Yolov8s Nlf Head Detection

🚀 keremberke/yolov8s-nlf-head-detection

本項目基於ultralytics庫，使用YOLOv8模型進行目標檢測，可對美式橄欖球比賽中的頭盔目標進行檢測，在keremberke/nfl-object-detection數據集上進行了驗證。

🚀 快速開始

支持的標籤

['Helmet', 'Helmet-Blurred', 'Helmet-Difficult', 'Helmet-Partial', 'Helmet-Sideline']

如何使用

• 安裝 ultralyticsplus：

pip install ultralyticsplus==0.0.24 ultralytics==8.0.23

• 加載模型並進行預測：

from ultralyticsplus import YOLO, render_result

# load model
model = YOLO('keremberke/yolov8s-nlf-head-detection')

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

更多模型請訪問：awesome-yolov8-models

📦 安裝指南

安裝所需的庫，使用以下命令：

pip install ultralyticsplus==0.0.24 ultralytics==8.0.23

💻 使用示例

基礎用法

from ultralyticsplus import YOLO, render_result

# load model
model = YOLO('keremberke/yolov8s-nlf-head-detection')

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

📚 詳細文檔

模型信息

評估指標

在keremberke/nfl-object-detection數據集的驗證集上，模型的mAP@0.5(box)指標為 0.27882。