This is Deep Learning project using a Convolutional Neural Network (CNN) designed to classify images from the CIFAR-10 dataset into 10 distinct categories.
The CIFAR-10 dataset is a widely used benchmark in image classification tasks. It consists of 60,000 32x32 color images in 10 different classes, making it an ideal dataset for testing and training image classification models.
- Convolutional Neural Network (CNN) architecture optimized for image classification.
- Trained on the CIFAR-10 dataset with 10 distinct classes.
- Evaluation of model performance using various classification metrics.
- Potential for further improvements and experimentation with Hyperparameters tuning.
-
Python3.10
-
TensorFlow
-
Computer Vision
-
CNN
- Clone this repository to your local machine.
git clone https://github.com/stefanshipinkoski/cifar-10-cnn.git
- Change the project directory.
cd cifar-10-cnn
- Create a conda environment and install the required dependencies:
conda env create -f enviorment.yml
- Activate the conda environment:
conda activate cifar-10-env
- Run Jupyter Notebook in the directory
jupyter notebook
Any contributions to this project are welcomed!