带标注的家具识别数据集，可识别床，椅子，餐桌，门，水槽，沙发，马桶，浴缸等12种，识别率87%，支持yolo，coco json，pascal voc xml格式的模型训练

前网易架构师-高司机

1164人浏览 · 2026-03-31 09:38:49

前网易架构师-高司机 · 2026-03-31 09:38:49 发布

带标注的家具识别数据集，可识别床，椅子，餐桌，门，水槽，沙发，马桶，浴缸等，识别率87%，支持yolo，coco json，pascal voc xml格式的模型训练

模型训练指标参数：

模型训练图：

数据集拆分

训练集

3190图像

验证集

84图像

测试集

67图像

预处理

自动定向：应用

调整大小：拉伸到640x640

增强

每个训练样本的输出数量：5

90° 旋转：顺时针、逆时针

旋转角度：-15° 至 +15° 之间

灰度化：应用于 15% 的图像

模糊：最大 2.5 像素

噪声：最多 0.1% 的像素添加

噪声裁剪遮挡：3 个遮挡框，每个尺寸为 10%

数据集标签：

'achair', 'bathtub', 'bed', 'chair', 'ctable', 'door', 'dtable', 'sink', 'sofa', 'ssink', 'ssofa', 'toilet'

数据集图片和标注信息示例：

数据集下载：

yolo26:https://download.csdn.net/download/pbymw8iwm/92774769

yolo v12:https://download.csdn.net/download/pbymw8iwm/92774768

yolo v11:https://download.csdn.net/download/pbymw8iwm/92774766

yolo v9:https://download.csdn.net/download/pbymw8iwm/92774770

yolo v8:https://download.csdn.net/download/pbymw8iwm/92774765

yolo v7:https://download.csdn.net/download/pbymw8iwm/92774763

yolo v5:https://download.csdn.net/download/pbymw8iwm/92774767

yolo darknet:https://download.csdn.net/download/pbymw8iwm/92774771

coco json: https://download.csdn.net/download/pbymw8iwm/92774772

pascal voc xml:https://download.csdn.net/download/pbymw8iwm/92774764

YOLO模型训练

下载数据集之后解压到当前文件夹，然后将我的仓库 https://gitcode.com/pbymw8iwm/YOLOProject里的训练模型脚本复制到文件夹下，假设你使用的是yolov8来训练你就用 python train_yolov8.py

注意，请根据你的GPU能力来适当调整训练参数，比如训练batch，patience，workers，以及模型类型（如果你的GPU硬件条件限制，可以联系作者进行付费模型训练，部分模型只需要一杯奶茶钱）

模型下载：

https://download.csdn.net/download/pbymw8iwm/92774837

模型验证测试情况：

验证测试代码：

#需要安装pip install ultralytics
from ultralytics import YOLO
import cv2

# 加载训练好的 YOLO .pt 模型
model = YOLO('best.pt')  # 替换为你实际的 .pt 模型文件路径

# 定义要测试的图片路径
image_path = './image.jpg'  # 替换为你实际的图片文件路径

# 使用模型对图片进行预测
results = model(image_path)

# 获取预测结果
for result in results:
    # 获取绘制了检测框的图片
    annotated_image = result.plot()

    # 显示图片
    cv2.imshow("YOLOv Inference", annotated_image)

    # 等待按键退出
    cv2.waitKey(0)

    # 关闭所有 OpenCV 窗口
    cv2.destroyAllWindows()

推理结果：

{
"predictions": [
{
"x": 80.5,
"y": 495,
"width": 121,
"height": 88,
"confidence": 0.905,
"class": "sofa",
"class_id": 8,
"detection_id": "8398ebd1-f2e2-45c8-857c-fbd32a5025f6"
},
{
"x": 148.5,
"y": 205.5,
"width": 51,
"height": 87,
"confidence": 0.905,
"class": "ctable",
"class_id": 4,
"detection_id": "14974335-9c0e-43b6-9ff5-e7f6464c692f"
},
{
"x": 149.5,
"y": 59.5,
"width": 51,
"height": 85,
"confidence": 0.904,
"class": "ctable",
"class_id": 4,
"detection_id": "15696dd0-b737-4030-9294-bb573ebbd913"
},
{
"x": 331,
"y": 464.5,
"width": 84,
"height": 123,
"confidence": 0.9,
"class": "dtable",
"class_id": 6,
"detection_id": "23f9f47c-26a5-4283-bbb3-c26898326631"
},
{
"x": 507.5,
"y": 362,
"width": 89,
"height": 70,
"confidence": 0.9,
"class": "bathtub",
"class_id": 1,
"detection_id": "c63a8c50-c5fe-42fb-9a9c-293b2c4d4cd3"
},
{
"x": 70,
"y": 394.5,
"width": 60,
"height": 93,
"confidence": 0.895,
"class": "ctable",
"class_id": 4,
"detection_id": "01ce1cd4-1206-4550-bc9f-e51f6893ca40"
},
{
"x": 413,
"y": 509.5,
"width": 70,
"height": 65,
"confidence": 0.88,
"class": "sink",
"class_id": 7,
"detection_id": "ab339152-dac7-4a86-8af3-c4dc7caa506b"
},
{
"x": 353,
"y": 67,
"width": 88,
"height": 98,
"confidence": 0.879,
"class": "bed",
"class_id": 2,
"detection_id": "7f11e368-d765-48d8-8ab2-242afc98abc7"
},
{
"x": 282,
"y": 300.5,
"width": 60,
"height": 129,
"confidence": 0.877,
"class": "door",
"class_id": 5,
"detection_id": "a289d9ea-e623-480f-81cc-99baa9d6733c"
},
{
"x": 428.5,
"y": 395.5,
"width": 69,
"height": 113,
"confidence": 0.875,
"class": "door",
"class_id": 5,
"detection_id": "34ebf0f8-68ba-464e-9d0d-908ac165f0ad"
},
{
"x": 251,
"y": 583.5,
"width": 60,
"height": 113,
"confidence": 0.859,
"class": "door",
"class_id": 5,
"detection_id": "f6e28cdc-e8e5-4f38-9336-1c8584e096eb"
},
{
"x": 595.5,
"y": 430.5,
"width": 49,
"height": 67,
"confidence": 0.807,
"class": "toilet",
"class_id": 11,
"detection_id": "1c7f0b5a-6ad9-44f1-a69f-5f950af2fb35"
},
{
"x": 360.5,
"y": 177.5,
"width": 79,
"height": 101,
"confidence": 0.801,
"class": "bed",
"class_id": 2,
"detection_id": "ca1a2bd2-c15e-480d-952f-dae5ecb239c5"
}
]
}

