Image Classification with CIFAR-10 Dataset

This project involves building a Convolutional Neural Network (CNN) for image classification using the CIFAR-10 dataset. The goal is to develop a deep learning model capable of accurately categorizing images into one of ten classes. The project is available at https://github.com/Yossranour1996/Image-classification .

Dataset Acquisition:

The CIFAR-10 dataset is employed, consisting of 60,000 32x32 color images in 10 different classes (e.g., airplanes, automobiles, birds).

Data Preprocessing:

The pixel values of the input images are normalized to a range between 0 and 1 for effective training.

Model Architecture:

The CNN model is structured with two sets of convolutional layers followed by pooling layers, enhancing the model's ability to capture hierarchical features.

The convolutional layers use the ReLU activation function, promoting non-linearity in feature extraction.

Max-pooling layers reduce spatial dimensions, preserving essential information.

A dense hidden layer with 64 neurons, activated by ReLU, serves as a feature extractor.

The final layer, with 10 neurons and the softmax activation function, produces class probabilities.

Model Compilation:

The model is compiled using categorical crossentropy as the loss function, Adam as the optimizer, and accuracy as the evaluation metric.

Prediction and Evaluation:

Predictions are made on the test set, and the model's performance is evaluated using the argmax function to determine the predicted classes.

The project utilizes the classification_report from scikit-learn to provide a detailed summary of the model's performance, including precision, recall, and F1-score for each class.

Skills:

#CNN #Deeplearing #Classification