# Bharath's Zoo — Data

来源：https://www.kaggle.com/competitions/cs4670spring2020pa3/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>Welcome to The Data Page!</h2>
Here you will find the test data for generating the submission csv file using Kaggle_Submission.ipynb. You find more details on how to integrate this dataset with your current code in the About this file section below.

<h2>/test_labeled</h2>
This folder contains 16 subfolders corresponding to each of the 16 classes. Try exploring the folder by clicking on the down arrow next to the folder name below. You will see that each "class folder" has 25 images. We have included them because **the distribution that these images come from is not the same distribution as the training images**. You may find it helpful to perform validation on this data to get an idea of how well your model generalizes. You may also train on these images along with the provided training data. **Note**: this distribution is similar to the one being used by Kaggle for both public and private rankings.

<h2>/test_unlabeled</h2>
This folder contains 1984 images on which you will perform class prediction. Make sure this folder is place inside /data so Kaggle_Submission.ipynb can locate it. Note: The distribution is similar to the labeled data in */test_labeled*. You **may not** hand-label the images as this is a **violation of Academic Integrity**. See **Rules** for more information.

Now get cracking. Bharath needs your help sorting the animals.