Metadata-Version: 2.1
Name: sihl
Version: 0.0.3.dev11
Summary: Simple Image Heads and Layers
License: MIT
Author: jonregef
Author-email: jon.regef@pm.me
Requires-Python: >=3.8,<3.11
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Provides-Extra: all
Provides-Extra: lightning
Provides-Extra: timm
Requires-Dist: importlib-resources (==5.12.0) ; python_version < "3.9"
Requires-Dist: lightning (>=2.0.2,<3.0.0) ; extra == "lightning" or extra == "all"
Requires-Dist: timm (>=0.9.2,<0.10.0) ; extra == "timm" or extra == "all"
Requires-Dist: torch (>=2.1.0,<3.0.0)
Requires-Dist: torchmetrics (>=0.11.4,<0.12.0)
Requires-Dist: torchvision (>=0.16.0,<0.17.0)
Description-Content-Type: text/markdown

# Simple Image Heads and Layers

[![PyPI](https://img.shields.io/pypi/v/sihl.svg)][pypi_]
[![python versions](https://img.shields.io/pypi/pyversions/sihl)][python version]
[![coverage](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/jonregef/c203d6bce2a485ab49d1814ff3218a06/raw/covbadge.json)][coverage]
[![black](https://img.shields.io/badge/code%20style-black-000000.svg)][black]

[pypi_]: https://pypi.org/project/sihl/
[python version]: https://pypi.org/project/sihl
[coverage]: https://coverage.readthedocs.io/en/7.2.5/
[black]: https://github.com/psf/black

## Installation

```console
pip install sihl
```

<!-- github-only -->

[license]: https://github.com/sihlAI/sihl/blob/main/LICENSE

## Supported tasks
### Classification
- Binary classification
- Multiclass classification
- Multilabel classification

### Regression
- Regression
- Angular regression
- Ordinal regression

### Detection
- Keypoint detection
- Object detection
- Quadrilateral detection

### Segmentation
- Instance segmentation
- Semantic segmentation
- Panoptic segmentation
  - via multi-headed model (instance segmentation + semantic segmentation)

### Other
- Autoencoding
- Depth estimation
- Text recognition

