Example datasets for BluVision Haustoria

Supplementary Data Protocol This supplementary dataset includes all files necessary to reproduce and evaluate the training and validation of YOLOv8 and CNN models for detecting GUS-stained and haustoria-containing cells with the BluVision Haustoria software. 1. gus_training_set_yolo/- Contains the complete YOLOv8-compatible training dataset for GUS classification.- Format: PyTorch YOLOv5/8 structure from Roboflow export.- Subfolders: - train/, test/, val/: Image sets and corresponding label files. - data.yaml: Configuration file specifying dataset structure and classes. 2. haustoria_training_set_yolo/- Contains the complete YOLOv8-compatible training dataset for haustoria detection.- Format identical to gus_training_set_yolo/. 3. haustoria_training_set_cnn/- Dataset formatted for CNN-based classification.- Structure: - gus/: Images of cells without haustoria. - hau/: Images of cells with haustoria.- Suitable for binary classification pipelines (e.g., Keras, PyTorch). 4. yolo_models/- Directory containing the final trained YOLOv8 model weights.- Includes: - gus.pt: YOLOv8 model trained on GUS data. - haustoria.pt: YOLOv8 model trained on haustoria data.补充数据集规程 本补充数据集包含复现与评估用于通过BluVision Haustoria软件检测经GUS染色细胞及含吸器细胞的YOLOv8与卷积神经网络（Convolutional Neural Network, CNN）模型训练及验证所需的全部文件。 1. gus_training_set_yolo/：包含适配YOLOv8的完整GUS分类训练数据集。格式采用Roboflow导出的PyTorch版YOLOv5/8数据集结构。其子文件夹包括： - train/、test/、val/：图像集及对应标签文件 - data.yaml：指定数据集结构与类别信息的配置文件 2. haustoria_training_set_yolo/：包含适配YOLOv8的完整吸器检测训练数据集，格式与gus_training_set_yolo/完全一致。 3. haustoria_training_set_cnn/：适配基于卷积神经网络的分类任务的数据集，其结构如下： - gus/：不含吸器的细胞图像 - hau/：含吸器的细胞图像 该数据集适用于二元分类流水线（如Keras、PyTorch）。 4. yolo_models/：存储最终训练完成的YOLOv8模型权重的目录，包含以下文件： - gus.pt：基于GUS数据集训练得到的YOLOv8模型权重文件 - haustoria.pt：基于吸器数据集训练得到的YOLOv8模型权重文件