Yolov8m Table Extraction

🚀 keremberke/yolov8m-table-extraction

本项目基于ultralyticsplus和YOLOv8，用于表格提取的目标检测任务。它能准确识别有边框和无边框表格，在keremberke/table-extraction数据集上表现出色。

🚀 快速开始

支持的标签

['bordered', 'borderless']

如何使用

• 安装 ultralyticsplus：

pip install ultralyticsplus==0.0.23 ultralytics==8.0.21

• 加载模型并进行预测：

from ultralyticsplus import YOLO, render_result

# load model
model = YOLO('keremberke/yolov8m-table-extraction')

# 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()

更多模型请访问：awesome-yolov8-models

📦 安装指南

安装所需的库，使用以下命令：

pip install ultralyticsplus==0.0.23 ultralytics==8.0.21

💻 使用示例

基础用法

from ultralyticsplus import YOLO, render_result

# load model
model = YOLO('keremberke/yolov8m-table-extraction')

# 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()

📚 详细文档

模型信息

评估指标

在keremberke/table-extraction数据集的验证集上，模型的mAP@0.5(box)精度为 0.95194。

📄 许可证

本项目采用AGPL-3.0许可证。