Implementation Of Simple CNN

This project implements a convolutional neural network (CNN) for image classification of cats and dogs. The CNN consists of four convolutional layers three max pooling layers and two dense layers. It is trained using the CIFAR-10 dataset which contains 60000 32x32 color images divided into 10 classes. The model is compiled with the Adam optimizer sparse categorical crossentropy loss function and accuracy metric. It is trained for 10 epochs and achieves an accuracy of around 90% on the test set. The trained model can be saved and loaded for future use. Additionally the project includes code for visualizing sample images and their corresponding predictions. This project showcases the implementation of a CNN for image classification using TensorFlow and demonstrates its effectiveness in distinguishing between cats and dogs.

Project Screenshots: