Skip to main content
Ctrl+K
onnx-light 0.1.4 documentation - Home onnx-light 0.1.4 documentation - Home
  • Quick tour
  • Getting Started
  • Design
  • API
  • Operators
    • How-To
    • Miscellaneous
  • GitHub
  • Quick tour
  • Getting Started
  • Design
  • API
  • Operators
  • How-To
  • Miscellaneous
  • GitHub

Section Navigation

  • How-to Python / C++
    • Command-line interface
    • How to install onnx-light
    • How to replace onnx by onnx-light
    • Replacing onnxruntime’s protobuf usage with onnx-light
    • How to link a C++ project against the pre-built onnx-light artifacts
    • How to load and save ONNX files
    • How to re-align external weights without loading them in memory
    • How to save a model that shares weights with another on-disk model
    • How to save a model in the ORT flatbuffer format
    • How to collect backend test cases (by op type or by name)
    • How to use a custom kernel
    • How to use a custom optim shape inference function
    • How to use ONNX graph manipulation helpers
  • Core Examples
    • Benchmark streaming vs in-memory alignment of external data
    • Load and save ONNX models with external data
    • Measures loading and saving time for an ONNX model
    • Number of threads used to load and save ONNX models
    • Profiles ONNX external-data save time
    • Save an ONNX model in the ORT flatbuffer format and compare sizes
    • Track tensor weights while parsing with a raw_data callback
  • Optimization Examples
    • ComputeContext memory expressions
    • Evaluating inferred shapes with concrete input dimensions
    • Optimized Shape inference
    • Shape inference with a custom operator
    • Symbolic expressions for dimensions
    • pretty_onnx: shape info, shape tags, inplace and release annotations
  • Backend Test and Kernels Examples
    • Extend ReferenceEvaluator with a custom kernel
    • Retrieve a backend test case and display its model and data
    • Run a model with the runtime and inspect intermediate results
    • Run an ONNX model casting a float tensor into an int2 tensor
  • Examples with the C++ API
    • Standalone C++ example: combine onnx-light with Eclipse Aidge
    • Standalone C++ example: validate an ONNX model with onnx_light checker
    • Standalone C++ example: build, save and load an ONNX model with only lib_onnx_proto
    • Standalone C++ example: export an ONNX model to NNEF
    • Standalone C++ example: load an ONNX file with onnx_light
    • Standalone C++ example: measure ONNX loading time
    • Standalone C++ example: print a proto for debugging
    • Standalone C++ example: run every backend test through onnxruntime
  • How-To

How-To#

  • How-to Python / C++
  • Core Examples
  • Optimization Examples
  • Backend Test and Kernels Examples
  • Examples with the C++ API

previous

DelayedInitializer

next

How-to Python / C++
Show Source

Created using Sphinx 9.1.0.

Built with the PyData Sphinx Theme 0.19.0.