Proto Examples#

Examples demonstrating the proto features of onnx-light.

Benchmark streaming vs in-memory alignment of external data

Benchmark streaming vs in-memory alignment of external data

Inspect and edit nodes while parsing or serializing with a node callback

Inspect and edit nodes while parsing or serializing with a node callback

Load and save ONNX models with external data

Load and save ONNX models with external data

Measures fresh-process ONNX model-load cold start

Measures fresh-process ONNX model-load cold start

Measures loading and saving time for an ONNX model

Measures loading and saving time for an ONNX model

Number of threads used to load and save ONNX models

Number of threads used to load and save ONNX models

Profiles ONNX external-data save time

Profiles ONNX external-data save time

Save an ONNX model in the ORT flatbuffer format and compare sizes

Save an ONNX model in the ORT flatbuffer format and compare sizes

Statistics on the weights of an ONNX model

Statistics on the weights of an ONNX model

Track tensor weights while parsing with a raw_data callback

Track tensor weights while parsing with a raw_data callback

pretty_onnx: shape info, shape tags, inplace and release annotations

pretty_onnx: shape info, shape tags, inplace and release annotations

translate: turn an ONNX model back into Python code

translate: turn an ONNX model back into Python code

Gallery generated by Sphinx-Gallery