# INT20H Hackathon — Data

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

采集时间：2026-10-19T07:12:06Z

Data description
train.csv
file has two columns – `name` and `category`.
`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.
train.zip
file has images mentioned in
train.csv
test.zip
file has images for which you need to predict a corresponding category.
Goal
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)`.
Metric
Submissions will be evaluated based on their
[accuracy](https://en.wikipedia.org/wiki/Accuracy_and_precision#In_binary_classification)
score.
Submission File Format
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