This project is an implementation of image classification using the CIFAR-10 dataset. The CIFAR-10 dataset is a collection of 60,000 images in 10 different classes, with 6,000 images per class. The goal of this project is to build a machine learning model that can accurately classify these images into their respective classes.
The code for this project is written in Python and can be found in the CIFAR-10 Image Classification.ipynb notebook in this repository. The notebook uses the Keras library to build a convolutional neural network (CNN) model and train it on the CIFAR-10 dataset.
To run this project, you will need to have Python 3 installed on your machine. You will also need to install the following libraries:
- Keras
- NumPy
- Matplotlib
- TensorFlow You can install these libraries using pip. For example, to install Keras, you can run the following command:
pip install kerasOnce you have installed the required libraries, you can clone this repository to your local machine using Git. To do this, run the following command:
git clone https://github.com/reeba212/CIFAR-10-Image-Classification.gitTo run the notebook, navigate to the project directory in your terminal and run the following command:
jupyter notebook
This will open the Jupyter Notebook interface in your web browser. From here, you can open the CIFAR-10 Image Classification.ipynb notebook and run the cells to train and test the model.
After training the model on the CIFAR-10 dataset, we achieved an accuracy of over 70% on the test set. This demonstrates that the CNN model is effective at classifying images in the CIFAR-10 dataset.
This project shows how to build an image classification model using the CIFAR-10 dataset and the Keras library. With this knowledge, you can extend this project to work on other datasets and improve the accuracy of the model by fine-tuning the hyperparameters or using other techniques such as data augmentation.