Implementation:Kornia Kornia ONNXSequential Export

Knowledge Sources	Kornia
Domains	ONNX, Deployment
Last Updated	2026-02-09 15:00 GMT

Overview

Concrete tool for exporting combined ONNX pipeline to a single file provided by Kornia.

Description

The ONNXSequential.export method serializes the combined ONNX computation graph to a single .onnx file on disk. This includes all model weights and the merged graph topology.

Usage

Call after constructing and validating an ONNXSequential pipeline.

Code Reference

Repository	https://github.com/kornia/kornia
File	`kornia/onnx/sequential.py`
Lines	L111–112
Signature	`def export(self, file_path: str, **kwargs) -> None`
Import	`from kornia.onnx import ONNXSequential` (call via instance method)

I/O Contract

Inputs

Parameter	Type	Required	Description
`file_path`	`str`	Yes	Output path for the combined ONNX file

Outputs

Single combined .onnx file on disk.

Usage Examples

Exporting a combined pipeline

from kornia.onnx import ONNXSequential

# Build pipeline
pipeline = ONNXSequential(
    "hf://operators/resize",
    "hf://operators/classifier",
    io_maps=[("resized", "input_image")],
)

# Export to a single file
pipeline.export("combined_pipeline.onnx")

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment