https://github.com/danielgatis/darknetpy
darknetpy is a simple binding for darknet's yolo detector.
https://github.com/danielgatis/darknetpy
darknet darknet-python
Last synced: about 2 hours ago
JSON representation
darknetpy is a simple binding for darknet's yolo detector.
- Host: GitHub
- URL: https://github.com/danielgatis/darknetpy
- Owner: danielgatis
- License: mit
- Created: 2017-09-01T20:38:44.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2022-12-01T13:20:15.000Z (almost 3 years ago)
- Last Synced: 2025-03-19T00:06:49.198Z (7 months ago)
- Topics: darknet, darknet-python
- Language: Jupyter Notebook
- Homepage:
- Size: 9.95 MB
- Stars: 66
- Watchers: 2
- Forks: 15
- Open Issues: 3
-
Metadata Files:
- Readme: README.rst
- License: LICENSE.txt
Awesome Lists containing this project
README
=========
Darknetpy
=========
|Downloads| |DownloadsMonth| |DownloadsWeek|
.. |Downloads| image:: https://pepy.tech/badge/darknetpy
:target: https://pepy.tech/project/darknetpy
.. |DownloadsMonth| image:: https://pepy.tech/badge/darknetpy/month
:target: https://pepy.tech/project/darknetpy/month
.. |DownloadsWeek| image:: https://pepy.tech/badge/darknetpy/week
:target: https://pepy.tech/project/darknetpy/week
Darknetpy is a simple binding for darknet's yolo (v4) detector.
.. image:: https://raw.githubusercontent.com/danielgatis/darknetpy/master/example/example.png
Installation
============
Install it from pypi
::
curl https://sh.rustup.rs -sSf | sh
::
rustup default nightly
::
pip install darknetpy
Install a pre-built binary
::
pip install https://github.com/danielgatis/darknetpy/raw/master/dist/darknetpy-4.2-cp37-cp37m-linux_x86_64.whl
Advanced options (only for pypi installation)
---------------------------------------------
::
GPU=1 pip install darknetpy
to build with CUDA to accelerate by using GPU (CUDA should be in /use/local/cuda).
::
CUDNN=1 pip install darknetpy
to build with cuDNN to accelerate training by using GPU (cuDNN should be in /usr/local/cudnn).
::
OPENCV=1 pip install darknetpy
to build with OpenCV.
::
OPENMP=1 pip install darknetpy
to build with OpenMP support to accelerate Yolo by using multi-core CPU.
Usage
=====
In example.py::
from darknetpy.detector import Detector
detector = Detector('/darknet/cfg/coco.data',
'/darknet/cfg/yolo.cfg',
'/darknet/yolo.weights')
results = detector.detect('/darknet/data/dog.jpg')
print(results)
Runing::
python example.py
Result::
[{'right': 194, 'bottom': 353, 'top': 264, 'class': 'dog', 'prob': 0.8198755383491516, 'left': 71}]
Build
=====
On the project root directory
::
docker run --rm -v `pwd`:/io quay.io/pypa/manylinux2010_x86_64 /io/build-wheels.sh
Buy me a coffee
===============
Liked some of my work? Buy me a coffee (or more likely a beer)
|BuyMeACoffee|
.. |BuyMeACoffee| image:: https://bmc-cdn.nyc3.digitaloceanspaces.com/BMC-button-images/custom_images/orange_img.png
:target: https://www.buymeacoffee.com/danielgatis