推理结果：

{
"predictions": [
{
"x": 523,
"y": 327.5,
"width": 28,
"height": 49,
"confidence": 0.93,
"class": "ctable",
"class_id": 4,
"detection_id": "146f4cb7-2a4b-40c6-b820-236a457da41e"
},
{
"x": 244.5,
"y": 579.5,
"width": 51,
"height": 55,
"confidence": 0.922,
"class": "bed",
"class_id": 2,
"detection_id": "e60e12b1-d1f4-4fc8-b2a1-a489d979910c"
},
{
"x": 279.5,
"y": 125.5,
"width": 63,
"height": 89,
"confidence": 0.913,
"class": "dtable",
"class_id": 6,
"detection_id": "d406b8ff-8f98-4d11-ab45-731ae1e4ae2f"
},
{
"x": 244.5,
"y": 343.5,
"width": 63,
"height": 89,
"confidence": 0.912,
"class": "dtable",
"class_id": 6,
"detection_id": "afaed4b6-1237-4b7e-98f0-0caa5b60bf75"
},
{
"x": 597.5,
"y": 453.5,
"width": 35,
"height": 87,
"confidence": 0.91,
"class": "bed",
"class_id": 2,
"detection_id": "bb0f5c3c-6473-4bcc-a9cb-0d073672862d"
},
{
"x": 437,
"y": 453.5,
"width": 36,
"height": 87,
"confidence": 0.908,
"class": "bed",
"class_id": 2,
"detection_id": "dfba14f1-fa9a-4510-a4b3-55f9b349a05c"
},
{
"x": 525,
"y": 203.5,
"width": 24,
"height": 85,
"confidence": 0.908,
"class": "bathtub",
"class_id": 1,
"detection_id": "c63c76ce-9abb-48fe-a17f-ba454494f0e4"
},
{
"x": 545,
"y": 453,
"width": 36,
"height": 86,
"confidence": 0.904,
"class": "bed",
"class_id": 2,
"detection_id": "7634a0e6-fa93-4cf9-8796-bedc729b4c62"
},
{
"x": 523,
"y": 68,
"width": 26,
"height": 88,
"confidence": 0.903,
"class": "bathtub",
"class_id": 1,
"detection_id": "dfd89ffd-1c6d-45f4-b04e-f744bda18002"
},
{
"x": 541.5,
"y": 595.5,
"width": 31,
"height": 51,
"confidence": 0.902,
"class": "ctable",
"class_id": 4,
"detection_id": "3eb3ca0c-a30e-4656-ba22-388aaa55d5f5"
},
{
"x": 491.5,
"y": 451.5,
"width": 35,
"height": 85,
"confidence": 0.902,
"class": "bed",
"class_id": 2,
"detection_id": "9bb9a427-6013-48ef-baf5-04cc2cfc3a01"
},
{
"x": 453.5,
"y": 594.5,
"width": 29,
"height": 49,
"confidence": 0.889,
"class": "ctable",
"class_id": 4,
"detection_id": "372eedfe-7bd1-430a-a2e6-e103b21879f1"
},
{
"x": 124.5,
"y": 119.5,
"width": 27,
"height": 51,
"confidence": 0.884,
"class": "ctable",
"class_id": 4,
"detection_id": "dddaa611-03d6-4ad4-8da8-8ac9205cb229"
},
{
"x": 288,
"y": 251,
"width": 38,
"height": 66,
"confidence": 0.882,
"class": "door",
"class_id": 5,
"detection_id": "27db1168-baab-4a76-8173-4d32421475a2"
},
{
"x": 459.5,
"y": 252,
"width": 37,
"height": 64,
"confidence": 0.874,
"class": "door",
"class_id": 5,
"detection_id": "d97d831b-d950-438c-8d7b-b9d3bcc1837d"
},
{
"x": 497.5,
"y": 595,
"width": 31,
"height": 50,
"confidence": 0.873,
"class": "ctable",
"class_id": 4,
"detection_id": "6afe1d28-f4c9-4e8d-bd78-3d1bd6b12b11"
