• Make sure to install GPU drivers in your system if you want to use GPU . Follow driver installation for further instructions.
• Make sure you have MS Build tools installed in system if using windows.
• Download git for windows if not installed.

💾 Clone the Repository

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

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

pip install -r requirements.txt

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

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

pip install asone onnxruntime-gpu==1.12.1
pip install typing_extensions==4.7.1
pip install super-gradients==3.1.3
# 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

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


pip install -r requirements.txt

# for CPU
pip install torch torchvision

import asone
from asone import ASOne

model = ASOne(detector=asone.YOLOV9_C, use_cuda=True) # Set use_cuda to False for cpu
vid = model.read_video('data/sample_videos/test.mp4')

for img in vid:
    detection = model.detecter(img)
    annotations = ASOne.draw(detection, img=img, display=True)

Run the asone/demo_detector.py to test detector.

# run on gpu
python -m asone.demo_detector data/sample_videos/test.mp4

# run on cpu
python -m asone.demo_detector data/sample_videos/test.mp4 --cpu

import asone
from asone import ASOne

model = ASOne(detector=asone.YOLOV9_C, weights='data/custom_weights/yolov7_custom.pt', use_cuda=True) # Set use_cuda to False for cpu
vid = model.read_video('data/sample_videos/license_video.mp4')

for img in vid:
    detection = model.detecter(img)
    annotations = ASOne.draw(detection, img=img, display=True, class_names=['license_plate'])

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

# For macOs
# YOLO5
model = ASOne(detector=asone.YOLOV5X_MLMODEL)
# YOLO7
model = ASOne(detector=asone.YOLOV7_MLMODEL)
# YOLO8
model = ASOne(detector=asone.YOLOV8L_MLMODEL)

Use tracker on sample video.

import asone
from asone import ASOne

# Instantiate Asone object
model = ASOne(tracker=asone.BYTETRACK, detector=asone.YOLOV9_C, use_cuda=True) #set use_cuda=False to use cpu
tracks = model.video_tracker('data/sample_videos/test.mp4', filter_classes=['car'])

# Loop over track to retrieve outputs of each frame
for model_output in tracks:
    annotations = ASOne.draw(model_output, display=True)
    # Do anything with bboxes here

[Note] Use can use custom weights for a detector model by simply providing path of the weights file. in ASOne class.

model = ASOne(tracker=asone.BYTETRACK, detector=asone.YOLOV9_C, use_cuda=True)
# Change tracker
model = ASOne(tracker=asone.DEEPSORT, detector=asone.YOLOV9_C, use_cuda=True)

# Change Detector
model = ASOne(tracker=asone.DEEPSORT, detector=asone.YOLOX_S_PYTORCH, use_cuda=True)

Run the asone/demo_tracker.py to test detector.

# run on gpu
python -m asone.demo_tracker data/sample_videos/test.mp4

# run on cpu
python -m asone.demo_tracker data/sample_videos/test.mp4 --cpu

import asone
from asone import ASOne

model = ASOne(detector=asone.YOLOV9_C, segmentor=asone.SAM, use_cuda=True) #set use_cuda=False to use cpu
tracks = model.video_detecter('data/sample_videos/test.mp4', filter_classes=['car'])

for model_output in tracks:
    annotations = ASOne.draw_masks(model_output, display=True) # Draw masks

Sample code to detect text on an image

# Detect and recognize text
import asone
from asone import ASOne, utils
import cv2

model = ASOne(detector=asone.CRAFT, recognizer=asone.EASYOCR, use_cuda=True) # Set use_cuda to False for cpu
img = cv2.imread('data/sample_imgs/sample_text.jpeg')
results = model.detect_text(img)
annotations = utils.draw_text(img, results, display=True)

Use Tracker on Text

import asone
from asone import ASOne

# Instantiate Asone object
model = ASOne(tracker=asone.DEEPSORT, detector=asone.CRAFT, recognizer=asone.EASYOCR, use_cuda=True) #set use_cuda=False to use cpu
tracks = model.video_tracker('data/sample_videos/GTA_5-Unique_License_Plate.mp4')

# Loop over track to retrieve outputs of each frame
for model_output in tracks:
    annotations = ASOne.draw(model_output, display=True)

    # Do anything with bboxes here

Run the asone/demo_ocr.py to test ocr.

# run on gpu
 python -m asone.demo_ocr data/sample_videos/GTA_5-Unique_License_Plate.mp4

# run on cpu
 python -m asone.demo_ocr data/sample_videos/GTA_5-Unique_License_Plate.mp4 --cpu

Sample code to estimate pose on an image

# Pose Estimation
import asone
from asone import PoseEstimator, utils
import cv2

model = PoseEstimator(estimator_flag=asone.YOLOV8M_POSE, use_cuda=True) #set use_cuda=False to use cpu
img = cv2.imread('data/sample_imgs/test2.jpg')
kpts = model.estimate_image(img)
annotations = utils.draw_kpts(kpts, image=img, display=True)

• Now you can use Yolov8 and Yolov7-w6 for pose estimation. The flags are provided in benchmark tables.

# Pose Estimation on video
import asone
from asone import PoseEstimator, utils

model = PoseEstimator(estimator_flag=asone.YOLOV7_W6_POSE, use_cuda=True) #set use_cuda=False to use cpu
estimator = model.video_estimator('data/sample_videos/football1.mp4')
for model_output in estimator:
    annotations = utils.draw_kpts(model_output)
    # Do anything with kpts here

Run the asone/demo_pose_estimator.py to test Pose estimation.

# run on gpu
 python -m asone.demo_pose_estimator data/sample_videos/football1.mp4

# run on cpu
 python -m asone.demo_pose_estimator data/sample_videos/football1.mp4 --cpu