Deep CNN for Image Classification

This repository contains code for building and training a Deep Convolutional Neural Network (CNN) for image classification.

Getting Started

Install Dependencies and Setup: Clone the repository and configure TensorFlow to use GPU.
Remove Dodgy Images: Remove images with incorrect file extensions or corrupt files from the dataset.
Load Data: Load and visualize the image dataset from the directory.
Scale Data: Normalize the image data for training.
Split Data: Split the dataset into training, validation, and test sets.
Build Deep Learning Model: Construct and compile the CNN model.
Train: Train the model on the training dataset and validate using the validation set.
Plot Performance: Plot the training and validation loss and accuracy.
Evaluate: Evaluate the model's performance on the test dataset using precision, recall, and accuracy metrics.
Test: Test the model with a new image and predict its class.
Save the Model: Save the trained model for future use.

This project is licensed under the MIT License.