# INT20H Hackathon — Data

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

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>
Data description
</h2>

<li>
<strong>train.csv</strong> file has two columns – `name` and `category`.
</li>

`name` is the filename of an image. That image can be found in the `train` folder. 

`category` is the corresponding category of that image. There are 100 different categories.

<li>
<strong>train.zip</strong> file has images mentioned in <strong>train.csv</strong>
</li>

<li>
<strong>test.zip</strong> file has images for which you need to predict a corresponding category.
</li>

<h2>
Goal
</h2>

Your goal is to predict the correct classes for images.

Each image belongs to 1 of 100 categories.

For each image in the test set you must predict an integer value in range `[0, 100)`.

<h2>
Metric
</h2>

Submissions will be evaluated based on their <a href="https://en.wikipedia.org/wiki/Accuracy_and_precision#In_binary_classification">accuracy</a> score.

<h2>
Submission File Format
</h2>

You should submit a `.csv` file with exactly 16858 rows plus a header row.

Header row should only have two columns called `name` and `category`.

Your submission .csv file should have the following format:

    name,category
    0.jpg,9
    1.jpg,19
    2.jpg,29
    ...etc