CIFAR-10 Image Classification
This repository contains code for training and evaluating convolutional neural network models for image classification on the CIFAR-10 dataset.
Introduction
The CIFAR-10 dataset is a widely used benchmark in the field of computer vision. It consists of 60,000 32x32 color images across 10 classes, with each class containing 6,000 images. The classes include objects such as airplanes, automobiles, birds, cats, deer, dogs, frogs, horses, ships, and trucks.
Requirements
To run the code in this repository, you'll need the following dependencies:
- Python 3.x
- Jupyter Notebook
- PyTorch
- NumPy
- Matplotlib
- Pandas
Usage
Clone this repository:
https://github.com/Sarthug99/DL-Mini-Project-Submission.git
Navigate to the repository directory:
cd DL-Mini-Project-Submission
Open the Jupyter Notebook:
jupyter notebook
Open the mini-project-submission.ipynb notebook and run all the commands to train, evaluate, and test the models.
Model Architectures
This repository includes two model architectures for image classification:
- ResNet: A convolutional neural network based on the ResNet architecture.
- Modified ResNet: A modified version of ResNet with additional layers and depthwise separable convolutions.