Metadata-Version: 2.1
Name: viame
Version: 0.23.2
Summary: VIAME: Video and Image Analytics for Marine Environments
License: BSD-3-Clause
Requires-Python: ==3.12.*
Description-Content-Type: text/markdown
Project-URL: Homepage, https://www.viametoolkit.org
Project-URL: Source, https://github.com/VIAME/VIAME
Project-URL: Documentation, https://viame.readthedocs.io
Project-URL: Issues, https://github.com/VIAME/VIAME/issues
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: C++
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Dist: numpy>=1.24.4
Requires-Dist: av
Requires-Dist: scriptconfig
Requires-Dist: ubelt
Requires-Dist: pillow>=9.4.0
Requires-Dist: opencv-python-headless
Requires-Dist: onnxruntime
Requires-Dist: ensemble_boxes
Requires-Dist: kwimage
Requires-Dist: kwcoco
Requires-Dist: kwarray
Requires-Dist: ndsampler
Requires-Dist: astunparse
Requires-Dist: pygtrie
Requires-Dist: networkx_algo_common_subtree
Requires-Dist: torch_liberator
Requires-Dist: liberator
Requires-Dist: requests
Requires-Dist: tqdm>=4.66.1
Requires-Dist: transformers>=5.1.0,<6.0.0
Requires-Dist: pydantic>=2.0,<3
Requires-Dist: pyDeprecate>=0.9,<0.10
Requires-Dist: supervision
Requires-Dist: hydra-core>=1.3.2
Requires-Dist: iopath>=0.1.10
Requires-Dist: torch>=2.11
Requires-Dist: torchvision>=0.18.1

# VIAME

VIAME is an open-source computer vision toolkit for analysing imagery and
video, built for marine science: detection, tracking, stereo measurement,
classification, search and training, in configurable pipelines.

This wheel carries the VIAME runtime and the `viame` command line tool.

## Install

```
pip install viame
```

Bring your own GPU stack: `torch` comes with the CUDA runtime this build
links against, and nothing CUDA is bundled here.

## Use

```
viame run detector_generic input.mp4       # run a pipeline over a video
viame train --list                         # what can be trained
viame score -c computed.csv -t truth.csv   # score results
```

```python
import viame
```

The pipelines that ship are those whose models are small enough to travel
with the code. Larger models are add-on packs, fetched at runtime:

```
viame add-ons
```

## Links

* [viametoolkit.org](https://www.viametoolkit.org)
* [Source](https://github.com/VIAME/VIAME)
* [Documentation](https://viame.readthedocs.io)

BSD 3-Clause licensed.

