### **Description**

Can your model tell the difference between a **cat 🐱** and a **dog 🐶**?

In this competition, participants are challenged to build an image classification model that can accurately identify whether a given image contains a **cat** or a **dog**.
This task is a fundamental problem in **computer vision** and a great starting point for anyone exploring **deep learning** and **image recognition**.

---

## **About the Problem**

Image classification is a key task in the field of machine learning.
Given a set of labeled images, the goal is to train a model to automatically predict the label of a new, unseen image.
In this case, your model should predict whether an image belongs to the **cat** class or the **dog** class.

You can use traditional ML algorithms or train **convolutional neural networks (CNNs)** for higher accuracy.

---

## **Dataset Overview**

The dataset consists of a single folder containing mixed images of cats and dogs.
Each image is named as an integer (e.g., `0.jpg`, `1.jpg`, `2.jpg`, ...).

Participants must use these images to train and evaluate their models.
No labels are provided — you’ll have to infer them using your own model training and experimentation.


## **Mathematical Representation**

You can include equations in LaTeX format.
For instance, the prediction confidence of your model can be represented as:

$$ \epsilon = \sqrt{x_n^2 + 1} $$

This shows how LaTeX renders math expressions beautifully in your competition description.