Metadata-Version: 2.1
Name: meter_detection
Version: 0.2.0
Summary: a library for meter detection
Author-Email: svtter <svtter@qq.com>
License: MIT
Requires-Python: !=3.9.7,<3.10.0,>3.9
Requires-Dist: numpy<2.0
Requires-Dist: opencv-python==4.10.0.84
Requires-Dist: meterviewer>=1.3.1
Requires-Dist: pydantic>2.0
Requires-Dist: imgaug>=0.4.0
Description-Content-Type: text/markdown

# Detection model for Reading Area Detection

Detection models for meter reading area.

We use stanford-extra dataset as the basic dataset.

## Install

`pip install meter_detection`

Install keras and torch by yourself.

## Features

- [x] To train with stanford-extra dataset, using `examples/notebooks/keypoint_detection.ipynb`.
- [x] train with meter dataset, just run `examples/notebooks/meter_detection.ipynb`.
- [x] I want to use keras as the deep learning framework to build the detection model.
The detection model is planed to be based on `mobilenetv2` with pretrained weights.
