Tutorials
API
Examples Gallery
Notebooks Gallery
Other pages
Blog Gallery

Fast runtime with onnxruntime

Benchmark inference for scikit-learn models

What is the opset number?

Train and deploy a scikit-learn pipeline

Convert a pipeline with a LightGBM classifier

Intermediate results and investigation

Store arrays in one onnx graph

Black list operators when converting

Forward backward on a neural network on GPU

Train a scikit-learn neural network with onnxruntime-training on GPU

Modify the ONNX graph

Converter for WOE

Train a linear regression with forward backward

Benchmark ONNX conversion

Dataframe as an input

Funny discrepancies

Train a linear regression with onnxruntime-training

Convert a pipeline with a LightGBM regressor

Forward backward on a neural network on GPU (Nesterov) and penalty

Implement a new converter using other converters

One model, many possible conversions with options

Profile onnxruntime execution

Change the number of outputs by adding a parser

Two ways to implement a converter

Convert a pipeline with a XGBoost model

Choose appropriate output of a classifier

A new converter with options

Transfer Learning with ONNX

Profiling of ONNX graph with onnxruntime

Issues when switching to float

Implement a new converter

Benchmark onnxruntime optimization

Benchmark, comparison scikit-learn - forward-backward

Benchmark, comparison scikit-learn - onnxruntime-training

Benchmark operator LeakyRelu

Benchmark operator Slice

Benchmark, comparison torch - forward-backward

Converter for WOEEncoder from categorical_encoder

Benchmark onnxruntime API: run or …

Benchmark, comparison sklearn - forward-backward - classification

TfIdf and sparse matrices

Benchmark inference for a linear regression

Compares numpy to onnxruntime on simple functions

Fast design with a python runtime

Benchmark and profile of operator Slice

Add a parser to handle dataframes

Train a linear regression with onnxruntime-training on GPU in details

Train a linear regression with onnxruntime-training in details

Examples Gallery¶

Fast runtime with onnxruntime — Fast runtime with onnxruntime¶

Benchmark inference for scikit-learn models — Benchmark inference for scikit-learn models¶

What is the opset number? — What is the opset number?¶

Train and deploy a scikit-learn pipeline — Train and deploy a scikit-learn pipeline¶

Convert a pipeline with a LightGBM classifier — Convert a pipeline with a LightGBM classifier¶

Intermediate results and investigation — Intermediate results and investigation¶

Store arrays in one onnx graph — Store arrays in one onnx graph¶

Black list operators when converting — Black list operators when converting¶

Forward backward on a neural network on GPU — Forward backward on a neural network on GPU¶

Train a scikit-learn neural network with onnxruntime-training on GPU — Train a scikit-learn neural network with onnxruntime-training on GPU¶

Modify the ONNX graph — Modify the ONNX graph¶

Converter for WOE — Converter for WOE¶

Train a linear regression with forward backward — Train a linear regression with forward backward¶

Benchmark ONNX conversion — Benchmark ONNX conversion¶

Dataframe as an input — Dataframe as an input¶

Funny discrepancies — Funny discrepancies¶

Train a linear regression with onnxruntime-training — Train a linear regression with onnxruntime-training¶

Convert a pipeline with a LightGBM regressor — Convert a pipeline with a LightGBM regressor¶

Forward backward on a neural network on GPU (Nesterov) and penalty — Forward backward on a neural network on GPU (Nesterov) and penalty¶

Implement a new converter using other converters — Implement a new converter using other converters¶

One model, many possible conversions with options — One model, many possible conversions with options¶

Profile onnxruntime execution¶

Change the number of outputs by adding a parser — Change the number of outputs by adding a parser¶

Two ways to implement a converter — Two ways to implement a converter¶

Convert a pipeline with a XGBoost model — Convert a pipeline with a XGBoost model¶

Choose appropriate output of a classifier — Choose appropriate output of a classifier¶

A new converter with options — A new converter with options¶

Transfer Learning with ONNX — Transfer Learning with ONNX¶

Profiling of ONNX graph with onnxruntime — Profiling of ONNX graph with onnxruntime¶

Issues when switching to float — Issues when switching to float¶

Implement a new converter — Implement a new converter¶

Benchmark onnxruntime optimization — Benchmark onnxruntime optimization¶

Benchmark, comparison scikit-learn - forward-backward — Benchmark, comparison scikit-learn - forward-backward¶

Benchmark, comparison scikit-learn - onnxruntime-training — Benchmark, comparison scikit-learn - onnxruntime-training¶

Benchmark operator LeakyRelu — Benchmark operator LeakyRelu¶

Benchmark operator Slice — Benchmark operator Slice¶

Benchmark, comparison torch - forward-backward — Benchmark, comparison torch - forward-backward¶

Converter for WOEEncoder from categorical_encoder — Converter for WOEEncoder from categorical_encoder¶

Benchmark onnxruntime API: run or ... — Benchmark onnxruntime API: run or …¶

Benchmark, comparison sklearn - forward-backward - classification — Benchmark, comparison sklearn - forward-backward - classification¶

TfIdf and sparse matrices — TfIdf and sparse matrices¶

Benchmark inference for a linear regression — Benchmark inference for a linear regression¶

Compares numpy to onnxruntime on simple functions — Compares numpy to onnxruntime on simple functions¶

Fast design with a python runtime — Fast design with a python runtime¶

Benchmark and profile of operator Slice¶

Add a parser to handle dataframes — Add a parser to handle dataframes¶

Train a linear regression with onnxruntime-training on GPU in details — Train a linear regression with onnxruntime-training on GPU in details¶

Train a linear regression with onnxruntime-training in details — Train a linear regression with onnxruntime-training in details¶

Download all examples in Python source code: gyexamples_python.zip

Download all examples in Jupyter notebooks: gyexamples_jupyter.zip

Gallery generated by Sphinx-Gallery

previous

Gradient

next

Benchmark, comparison torch - forward-backward

© Copyright 2022, Xavier Dupré.

Created using Sphinx 4.4.0.