https://github.com/kadirnar/yolov7-pip

This repo is a packaged version of the Yolov7 model.
https://github.com/kadirnar/yolov7-pip

computer-vision object-detection yolov7

Last synced: about 1 month ago
JSON representation

This repo is a packaged version of the Yolov7 model.

• Host: GitHub
• URL: https://github.com/kadirnar/yolov7-pip
• Owner: kadirnar
• License: mit
• Created: 2022-11-22T10:12:50.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-03-15T17:00:54.000Z (11 months ago)
• Last Synced: 2024-05-01T16:28:38.766Z (10 months ago)
• Topics: computer-vision, object-detection, yolov7
• Language: Python
• Homepage:
• Size: 66.2 MB
• Stars: 24
• Watchers: 2
• Forks: 8
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-yolo-object-detection - kadirnar/yolov7-pip - pip?style=social"/> : Packaged version of yolov7 model. (Other Versions of YOLO)
• awesome-yolo-object-detection - kadirnar/yolov7-pip - pip?style=social"/> : Packaged version of yolov7 model. (Other Versions of YOLO)

README

        




  Yolov7-Pip: Packaged version of the Yolov7 repository  





    





    

    

    





## 
Overview


This repo is a packaged version of the [Yolov7](https://github.com/WongKinYiu/yolov7) model.

### Installation

```

pip install yolov7detect

```

### Yolov7 Inference

```python

import yolov7

# load pretrained or custom model

model = yolov7.load('yolov7.pt')

#model = yolov7.load('kadirnar/yolov7-v0.1', hf_model=True)

# 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=1280, 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()

```

### Citation

```bibtex

@article{wang2022yolov7,

  title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},

  author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},

  journal={arXiv preprint arXiv:2207.02696},

  year={2022}

}

```

### Acknowledgement

A part of the code is borrowed from [Yolov5-pip](https://github.com/fcakyon/yolov5-pip). Many thanks for their wonderful works.