Package {churon}

Title:	'ONNX Runtime' Integration
Version:	0.1.12
Description:	Provides high-performance R bindings for 'ONNX Runtime' https://onnxruntime.ai/, enabling efficient machine learning model inference. Written in 'Rust' for memory safety and speed, the package supports cross-platform model execution with multiple execution providers. Includes comprehensive error handling and validation, with bundled MNIST example model for immediate testing and prototyping. Designed for production use with support for macOS (arm64), Linux (x64/arm64), and Windows (x64). Runtime libraries are downloaded on explicit request from https://github.com/microsoft/onnxruntime/releases.
License:	MIT + file LICENSE
URL:	https://github.com/mrchypark/churon
BugReports:	https://github.com/mrchypark/churon/issues
Encoding:	UTF-8
Config/rextendr/version:	0.5.0
SystemRequirements:	Cargo (>= 1.88.0), rustc (>= 1.88.0); ONNX Runtime (>= 1.28.0, optional at runtime)
Depends:	R (≥ 4.0.0)
Imports:	digest
Suggests:	testthat (≥ 3.2.0)
Config/roxygen2/version:	8.1.0
NeedsCompilation:	yes
Packaged:	2026-09-10 16:36:56 UTC; cypark
Author:	Chanyub Park [aut, cre], The authors of the dependency Rust crates [ctb] (See inst/AUTHORS for details), ONNX Project contributors [ctb, cph] (Bundled MNIST model, Apache License 2.0; see inst/COPYRIGHTS), Microsoft Corporation [cph] (ONNX Runtime, downloaded only on explicit user request)
Maintainer:	Chanyub Park <mrchypark@gmail.com>
Repository:	CRAN
Date/Publication:	2026-09-25 22:40:02 UTC

S3 Methods for TensorInfo and RSession

Description

These methods provide convenient access to object properties.

Usage

## S3 method for class 'TensorInfo'
x$name

Arguments

Value

For name and data_type, a character scalar identifying the tensor or its element type. For shape, an integer vector of tensor dimensions (negative dimensions indicate dynamic sizes). For a method name, a function bound to the object; for an unknown name, NULL.

Optimize Session Performance Batch Process Data

Description

Process data in batches for memory efficiency with large datasets.

Usage

batch_process_data(session, data_list, batch_size = 32)

Arguments

Value

A list of results from batch processing

Check if ONNX Runtime is Available

Description

This function checks if ONNX Runtime is properly configured and available.

Usage

check_onnx_runtime_available()

Value

Logical indicating whether ONNX Runtime is available

Get ONNX Runtime Information

Description

This function returns information about the current ONNX Runtime configuration.

Usage

get_onnx_runtime_info()

Value

A list containing ONNX Runtime configuration information

Install ONNX Runtime

Description

Download and install ONNX Runtime library for your platform. This is required before using the churon package if ONNX Runtime is not already installed on your system.

Usage

install_onnx_runtime(version = "1.29.0", quiet = FALSE, destdir, ...)

Arguments

Details

This function installs external software only when explicitly called. Supply destdir yourself; no installation directory is selected by default. The library is placed in destdir/lib and configured for this R session. In later sessions, set ORT_DYLIB_PATH to the installed library file before loading churon. Restart R before switching an already loaded runtime.

Value

Invisible TRUE on success, stops with error on failure.

ONNX Example Models

Description

List available example models bundled with the package.

Usage

onnx_example_models()

Value

A named character vector with model names as names and paths as values

ONNX Example Session

Description

Create a session with an example model.

Usage

onnx_example_session(model_name = "mnist", providers = NULL)

Arguments

Value

An RSession object

Get Input Information

Description

Retrieve information about model input tensors.

Usage

onnx_input_info(session)

Arguments

Value

A list of TensorInfo objects containing input tensor metadata

Examples

if (check_onnx_runtime_available()) {
  session <- onnx_example_session()
  input_info <- onnx_input_info(session)
  print(input_info)
}

Get Model Path

Description

Get the model path from a session.

Usage

onnx_model_path(session)

Arguments

Value

Character string with the model path

Examples

if (check_onnx_runtime_available()) {
  session <- onnx_example_session()
  model_path <- onnx_model_path(session)
  cat("Model path:", model_path, "\n")
}

Get Output Information

Description

Retrieve information about model output tensors.

Usage

onnx_output_info(session)

Arguments

Value

A list of TensorInfo objects containing output tensor metadata

Examples

if (check_onnx_runtime_available()) {
  session <- onnx_example_session()
  output_info <- onnx_output_info(session)
  print(output_info)
}

Get Execution Providers

Description

Get the execution providers available for the session.

Usage

onnx_providers(session)

Arguments

Value

A character vector of available execution providers

Examples

if (check_onnx_runtime_available()) {
  session <- onnx_example_session()
  providers <- onnx_providers(session)
  cat("Available execution providers:", paste(providers, collapse = ", "), "\n")
}

Run ONNX Inference

Description

Execute inference on an ONNX model with input data.

Usage

onnx_run(session, inputs)

Arguments

Value

A named list of output tensors

Examples

if (check_onnx_runtime_available()) {
  session <- onnx_example_session()
  inputs <- list(Input3 = array(0, dim = c(1, 1, 28, 28)))
  outputs <- onnx_run(session, inputs)
}

Check if ONNX Runtime is Installed

Description

Check if the ONNX Runtime library is installed and available.

Usage

onnx_runtime_is_installed()

Value

Logical indicating whether ONNX Runtime is installed.

Get ONNX Runtime Library Path

Description

Get the path to the ONNX Runtime library for the current platform.

Usage

onnx_runtime_lib_path()

Value

Character string with the library path.

Create ONNX Session

Description

Create a new ONNX Runtime session from a model file.

Usage

onnx_session(model_path, providers = NULL)

Arguments

Value

An RSession object for running inference

Examples

if (check_onnx_runtime_available()) {
  # Create session with default providers
  session <- onnx_example_session()

  # Create session with specific providers
  session <- onnx_example_session(providers = "cpu")
}

Safe ONNX Run

Description

Run inference with automatic error handling and monitoring.

Usage

safe_onnx_run(session, inputs, monitor_performance = FALSE)

Arguments

Value

Result of inference or NULL if failed

Safe ONNX Session Creation

Description

Safe ONNX Session Creation

Usage

safe_onnx_session(model_path, providers = NULL)

Arguments

Details

Create an ONNX session with automatic error handling.

Value

An RSession object or NULL if creation fails

Setup ONNX Runtime Library Path

Description

This function sets up the ONNX Runtime library path for the current session. It looks for the ONNX Runtime library in the package installation directory.

Usage

setup_onnx_runtime()

Value

Logical indicating whether setup was successful