SkalskiP / AS-One

Easy & Modular Computer Vision Detectors and Trackers - Run YOLOv7,v6,v5,R,X in under 20 lines of code.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

AS-One : A Modular Libary for YOLO Object Detection and Object Tracking BETA

croped

Table of Contents

  1. Introduction
  2. Prerequisites
  3. Clone the Repo
  4. Installation
  5. Running AS-One
  6. Train detectors with custom datasets
  7. Usage
  8. Benchmarks

1. Introduction

AS-One 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. We plan to offer support for future versions of YOLO when they get released.

This is One Library for most of your computer vision needs.

If you would like to dive deeper into YOLO Object Detection and Tracking, then check out our courses and projects

Watch the step-by-step tutorial

2. Prerequisites

3. Clone the Repo

Navigate to an empty folder of your choice.

git clone https://github.com/augmentedstartups/AS-One.git

Change Directory to AS-One

cd AS-One

4. Installation

For Linux

python3 -m venv .env
source .env/bin/activate

pip install numpy Cython
pip install cython-bbox

pip install asone


# for CPU
pip install torch torchvision

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

For Windows 10/11

python -m venv .env
.env\Scripts\activate
pip install numpy Cython
pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox

pip install asone

# for CPU
pip install torch torchvision

# for GPU
pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/cu113
or
pip install torch==1.10.1+cu113 torchvision==0.11.2+cu113 torchaudio===0.10.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html

Run in Google Colab

Open In Colab

5. Running AS-One

Run main.py to test tracker on data/sample_videos/test.mp4 video

import asone
from asone import utils
from asone.detectors import Detector
import cv2

img = cv2.imread('data/sample_imgs/test2.jpg')
detector = Detector(asone.YOLOV7_E6_ONNX, use_cuda=True) # Set use_cuda to False for cpu

filter_classes = ['person'] # Set to None to detect all classes

dets, img_info = detector.detect(img, , filter_classes=filter_classes)

bbox_xyxy = dets[:, :4]
scores = dets[:, 4]
class_ids = dets[:, 5]

img = utils.draw_boxes(img, bbox_xyxy, class_ids=class_ids)
cv2.imwrite('result.png', img)

Use Custom Trained Weights

Use your custom weights of a detector model trained on custom data by simply providing path of the weights file.

import asone
from asone import utils
from asone.detectors import Detector
import cv2

img = cv2.imread('data/sample_imgs/test2.jpg')
detector = Detector(asone.YOLOV7_PYTORCH, weights="data/custom_weights/yolov7_custom.pt", use_cuda=True) # Set use_cuda to False for cpu

filter_classes = ['person'] # Set to None to detect all classes

dets, img_info = detector.detect(img, , filter_classes=filter_classes)

bbox_xyxy = dets[:, :4]
scores = dets[:, 4]
class_ids = dets[:, 5]

img = utils.draw_boxes(img, bbox_xyxy, class_ids=class_ids, class_names=['License Plate']) # class_names are names of classes in your dataset
cv2.imwrite('result.png', img)

Changing Detector Models

Change detector by simply changing detector flag. The flags are provided in benchmark tables.

# Change detector
detector = Detector(asone.YOLOX_S_PYTORCH, use_cuda=True)

Run the asone/demo_detector.py to test detector.

# run on gpu
python -m asone.demo_detector data/sample_imgs/test2.jpg

# run on cpu
python -m asone.demo_detector data/sample_imgs/test2.jpg --cpu

Object Tracking

Video

Use tracker on sample video using gpu.

import asone
from asone import ASOne

# Instantiate Asone object
dt_obj = ASOne(tracker=asone.BYTETRACK, detector=asone.YOLOX_DARKNET_PYTORCH, use_cuda=True)

filter_classes = ['person'] # set to None to track all classes

# Get tracking function
track_fn = dt_obj.track_video('data/sample_videos/test.mp4', output_dir='data/results', save_result=True, display=True, filter_classes=filter_classes)

# Loop over track_fn to retrieve outputs of each frame 
for bbox_details, frame_details in track_fn:
    bbox_xyxy, ids, scores, class_ids = bbox_details
    frame, frame_num, fps = frame_details
    # Do anything with bboxes here

# To track using webcam
# Get tracking function
track_fn = dt_obj.track_webcam(cam_id=0, output_dir='data/results', save_result=True, display=True, filter_classes=filter_classes)

# Loop over track_fn to retrieve outputs of each frame 
for bbox_details, frame_details in track_fn:
    bbox_xyxy, ids, scores, class_ids = bbox_details
    frame, frame_num, fps = frame_details
    # Do anything with bboxes here

Use Custom Trained Weights for Detector

Use your custom weights of a detector model trained on custom data by simply providing path of the weights file.

import asone
from asone import ASOne

# Instantiate Asone object
dt_obj = ASOne(tracker=asone.BYTETRACK, detector=asone.YOLOX_DARKNET_PYTORCH, weights='data/custom_weights/yolov7_custom.pt', use_cuda=True)

filter_classes = ['person'] # set to None to track all classes

# Get tracking function
track_fn = dt_obj.track_video('data/sample_videos/test.mp4', output_dir='data/results', save_result=True, display=True, filter_classes=filter_classes, class_names=['License Plate']) #class_names are class names in your custom data

# Loop over track_fn to retrieve outputs of each frame 
for bbox_details, frame_details in track_fn:
    bbox_xyxy, ids, scores, class_ids = bbox_details
    frame, frame_num, fps = frame_details
    # Do anything with bboxes here

Changing Detector and Tracking Models

Change Tracker by simply changing the tracker flag.

The flags are provided in benchmark tables.

dt_obj = ASOne(tracker=asone.BYTETRACK, detector=asone.YOLOX_DARKNET_PYTORCH, use_cuda=True)
// Change tracker
dt_obj = ASOne(tracker=asone.DEEPSORT, detector=asone.YOLOX_DARKNET_PYTORCH, use_cuda=True)
dt_obj = ASOne(tracker=asone.DEEPSORT, detector=asone.YOLOX_S_PYTORCH, use_cuda=True)

To setup ASOne using Docker follow instructions given in docker setup

6. Train custom detection models

Learn and train your object detection model! Search for dataset perfect for your use-case on Roboflow Universe.

model open notebook in github open notebook in colab or kaggle complementary materials
YOLOv7 GitHub Colab Kaggle Roboflow YouTube
YOLOv6 GitHub Colab Kaggle Roboflow YouTube
YOLOv5 GitHub Colab Kaggle Roboflow YouTube
YOLOR GitHub Colab Kaggle Roboflow YouTube
YOLOX GitHub Colab Kaggle Roboflow YouTube

Find more training tutorials at Roboflow Notebooks.

ToDo

  • First Release
  • Import trained models
  • Simplify code even further
  • Add support for other Trackers and Detectors
  • M1/2 Apple Silicon Compatibility
Offered By: Maintained By:
AugmentedStarups AxcelerateAI

About

Easy & Modular Computer Vision Detectors and Trackers - Run YOLOv7,v6,v5,R,X in under 20 lines of code.

License:MIT License


Languages

Language:Python 99.4%Language:Shell 0.4%Language:Batchfile 0.1%Language:Dockerfile 0.1%