{"id":13642887,"url":"https://github.com/madhawav/YOLO3-4-Py","last_synced_at":"2025-04-20T21:31:49.153Z","repository":{"id":31359148,"uuid":"127641706","full_name":"madhawav/YOLO3-4-Py","owner":"madhawav","description":"A Python wrapper on Darknet. Compatible with YOLO V3.","archived":false,"fork":false,"pushed_at":"2021-11-27T23:26:55.000Z","size":6217,"stargazers_count":516,"open_issues_count":5,"forks_count":162,"subscribers_count":23,"default_branch":"master","last_synced_at":"2025-04-07T23:07:53.803Z","etag":null,"topics":["cython","darknet","object-detection","python-wrapper","python3","yolo","yolo3","yolov3"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/madhawav.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-04-01T15:26:25.000Z","updated_at":"2025-03-13T03:11:53.000Z","dependencies_parsed_at":"2022-08-07T16:15:53.445Z","dependency_job_id":null,"html_url":"https://github.com/madhawav/YOLO3-4-Py","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madhawav%2FYOLO3-4-Py","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madhawav%2FYOLO3-4-Py/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madhawav%2FYOLO3-4-Py/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/madhawav%2FYOLO3-4-Py/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/madhawav","download_url":"https://codeload.github.com/madhawav/YOLO3-4-Py/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249965544,"owners_count":21352924,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cython","darknet","object-detection","python-wrapper","python3","yolo","yolo3","yolov3"],"created_at":"2024-08-02T01:01:37.682Z","updated_at":"2025-04-20T21:31:48.330Z","avatar_url":"https://github.com/madhawav.png","language":"Python","funding_links":[],"categories":["Other Versions of YOLO"],"sub_categories":[],"readme":"# YOLO3-4-Py\n[![PyPI Badge](https://img.shields.io/badge/PyPI-0.2.0-blue.svg)](https://pypi.org/project/yolo34py)\n[![PyPI Badge](https://img.shields.io/badge/PyPI-0.2.0--gpu-blue.svg)](https://pypi.org/project/yolo34py-gpu)\n[![Build Status](https://travis-ci.org/madhawav/YOLO3-4-Py.svg?branch=master)](https://travis-ci.org/madhawav/YOLO3-4-Py)\n\nA Python wrapper on [Darknet](https://github.com/pjreddie/darknet). Compatible with latest [YOLO V3](https://pjreddie.com/darknet/yolo).\nYOLO 3.0 is an Object Detector by [pjreddie](https://pjreddie.com/).\n\n![OutputImage](doc/output.jpg)\nImage source: http://absfreepic.com/free-photos/download/crowded-cars-on-street-4032x2272_48736.html\n\n## Google Colab Demo\nRefer the following link to preview YOLO3-4-Py in Google Colab: [[Google Colab](https://colab.research.google.com/drive/1DGzgpb8VR69EqSEb3bco6nSZQ_59eUZf?usp=sharing)]. \n\nCopy the notebook to your drive and run all cells. Ensure that you are in a GPU runtime. You can change the runtime by accessing the menu __Runtime__/__Change runtime type__.\n## What's New?\n* 2021-02-27 - Fixed the pkg-config related issue affecting some users of Ubuntu 20.04 and later.\n* 2020-06-18 - Added a sample Google Colab notebook demonstrating functionality.\n* 2019-01-15 - Added nvidia-docker support.\n* 2018-08-04 - Option to select the preferred GPU - `pydarknet.set_cuda_device(GPU_INDEX)`\n* 2018-04-23 - [PyPI Release of RC12](https://pypi.org/project/yolo34py-gpu)\n\n## Pre-requisites\n1) Python 3.5+\n2) Python3-Dev (For Ubuntu, `sudo apt-get install python3-dev`)\n3) Numpy `pip3 install numpy`\n4) Cython `pip3 install cython`\n5) Optionally, OpenCV 3.x with Python bindings. (Tested on OpenCV 3.4.0)\n    - You can use [this script](tools/install_opencv34.sh) to automate Open CV 3.4 installation (Tested on Ubuntu 16.04).\n    - Performance of this approach is better than not using OpenCV.\n    - Installations from PyPI distributions does not use OpenCV.\n```\nNOTE: OpenCV 3.4.1 has a bug which causes Darknet to fail. Therefore this wrapper would not work with OpenCV 3.4.1.\nMore details are available at https://github.com/pjreddie/darknet/issues/502\n```\n\n## Installation\nInstallation from PyPI distribution (as described below) is the most convenient approach if you intend to use yolo34py for your projects.\n\n### Installation of CPU Only Version\n```bash\npython3 -m pip install yolo34py\n```\n\n### Installation of GPU Accelerated Version\n```bash\npython3 -m pip install yolo34py-gpu\n```\n\n```\nNOTE: PyPI Deployments does not use OpenCV due to complexity involved in installation. \nTo get best performance, it is recommended to install from source with OpenCV enabled.\n```\n```\nNOTE: Make sure CUDA_HOME environment variable is set.\n```\n\n## How to run demos in local machine?\n1) If you have not installed already, run `python3 setup.py build_ext --inplace` to install library locally.\n2) Download \"yolov3\" model file and config files using `sh download_models.sh`.\n3) Run `python3 webcam_demo.py`, `python3 video_demo.py` or `python3 image_demo.py`\n\n## How to run demo using docker?\n1) Navigate to [docker](/docker) directory.\n2) Copy sample images into the `input` directory. Or else run [input/download_sample_images.sh](docker/input/download_sample_images.sh)\n3) Run `sh run.sh` or `sh run-gpu.sh`\n4) Observe the outputs generated in `output` directory.\n```\nGPU Version requires nvidia-docker\n```\n\n## Installation from Source\n1) Set environment variables\n - To enable GPU acceleration, `export GPU=1`.\n - To enable OpenCV, `export OPENCV=1`\n \n2) Navigate to `./src` and run `pip3 install .` to install library.\n\n### Using a custom version of Darknet\n1) Set environment variable DARKNET_HOME to download location of darknet.\n2) Add DARKNET_HOME to LD_LIBRARY_PATH. `export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$DARKNET_HOME`\n3) Continue instructions for _installation from source_.\n\n## Having trouble? \nKindly raise your issues in the issues section of GitHub repository.\n\n## Like to contribute?\nFeel free to send PRs or discuss on possible future improvements in issues section. \nYour contributions are most welcome!\n\n## Looking for YOLO v4?\nhttps://github.com/AlexeyAB/darknet\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmadhawav%2FYOLO3-4-Py","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmadhawav%2FYOLO3-4-Py","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmadhawav%2FYOLO3-4-Py/lists"}