https://github.com/fcakyon/ultralyticsplus

Huggingface utilities for Ultralytics/YOLOv8
https://github.com/fcakyon/ultralyticsplus

huggingface object-detection ultralytics yolov8

Last synced: 7 days ago
JSON representation

Huggingface utilities for Ultralytics/YOLOv8

• Host: GitHub
• URL: https://github.com/fcakyon/ultralyticsplus
• Owner: fcakyon
• License: gpl-3.0
• Created: 2023-01-09T23:18:23.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-02-07T21:13:40.000Z (9 months ago)
• Last Synced: 2024-10-29T14:20:11.260Z (10 days ago)
• Topics: huggingface, object-detection, ultralytics, yolov8
• Language: Python
• Homepage: https://yolov8.xyz
• Size: 88.9 KB
• Stars: 79
• Watchers: 2
• Forks: 11
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

• awesome-yolov8-models - package readme

README

        
# ultralytics+

Extra features for [ultralytics/ultralytics](https://github.com/ultralytics/ultralytics).

## installation

```bash

pip install ultralyticsplus

```

## push to 🤗 hub

```bash

ultralyticsplus --exp_dir runs/detect/train --hf_model_id HF_USERNAME/MODELNAME

```

## load from 🤗 hub

```python

from ultralyticsplus import YOLO, render_result

# load model

model = YOLO('HF_USERNAME/MODELNAME')

# set model parameters

model.overrides['conf'] = 0.25  # NMS confidence threshold

model.overrides['iou'] = 0.45  # NMS IoU threshold

model.overrides['agnostic_nms'] = False  # NMS class-agnostic

model.overrides['max_det'] = 1000  # maximum number of detections per image

# set image

image = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

# perform inference

results = model.predict(image, imgsz=640)

# parse results

result = results[0]

boxes = result.boxes.xyxy # x1, y1, x2, y2

scores = result.boxes.conf

categories = result.boxes.cls

scores = result.probs # for classification models

masks = result.masks # for segmentation models

# show results on image

render = render_result(model=model, image=image, result=result)

render.show()

```