keremberke's picture
add ultralytics model card
d4a15a4
|
raw
history blame
1.93 kB
metadata
tags:
  - ultralyticsplus
  - yolov8
  - ultralytics
  - yolo
  - vision
  - image-segmentation
  - pytorch
  - awesome-yolov8-models
library_name: ultralytics
library_version: 8.0.20
inference: false
datasets:
  - keremberke/satellite-building-segmentation
model-index:
  - name: keremberke/yolov8m-building-segmentation
    results:
      - task:
          type: image-segmentation
        dataset:
          type: keremberke/satellite-building-segmentation
          name: satellite-building-segmentation
          split: validation
        metrics:
          - type: precision
            value: 0.62261
            name: mAP@0.5(box)
          - type: precision
            value: 0.61275
            name: mAP@0.5(mask)
keremberke/yolov8m-building-segmentation

Supported Labels

['Building']

How to use

pip install ultralyticsplus==0.0.21
  • Load model and perform prediction:
from ultralyticsplus import YOLO, render_result

# load model
model = YOLO('keremberke/yolov8m-building-segmentation')

# 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)

# observe results
print(results[0].boxes)
print(results[0].masks)
render = render_result(model=model, image=image, result=results[0])
render.show()