# BrokenWorkshop - Kaggle pls fix — Data

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

采集时间：2026-10-24T04:02:10Z

The Street View House Numbers (SVHN) Dataset
SVHN is a real-world image dataset for developing machine learning and object recognition algorithms with minimal requirement on data preprocessing and formatting. It can be seen as similar in flavor to MNIST (e.g., the images are of small cropped digits), but comes from a significantly harder, unsolved, real world problem (recognizing digits and numbers in natural scene images). SVHN is obtained from house numbers in Google Street View images.

* 10 classes, 1 for each digit. Digit '1' has label 1, '9' has label 9 and '0' has label 10.
* MNIST-like 32-by-32 images centered around a single character (many of the images do contain some distractors at the sides).
File descriptions
train_x.npy
- the training set features as a numpy matrix. Dimension: (43954, 32, 32, 3).
train_y.npy
- the training set labels as a numpy matrix. Dimension: (43954,).
test.npy
- the test set as a numpy matrix. Dimension: (29303, 32, 32, 3)
example_submission.csv
- a sample submission file in the correct format
We are dealing with RGB images in this competition. The dimensions of the training set features matrix should be read as: 
43954 rgb images, each of which are 32 by 32 and have 3 channels corresponding to r,g,b.