asone 0.1.2.dev2

No project description provided

ASOne

Table of Contents

• Introduction
• Asone Library Installation
  • Install In Docker Container
    • Prerequisite
    • Installation
  • Install Locally

Introduction

Asone is a python wrapper for multiple detection and tracking algorithms all at one place. Different trackers such as ByteTrack, DeepSort or NorFair can be integrated with different versions of YOLO with minimum lines of code. This python wrapper provides yolo models in both ONNX and PyTorch versions.

Usage:

pip install asone


# for windows
pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox
# for linux
pip install cython-bbox

# for gpu
pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/cu113

Sample code:

import asone
from asone import ASOne

dt_obj = ASOne(tracker=asone.BYTETRACK, detector=asone.YOLOX_DARKNET_PYTORCH, use_cuda=True)
dt_obj.start_tracking('sample_videos/test.mp4')

Results on provided sample video

https://user-images.githubusercontent.com/107035454/195079926-aee47eac-0430-4ada-8cc7-cc9d1d13c889.mp4

Asone Library Installation

Install In Docker Container

Prerequisite

• Make sure you have docker installed in your system. if not reffer to docker installation for Linux, Windows

Installation

1. Clone the repo

git clone https://github.com/axcelerateai/asone.git
cd asone

2. If using windows, Run this command in command prompt.

set PWD=%cd%

2. Run docker coompose command.

# if you wanna test on gpu system
docker compose run asone-gpu

# if you wanna test on cpu system
docker compose run asone

3. In docker terminal.

# if using gpu
python main.py [VIDEO_PATH]

# if using cpu
python main.py [VIDEO_PATH] --cpu

Install Locally

1. Clone the repo

git clone https://github.com/axcelerateai/asone.git
cd asone

2. Create virtual env.

python3 -m venv .env

3. Activate venv

# linux
source .env/bin/activate

# windows
.env\Scripts\activate

4. Install asone

pip install .

5. Intall pre-requisite

# for windows
pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox

# for linux
pip install cython-bbox

6. Install torch

# for gpu
pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/cu113

7. Test it by runiing main.py

# if using gpu
python main.py [VIDEO_PATH]

# if using cpu
python main.py [VIDEO_PATH] --cpu