},
{
"x": 396.5,
"y": 45.5,
"width": 27,
"height": 41,
"confidence": 0.87,
"class": "toilet",
"class_id": 11,
"detection_id": "087a58a2-72e9-41bd-93f7-25a6e0ee86dd"
},
{
"x": 189,
"y": 414,
"width": 44,
"height": 68,
"confidence": 0.869,
"class": "door",
"class_id": 5,
"detection_id": "db083400-1f73-4bb3-8e60-4cb9362b431e"
},
{
"x": 395.5,
"y": 239,
"width": 27,
"height": 40,
"confidence": 0.865,
"class": "toilet",
"class_id": 11,
"detection_id": "815d3e0c-3f27-4529-9510-ea7d4a7123b1"
},
{
"x": 318.5,
"y": 582.5,
"width": 31,
"height": 51,
"confidence": 0.865,
"class": "chair",
"class_id": 3,
"detection_id": "ea4d5ee0-53f6-4086-88d4-94b20790b5ed"
},
{
"x": 159.5,
"y": 115.5,
"width": 31,
"height": 113,
"confidence": 0.859,
"class": "sofa",
"class_id": 8,
"detection_id": "274ab05b-ae04-4123-a033-d1471e0f7aad"
},
{
"x": 119,
"y": 248.5,
"width": 40,
"height": 67,
"confidence": 0.855,
"class": "door",
"class_id": 5,
"detection_id": "561f9eee-60b0-4631-a7c5-956469510388"
},
{
"x": 357,
"y": 495.5,
"width": 46,
"height": 65,
"confidence": 0.852,
"class": "door",
"class_id": 5,
"detection_id": "43374764-b6d8-4d0c-a3a7-e72213dfae00"
},
{
"x": 593.5,
"y": 598,
"width": 35,
"height": 56,
"confidence": 0.85,
"class": "ssofa",
"class_id": 10,
"detection_id": "d427e30f-a0a2-408d-a605-be3c2ca9cc26"
},
{
"x": 19.5,
"y": 119,
"width": 39,
"height": 66,
"confidence": 0.845,
"class": "door",
"class_id": 5,
"detection_id": "e2b5b57c-7a3f-400c-8356-11f1dd769b7f"
},
{
"x": 80.5,
"y": 115.5,
"width": 33,
"height": 113,
"confidence": 0.835,
"class": "sofa",
"class_id": 8,
"detection_id": "9b792622-1d2b-4c5e-88f0-130c4f61532b"
},
{
"x": 349,
"y": 67,
"width": 24,
"height": 72,
"confidence": 0.828,
"class": "sink",
"class_id": 7,
"detection_id": "53822221-72fb-42cf-9af1-312aaea3ad44"
},
{
"x": 240,
"y": 28.5,
"width": 50,
"height": 35,
"confidence": 0.81,
"class": "sink",
"class_id": 7,
"detection_id": "cd54f2b5-5be7-4eb7-9940-4a05be133027"
},
{
"x": 408,
"y": 591,
"width": 36,
"height": 58,
"confidence": 0.809,
"class": "bed",
"class_id": 2,
"detection_id": "ea52b384-956c-4781-a631-6c7938493cb3"
}
]
}

AtomGit开源社区

AtomGit 是由开放原子开源基金会联合 CSDN 等生态伙伴共同推出的新一代开源与人工智能协作平台。平台坚持“开放、中立、公益”的理念，把代码托管、模型共享、数据集托管、智能体开发体验和算力服务整合在一起，为开发者提供从开发、训练到部署的一站式体验。

更多推荐

智能体 JSON 处理防护与优化方案（实战版）

让智能体稳定处理 JSON 的关键不是“让模型一次就对”，而是构建一个可靠的数据处理链路✅ 前端约束生成✅ 中间严格校验✅ 后端有限修复✅ 异常可控重试即使模型不完美，系统仍然稳定。

AtomGit开源社区

AI写完文案就结束了？你的运营流程还停留在“手动时代“

闭环流程 = AI生成内容 → AI创建任务 → AI统计执行 → AI督办提醒一句话指令↓AI生成文案（1分钟）↓AI调用SCRM创建任务（10秒）↓负责人确认下发（1分钟）↓员工执行↓AI自动统计执行情况（0）↓AI主动提醒未执行员工（0）全程只需3分钟人工介入，其他全部自动完成。AI写完文案就结束了？如果答案是"是"，那你的运营流程还停留在手动时代。真正的效率提升，不是优化某个环节，而是重构