# 109-2 UTA DL APP HW1 — Data

来源：https://www.kaggle.com/competitions/109-2-uta-dl-app-hw1/data

采集时间：2026-10-19T09:16:20Z

Data Format
The training and testing images are 28x28 gray images.  There are 62 classes (0 ~ 9 & A ~ Z & a ~z) in EMNIST dataset, which are labeled sequentially as 0, 1, 2, ..., 61. The original data are saved in both binary and MATLAB format. We've converted it into NumPy format so you can easily load the data.
File descriptions
emnist-byclass-train.npz
- the training images and labels
emnist-byclass-test.npz
- the test images
simple_nn_train.ipynb
- A Jupyter notebook example of training a simple DNN model