Metadata-Version: 2.1
Name: segal
Version: 0.1.0
Summary: Sequence labeling active learning framework for Python
Home-page: https://github.com/tech-sketch/SegAL
License: MIT
Author: Xu Liang
Author-email: liangxu006@gmail.com
Requires-Python: >=3.8,<3.12
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Software Development :: Libraries
Requires-Dist: albumentations (>=1.3.0,<2.0.0)
Requires-Dist: matplotlib (>=3.6.0,<4.0.0)
Requires-Dist: scipy (>=1.8.0,<2.0.0)
Requires-Dist: segmentation-models-pytorch (==0.3.0)
Project-URL: Bug Tracker, https://github.com/tech-sketch/SegAL/issues
Project-URL: Changelog, https://segal.readthedocs.io/changelog.html
Project-URL: Documentation, https://segal.readthedocs.io
Project-URL: Repository, https://github.com/tech-sketch/SegAL
Description-Content-Type: text/markdown

# SegAL

SegAL is a semantice segmentation active learning tool.

## Installation

SegAL is available on PyPI:

`pip install seqal`

SegAL officially supports Python 3.8+.

## Usage

```
python examples/run_al_cycle.py --dataset CamVid  --data_path ./data/CamVid/ --model_name Unet --encoder resnet34 --encoder_weights imagenet --num_classes 12 --strategy LeastConfidence --seed_ratio 0.02 --query_ratio 0.02 --n_epoch 1
```
