# 109-2 NTUT Building Deep Learning Applications HW1 — Data

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

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2> Data Format </h2>
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.

<h2>File descriptions</h2>
<ul>
<li><strong>emnist-byclass-train.npz</strong> - the training images and labels</li>
<li><strong>emnist-byclass-test.npz</strong> - the test images</li>
<li><strong>simple_nn_train.ipynb</strong> - A Jupyter notebook example of training a simple DNN model </li>
</ul>