Создание и обучение сверточной нейронной сети (CNN) для классификации изображений из набора данных CIFAR-10 с аугментацией и предотвращением переобучения

Разработка сверточной нейронной сети для классификации изображений

Variety of neural network architectures implemented for different datasets and scenarios, along with regularization techniques and hyperparameter tuning strategies.

Experience CIFAR-Net, a streamlined Python solution for classifying CIFAR-10 images with precision. Train, test, and predict effortlessly using our efficient CNN architecture and automation scripts. Dive into diverse datasets, make accurate predictions, and redefine image classification with ease! 🌟

This is an implementation of the LeNet-5 architecture on the Cifar10 and MNIST datasets.

the CIFAR10 dataset

Tensorflow-based Object Detection on the CIFAR-10 dataset, served with FastAPI

In this project, the code snippet initialises a machine learning project for image classification.

This project encompasses a series of modules designed to facilitate the creation, training, and prediction using a PyTorch CNN Neural Network for Image classification based on the CIFAR10 dataset.

PyTorch implementation of "Learning Loss for Active Learning"

This repository contains the assignments of Artificial Intelligence course at Sharif University of Technology.

This repository contains a deep learning-based image classifier for the CIFAR-10 dataset. It leverages convolutional neural networks (CNNs) to classify images into ten classes, making it a valuable resource for image classification tasks.

This GitHub repository hosts my comprehensive CIFAR-10 image prediction project, which I completed as part of the SmartKnower program. CIFAR-10 is a widely used dataset in computer vision, consisting of 60,000 32x32 color images from 10 different classes.

This project is one of the Computational Intelligence course projects in the spring of 2023, and it includes code related to training neural networks with gradient descent, training neural network using neuroevolution, Neural Architecture Search (NAS), and Self-Organizing Maps (SOM)

This repository contains code to solve different tasks related to building, training and creating adversarial examples for classification models on the MNIST and CIFAR10 datasets.

This repository includes a study that aims to apply classification on well-known CIFAR10 dataset. Detailed info in ReadMe

The code explains step-by-step process of training a ResNet50 model for image classification on CiFar10 dataset and using cleverhans library to add adversarial attacks onto the dataset and compare the test accuracies

LeNet5 architecture implementation using pytorch, network parameter optimization and performance evaluation on dataset with Symmetric Label Noise

CIFAR-10 Classification

Convolutional Neural Network case study to predict image label of CIFAR10 images which are in built in Keras library