Instructions to use AmberY1201/best with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use AmberY1201/best with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("AmberY1201/best", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
室内物体识别模型(YOLO11m-seg)
用于 BEHAVIOR 仿真室内场景的物体识别与实例分割,共 172 类。输入 RGB 图像,输出物体类别、置信分数、检测框和掩码。
文件说明
best.pt:模型权重。class_ids.json:完整类别及编号。class_merge.json:应用侧类别合并规则,需要自行应用。
使用方法
安装依赖:
pip install ultralytics
下载 best.pt 后运行:
from ultralytics import YOLO
model = YOLO("best.pt")
results = model.predict("image.png", imgsz=640, conf=0.75, device="cpu")
results[0].save(filename="result.jpg")
有可用的 CUDA 环境时,可将 device="cpu" 改为 device=0。
说明
模型仍处于开发验证阶段,可能误检或漏检;conf=0.75 是当前实验门槛,可按需要调整。模型本身不输出三维坐标,获取物体坐标还需要深度图、相机参数和坐标变换。
- Downloads last month
- 9