# AOML Hackathon 1 — Data

来源：https://www.kaggle.com/competitions/aoml-hackathon-1/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Here is the dataset structure:

- **train**: This folder contains subfolders for each Pokémon, with images in JPG format for training your model.
- **validation**: This folder contains subfolders for each Pokémon, with images in JPG format for validating your model.
- **test**: This folder contains all the images (JPG format) for which you need to predict the corresponding class.
- **sample_submission.csv**: This file serves as a reference for your final submission. The columns should be labeled as follows:
  - **Image_Name**: The file name of each image in the test folder.
  - **Class**: The predicted class (Pokémon name) for each image.

Ensure that your final submission follows the same structure and column names as provided in the **sample_submission.csv file**. **This is purely for you to understand the structure of the dataset, but the final submission must have as many records in the test dataset.**