the-khiem7/snakeaid-yolov12-5291-bbox

--- license: cc0-1.0 task_categories: - object-detection tags: - yolo - yolov12 - snake-detection - roboflow pretty_name: SnakeAid YOLOv12 5291 BBox --- # SnakeAid YOLOv12 5291 BBox ## Dataset Summary This repository contains a YOLO-format SnakeAid object-detection dataset for snake detection experiments. It is organized as image/label pairs across `train, valid, test` splits and is intended for training or evaluating YOLO-family detectors, including the related SnakeAid Detect YOLOv12 checkpoints linked below. > Safety note: snake detection can be safety-critical in real-world use. Treat model outputs trained on this data as assistive signals only; do not use them as the sole basis for handling, approaching, or identifying a snake. ## Key Details | Field | Value | | --- | --- | | Format | YOLO object detection | | Splits | `train, valid, test` | | Images | 5291 | | Label files | 5291 | | Classes | 22 | | License metadata | `cc0-1.0` | | Uploadable local files | 10585 | ## Splits | Split | Images | Labels | | --- | ---: | ---: | | train | 4795 | 4795 | | valid | 265 | 265 | | test | 231 | 231 | ## File Layout ```text data.yaml train/images/*.jpg train/labels/*.txt valid/images/*.jpg valid/labels/*.txt test/images/*.jpg test/labels/*.txt ``` Each image is paired with a YOLO `.txt` label file using the same stem. Class names and split paths are defined in `data.yaml`. ## Classes | Class ID | Name | | ---: | --- | | 0 | `cap_nia_bac` | | 1 | `cap_nia_nam` | | 2 | `cap_nong` | | 3 | `ho_mang_chua` | | 4 | `ho_mang_xiem` | | 5 | `khiem_vach` | | 6 | `luc_cuom` | | 7 | `luc_nua` | | 8 | `luc_xanh` | | 9 | `luc_xanh_duoi_do` | | 10 | `ran_cuom` | | 11 | `ran_dai_lon` | | 12 | `ran_hoa_can_van_dom` | | 13 | `ran_hoa_co_do` | | 14 | `ran_rao` | | 15 | `ran_rao_trau` | | 16 | `ran_ri_ca` | | 17 | `ran_roi` | | 18 | `ran_sai_co` | | 19 | `ran_soc_dua` | | 20 | `ran_soc_go` | | 21 | `ran_trun` | ## Loading Example ```python from huggingface_hub import snapshot_download dataset_dir = snapshot_download( repo_id="the-khiem7/snakeaid-yolov12-5291-bbox", repo_type="dataset", ) print(dataset_dir) ``` For YOLO training, point your training command at the downloaded `data.yaml`. ## Provenance - workspace: anh-by-i-n-nh-em - project: snakeaid - version: 7 - license: Public Domain - url: https://universe.roboflow.com/anh-by-i-n-nh-em/snakeaid/dataset/7 ## Related Models - None ## Limitations - The dataset is provided as a local YOLO export, not as a fully curated benchmark. - Class balance, duplicate images, annotation quality, and real-world geographic coverage have not been independently audited in this upload workflow. - Performance can vary significantly with lighting, camera angle, occlusion, species similarity, and image quality. - Use additional validation before deploying a detector trained on this data in field or safety-sensitive settings.--- 许可证：cc0-1.0 任务类别： - 目标检测（object detection） 标签： - YOLO（You Only Look Once） - YOLOv12 - 蛇类检测（snake detection） - Roboflow 展示名称：SnakeAid YOLOv12 5291 边界框（Bounding Box，BBox） --- # SnakeAid YOLOv12 5291 边界框（Bounding Box，BBox） ## 数据集摘要 本仓库包含一个适配蛇类检测实验的、采用YOLO格式的SnakeAid目标检测数据集。该数据集按照训练（train）、验证（valid）、测试（test）划分集组织为图像-标签对，可用于训练或评估YOLO系列检测器，包括下文链接的SnakeAid Detect YOLOv12 模型检查点。 > 安全提示：蛇类检测在实际应用中属于安全关键场景。仅可将基于本数据集训练得到的模型输出作为辅助参考信号，不得将其作为处理、接近或识别蛇类的唯一依据。 ## 关键细节 | 字段 | 取值 | | --- | --- | | 格式 | YOLO目标检测格式 | | 划分集 | `train, valid, test` | | 图像总数 | 5291 | | 标签文件数 | 5291 | | 类别数 | 22 | | 许可证元数据 | `cc0-1.0` | | 可上传本地文件数 | 10585 | ## 划分集 | 划分集 | 图像数 | 标签数 | | --- | ---: | ---: | | 训练集（train） | 4795 | 4795 | | 验证集（valid） | 265 | 265 | | 测试集（test） | 231 | 231 | ## 文件布局 text data.yaml train/images/*.jpg train/labels/*.txt valid/images/*.jpg valid/labels/*.txt test/images/*.jpg test/labels/*.txt 每张图像均配有一个同名的YOLO `.txt` 标签文件，类别名称与划分集路径均在`data.yaml`中定义。 ## 类别列表 | 类别ID | 类别名称 | | ---: | --- | | 0 | `cap_nia_bac` | | 1 | `cap_nia_nam` | | 2 | `cap_nong` | | 3 | `ho_mang_chua` | | 4 | `ho_mang_xiem` | | 5 | `khiem_vach` | | 6 | `luc_cuom` | | 7 | `luc_nua` | | 8 | `luc_xanh` | | 9 | `luc_xanh_duoi_do` | | 10 | `ran_cuom` | | 11 | `ran_dai_lon` | | 12 | `ran_hoa_can_van_dom` | | 13 | `ran_hoa_co_do` | | 14 | `ran_rao` | | 15 | `ran_rao_trau` | | 16 | `ran_ri_ca` | | 17 | `ran_roi` | | 18 | `ran_sai_co` | | 19 | `ran_soc_dua` | | 20 | `ran_soc_go` | | 21 | `ran_trun` | ## 加载示例 python from huggingface_hub import snapshot_download dataset_dir = snapshot_download( repo_id="the-khiem7/snakeaid-yolov12-5291-bbox", repo_type="dataset", ) print(dataset_dir) 若需进行YOLO训练，只需将训练命令指向下载得到的`data.yaml`文件即可。 ## 数据集来源 - 工作区：anh-by-i-n-nh-em - 项目：snakeaid - 版本：7 - 许可证：公共领域（Public Domain） - 来源链接：https://universe.roboflow.com/anh-by-i-n-nh-em/snakeaid/dataset/7 ## 关联模型 - 无 ## 局限性 - 本数据集仅作为本地YOLO导出文件提供，并非经过全面整理的基准测试集。 - 本次上传流程中未对类别平衡、重复图像、标注质量以及实际地理覆盖范围进行独立审核。 - 模型性能会随光照条件、拍摄角度、遮挡情况、物种相似度以及图像质量的变化产生显著波动。 - 在野外或安全敏感场景中部署基于本数据集训练得到的检测器前，需进行额外的验证工作。