MultNIST Dataset

Dataset containing the images and labels for the MultNIST data used in the CVPR NAS workshop Unseen-data challenge under the codename "Mateo"The MultNIST dataset is a constructed dataset from MNIST Images. The intention of this dataset is to require machine learning models to do more than just image classification but also perform a calculation, in this case multiplaction followed by a mod operation. For each image, three MNIST Images were randomly chosen and combined together through the colour channels, resulting in a three colour-channel image so each MNIST image represents one colour channel. The data is in a channels-first format with a shape of (n, 3, 28, 28) where n is the number of samples in the corresponding set (50,000 for training, 10,000 for validation, and 10,000 for testing).There are ten classes in the dataset, with 7,000 examples of each, distributed evenly between the three subsets.The label of each image is generated using the formula "(r * b * g) % 10" where r, g, and b are the red, green, and blue colour channels respectively. An example of a MultNIST Image would be a rgb configuation of 3, 7, and 4 respectively, which would result in a label of 4 ((3 * 7 * 4) % 10).本数据集包含用于CVPR神经架构搜索（Neural Architecture Search, NAS）研讨会“不可见数据挑战赛”（代号“Mateo”）的MultNIST数据的图像与标签。MultNIST数据集是由MNIST（Modified National Institute of Standards and Technology）手写数字图像构建而成的定制数据集。本数据集的设计目标并非仅要求机器学习模型完成图像分类任务，而是需要其同时执行计算操作——本次任务为乘法运算后接取模运算。对于每张样本图像，我们将随机选取三张MNIST图像，并通过颜色通道进行拼接组合，生成一张三通道彩色图像，每张MNIST图像分别对应一个颜色通道。该数据集采用通道优先（channels-first）数据格式，张量形状为(n, 3, 28, 28)，其中n代表对应子集的样本总量：训练集包含50000个样本，验证集与测试集各包含10000个样本。本数据集共设有10个类别，每个类别拥有7000个样本，且在训练、验证、测试三个子集间均匀分布。每张图像的标签通过公式“(r * b * g) % 10”计算生成，其中r、g、b分别对应红色、绿色、蓝色通道的数值。以MultNIST图像为例，若RGB三个通道的数值分别为3、7、4，则最终标签为4（计算过程：(3 × 7 × 4) % 10 = 84 % 10 = 4）。