Model Description
YOLOv9: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
YOLOv9-Pip: Packaged version of the Yolov9 repository
Paper Repo: Implementation of paper - YOLOv9
Installation
pip install yolov9pip
Yolov7 Inference
import yolov9
# load pretrained or custom model
model = yolov7.load('kadirnar/yolov9-gelan-c')
# set model parameters
model.conf = 0.25 # NMS confidence threshold
model.iou = 0.45 # NMS IoU threshold
model.classes = None # (optional list) filter by class
# set image
imgs = 'inference/images'
# perform inference
results = model(imgs)
# inference with larger input size and test time augmentation
results = model(img, size=640, augment=True)
# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]
# show detection bounding boxes on image
results.show()
BibTeX Entry and Citation Info
@article{wang2024yolov9,
title={{YOLOv9}: Learning What You Want to Learn Using Programmable Gradient Information},
author={Wang, Chien-Yao and Liao, Hong-Yuan Mark},
booktitle={arXiv preprint arXiv:2402.13616},
year={2024}
}