • Using converters from other libraries
      • Convert a pipeline with a LightGBM classifier
      • Convert a pipeline with a LightGBM regressor
      • Convert a pipeline with a XGBoost model
      • Convert a pipeline with a CatBoost classifier
    • A custom converter for a custom model
      • Implement a new converter
      • Two ways to implement a converter
      • Issues with FunctionTransformer
      • Implement a new converter using other converters
      • A new converter with options
      • Change the number of outputs by adding a parser
    • Advanced scenarios
      • Tricky issue when converting CountVectorizer or TfidfVectorizer
      • TfIdf and sparse matrices
      • Converter for WOE
    • Write converters for other libraries
      • Converter for pyod.models.iforest.IForest
  • API Summary
  • Gallery of examples
    • Metadata
    • ONNX Runtime Backend for ONNX
    • Draw a pipeline
    • Logging, verbose
    • Probabilities or raw scores
    • Train, convert and predict a model
    • Append onnx nodes to the converted model
    • Investigate a pipeline
    • Compare CDist with scipy
    • Convert a pipeline with a LightGbm model
    • Probabilities as a vector or as a ZipMap
    • Convert a model with a reduced list of operators
    • Custom Operator for NMF Decomposition
    • Discrepencies with StandardScaler
    • Benchmark a pipeline
    • Convert a pipeline with a XGBoost model
    • Discrepencies with GaussianProcessorRegressor: use of double
    • Errors with onnxruntime
    • Play with ONNX operators
    • Different ways to convert a model
    • Convert a pipeline with ColumnTransformer
    • TfIdfVectorizer with ONNX
    • Walk through intermediate outputs
    • When a custom model is neither a classifier nor a regressor (alternative)
    • When a custom model is neither a classifier nor a regressor
    • Write your own converter for your own model
  • Convert a pipeline
  • Converters with options
  • Supported scikit-learn Models
Back to top
View this page

Advanced scenarios¶

Unexpected discrepencies may appear. This a list of examples with issues and resolved issues.

  • Tricky issue when converting CountVectorizer or TfidfVectorizer
  • TfIdf and sparse matrices
  • Converter for WOE
Next
Tricky issue when converting CountVectorizer or TfidfVectorizer
Previous
Change the number of outputs by adding a parser
Copyright © 2018-2025, Microsoft
Made with Sphinx and @pradyunsg's Furo