# configs/sub_data.yml # 专为对比模型训练的数据集设计的配置文件 # 支持对比不同训练策略(如蒸馏vs独立训练) # 数据配置 data: source_dir: "../../data_center/contrast_data/total" # 数据集名称(示例用,可替换为实际数据集) train_dir: "../../data_center/contrast_data/v1/train" # 训练数据集根目录 val_dir: "../../data_center/contrast_data/v1/val" # 验证数据集根目录 data_extra_dir: "../../data_center/contrast_data/v1/extra" max_files_ratio: 0.1 min_files: 10 split_ratio: 0.9 combine_scr_dir: "../../data_center/contrast_data/v1/val" # 合并数据集源目录· combine_dst_dir: "../../data_center/contrast_data/v2/val" # 合并数据集目标目录 extend: extend_same_dir: true extend_extra: true extend_extra_dir: "../../data_center/contrast_data/v1/extra" # 扩展测试集数据 extend_train: true extend_train_dir: "../../data_center/contrast_data/v1/train" # 训练接数据扩展 limit: count_limit: true limit_count: 200 limit_dir: "../../data_center/contrast_data/v1/train" # 限制单个样本数量 control: combine: true # 是否进行子类数据集合并 split: false # 子类数据集拆解与扩增