This repository contains an implementation of a binary image classification model using convolutional neural networks (CNNs) in PyTorch. The model is trained and evaluated on the CIFAR-10 dataset, which consists of 60,000 32x32 color images in 10 classes, with 6,000 images per class. The task is to classify each image as either a cat or a dog.
-
Python 3.7 or higher
-
PyTorch 1.9 or higher
-
torchvision 0.10 or higher
- Clone the repository:
git clone https://github.com/ArminMasoumian/binary-image-classification.git
- Navigate to the cloned repository:
cd binary-image-classification
- Install the required packages:
pip install -r requirements.txt
- Download the CIFAR-10 dataset:
python download_dataset.py
- Train the model:
python train.py
- Evaluate the model:
python evaluate.py
The model achieved an accuracy of 98.3% on the test set after training for 50 epochs. The training and validation curves are shown below:
This project is licensed under the MIT License - see the LICENSE file for details.