Metadata-Version: 2.4
Name: aeveon_simulator
Version: 8.0.0.post1
Summary: SynSense AG Aeveon Simulator
Keywords: synsense,event-based,neuromorphic,vision,image-processing,compression,simulation
Author-Email: Martin Rau <support@synsense.ai>
License-Expression: Apache-2.0
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: MacOS
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Scientific/Engineering :: Image Processing
Classifier: Topic :: Scientific/Engineering :: Visualization
Project-URL: Homepage, https://synsense.ai/
Project-URL: Documentation, https://synsense-sys-int.gitlab.io/aeveon-simulator
Requires-Python: >=3.10
Requires-Dist: nanobind-backend>=1.0
Description-Content-Type: text/markdown

# Aeveon Simulator

The Aeveon Simulator is a software simulation of the digital block of the Aeveon ASIC developed by SynSense Group. Its goal is to evaluate the encoder performance of the chip and to simplify system integration as well as application development.

This package contains both:

- the `aeveon-simulator` command line interface (CLI), which runs the full compression and decoding pipeline on an image sequence or video and reports figures of merit, and
- a Python API that allows more fine-grained control over simulator features, including low-level functions to follow how data flows through the chip.

## Installation

```bash
python -m venv .venv
source .venv/bin/activate
pip install aeveon_simulator
```

Prebuilt wheels are available for Linux and macOS, for Python 3.10 to 3.14.

## Quick start

Check that the CLI is available:

```bash
aeveon-simulator -h
```

Run the simulator with its default configuration on a folder of numbered images (e.g. `0.png`, `1.png`, ...):

```bash
aeveon-simulator -i PATH_TO_IMAGE_FOLDER
```

The results (summary video, reconstructed frames, figures of merit, chip configuration) are written to a new timestamped directory in the current working directory.

See the [CLI quickstart](https://synsense-sys-int.gitlab.io/aeveon-simulator/cli_quickstart.html) and the [Python API quickstart](https://synsense-sys-int.gitlab.io/aeveon-simulator/api_quickstart.html) for complete examples.

## Features

CLI:

- configure the chip through command line arguments or a JSON configuration file
- run the reference compression pipeline for all supported compression modes
- decode the encoded output back into reconstructed frames
- estimate compression ratio, bit rate, RMSE, power and latency per frame
- dump the MIPI CSI-2 payload produced by the chip

Python API:

- configure the chip with typed configuration classes
- encode frames using the high-level `Transformer` or the low-level, stateless encoding functions
- inspect and serialize the encoded data structures and MIPI payloads
- decode MIPI payloads with the reference decoder

## Documentation

- Project website: https://synsense.ai/
- Documentation: https://synsense-sys-int.gitlab.io/aeveon-simulator

## License

Apache 2.0
