Places205

Places205 数据集是一个以场景为中心的大规模数据集，包含 205 个常见场景类别。训练数据集包含来自这些类别的大约 2,500,000 张图像。在训练集中，每个场景类别有最少 5,000 和最多 15,000 张图像。验证集每个类别包含 100 张图像（总共 20,500 张图像），测试集每个类别包含 200 张图像（总共 41,000 张图像）。The Places205 dataset is a large-scale scene-centric dataset encompassing 205 common scene categories. The training dataset contains approximately 2,500,000 images from these categories, with each scene category having a minimum of 5,000 and a maximum of 15,000 images. The validation set contains 100 images per category, totaling 20,500 images. The test set contains 200 images per category, totaling 41,000 images.