Metadata-Version: 2.4
Name: rknn-convert
Version: 0.1.0
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Build Tools
Classifier: Programming Language :: Rust
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: License :: OSI Approved :: MIT License
Requires-Dist: onnx==1.16.1
Requires-Dist: rknn-toolkit2==2.3.2
Requires-Dist: setuptools<81
Requires-Dist: typer>=0.16,<0.17
License-File: LICENSE
Summary: Command-line tool for converting ONNX, TF, and PyTorch models to RKNN format using rknn-toolkit2
Author-email: Boyd Johnson <boyd@boundarybit.io>
Requires-Python: >=3.8
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM

# rknn-convert
Command-line tool for converting machine learning model files to RKNN format.

## Purpose
Using the rknn-toolkit2 library requires writing the same function calls in a similar order every time.
This tool simplifies the process by allowing you to define your conversion process in a TOML configuration file.

## Usage
```
rknn-convert convert <config.toml>
```
Converts the model to RKNN format using the configuration file.

```
rknn-convert explain <config.toml>
```
Shows each configuration option and whether is is the default value.

Pipx installable via `pipx install rknn-convert`

