Metadata-Version: 2.4
Name: yaac
Version: 0.1.1
Summary: Yet Another AI Company - Python package for loading and using trained image classification models
Author-email: Phil Ammirato <phil.ammirato.yaac@gmail.com>
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/withyaac/yaac
Project-URL: Repository, https://github.com/withyaac/yaac
Project-URL: Documentation, https://github.com/withyaac/yaac#readme
Project-URL: Bug Tracker, https://github.com/withyaac/yaac/issues
Keywords: machine-learning,deep-learning,pytorch,image-classification,computer-vision
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy==2.3.3
Requires-Dist: safetensors>=0.5.0
Requires-Dist: torch==2.8.0
Requires-Dist: torchvision==0.23.0
Requires-Dist: transformers>=4.40.0
Provides-Extra: dev
Requires-Dist: mypy>=1.8.0; extra == "dev"
Requires-Dist: ruff>=0.3.0; extra == "dev"
Requires-Dist: pytest>=8.0.0; extra == "dev"
Dynamic: license-file

# yaac

[![PyPI version](https://img.shields.io/pypi/v/yaac.svg)](https://pypi.org/project/yaac/)
[![Python 3.10+](https://img.shields.io/pypi/pyversions/yaac.svg)](https://pypi.org/project/yaac/)
[![License](https://img.shields.io/pypi/l/yaac.svg)](https://pypi.org/project/yaac/)

Yet Another AI Company - Python package for loading and using trained image classification models.

## Installation

Install from PyPI:

```bash
pip install yaac
```

## Quick Start

Load a trained model and run inference:

```python
from yaac.common.model_loader import load_model_from_checkpoint
import torch

# Load your trained model
model, config = load_model_from_checkpoint("path/to/checkpoint", device="cuda")

# Run inference
image = torch.randn(1, 3, 224, 224)  # Your image tensor
with torch.no_grad():
    predictions = model(image)
    processed = model.postprocess(predictions)

print(f"Predictions: {processed}")
```

## What is yaac?

`yaac` is a Python package that provides:

- **Model Loading**: Load trained image classification models from exported checkpoints (safetensors + config.json)
- **Model Interface**: Standardized `TrainableModel` interface for consistent model usage
- **SIC Models**: Support for Simple Image Classifier (SIC) models with configurable backbones and heads

Models are trained using YAAC's infrastructure and exported in a format compatible with this package.

## Documentation

- [Contributing Guide](CONTRIBUTING.md) - For developers who want to contribute
- [Publishing Guide](publish/PUBLISHING.md) - For maintainers publishing new versions

## License

Apache 2.0 - See [LICENSE](LICENSE) for details.
