地球资源数据云——数据资源详情
儿童与成人分类
该数据集《Children vs Adults Classification》主要用于多分类任务，数据形态以图像为主，应用场景偏向安全检测。 题目说明：800 images of children and adults 任务类型：图像多分类。 建议流程：先检查类别分布与脏样本，再用迁移学习（如 ResNet/EfficientNet）建立基线。 评估建议：使用分层切分或交叉验证，优先关注 F1、Recall、AUC 等分类指标。 可用文件：未检测到标准 CSV，可优先查看目录中的索引或说明文件。 The dataset contains 2 folders: one with the test data and the other one with train data. The test - train - split ratio is 0.15, with the test dataset containing 120 images and the train dataset containing 680. The images have a resolution of 370x320 pixels in RGB color model. Both the folders contain 2 classes: Adults Children Inspiration This dataset is ideal for performing multiclass classification with deep neural networks like CNNs or simpler machine learning classification models.
摘要概览
该数据集《Children vs Adults Classification》主要用于多分类任务，数据形态以图像为主，应用场景偏向安全检测。 题目说明：800 images of children and adults
任务类型：图像多分类。
建议流程：先检查类别分布与脏样本，再用迁移学习（如 ResNet/EfficientNet）建立基线。
评估建议：使用分层切分或交叉验证，优先关注 F1、Recall、AUC 等分类指标。
可用文件：未检测到标准 CSV，可优先查看目录中的索引或说明文件。
The dataset contains 2 folders: one with the test data and the other one with train data. The test - train - split ratio is 0.15, with the test dataset containing 120 images and the train dataset containing 680. The images have a resolution of 370x320 pixels in RGB color model. Both the folders contain 2 classes:
Adults
Children
Inspiration
This dataset is ideal for performing multiclass classification with deep neural networks like CNNs or simpler machine learning classification models.