Tutorial

The tutorial goes from a simple example which converts a pipeline to a more complex example involving operator not actually implemented in ONNX operators or ONNX ML Operators.

• 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
  • Black list operators when converting
  • Issues when switching to float
  • Intermediate results and investigation
  • Dataframe as an input
  • Transfer Learning with ONNX
• Using converter from other libraries
  • Convert a pipeline with a LightGBM model
  • Convert a pipeline with a XGBoost model
• A custom converter for a custom model
  • Implement a new converter
  • Two ways to implement a converter
  • Implement a new converter using other converters
  • A new converter with options
  • Change the number of outputs by adding a parser
  • Add a parser to handle dataframes
• Extend ONNX, extend runtime
  • Fast design with a python runtime
  • Fast runtime with onnxruntime
• Complex Scenarios
  • TfIdf and sparse matrices

The tutorial was tested with following version:

<<<

import sys
import numpy
import scipy
import sklearn
import lightgbm
import onnx
import onnxmltools
import onnxruntime
import xgboost
import skl2onnx
import mlprodict
import onnxcustom
import pyquickhelper

print("python {}".format(sys.version_info))
mods = [numpy, scipy, sklearn, lightgbm, xgboost,
        onnx, onnxmltools, onnxruntime, onnxcustom,
        skl2onnx, mlprodict, pyquickhelper]
mods = [(m.__name__, m.__version__) for m in mods]
mx = max(len(_[0]) for _ in mods) + 1
for name, vers in sorted(mods):
    print("{}{}{}".format(name, " " * (mx - len(name)), vers))

>>>

    python sys.version_info(major=3, minor=9, micro=1, releaselevel='final', serial=0)
    lightgbm      3.2.1
    mlprodict     0.7.1602
    numpy         1.21.2
    onnx          1.10.1
    onnxcustom    0.1.1
    onnxmltools   1.9.92
    onnxruntime   1.10.91
    pyquickhelper 1.10.3639
    scipy         1.7.1
    skl2onnx      1.9.3001
    sklearn       1.1.dev0
    xgboost       1.4.2