# ML Project 1: Build Handwritten Digit Recognizer — Data

来源：https://www.kaggle.com/competitions/ddumlindividual1/data

采集时间：2026-10-19T13:35:01Z

Hi, DDU students! Welcome to your first ML Project competition (Individual);
The data files train.csv and test.csv contain gray-scale images of hand-drawn digits from zero through nine.
Each image in the CSV file is 28 pixels in height and 28 pixels in width, totaling 784 pixels. Each pixel has a single pixel value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel value is an integer between 0 and 255, inclusive.
The test data set (test.csv) is the same as the training set, except that it does not contain the "label" column.
Your submission file should be in the following format: For each of the 500 images in the test set, output a single line containing the ImageId and the digit you predict. For example, if you predict that the first image is of a 2, the second image is of a 0, and the third image is of a 9, then your submission file would look like:
id_test_data,label
1,2
2,0
3,89
(499 more lines)
The evaluation metric for this contest is the categorization accuracy or the proportion of test images that are correctly classified. For example, a categorization accuracy of 0.97 indicates that you have correctly classified all but 3% of the images.