 |
VOOZH | about |
A hands-on TensorFlow image recognition project teaching a computer to identify 10 everyday objects, originally for a linear algebra class, with tools to train a CNN, auto-tune settings, and test accuracy on random internet images.
Convolutional Neural Networks for Image Classification
This project demonstrates image classification using a Convolutional Neural Network (CNN) on the CIFAR-10 dataset. The model is trained to classify images into one of 10 classes.
A hands-on task involving training and experimenting with a small CNN (or comparable baseline model) on a CIFAR-10 subset.
In this project, I have built a convolutional neural network in Keras with Python on a CIFAR-10 dataset. First, we will explore our dataset, and then we will train our neural network using Python and Keras. After training the model and obtaining the suitable accuracy we finally conclude our model creation part. Next, we have used Tkinter library…
In this we use Bayesian Statistical principles to classify images present in 10 different clases such as airplane, automobile, bird, cat, deer, dog, frog, horse, ship and truck.
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 repository contains my final submission for the COMP3547 Deep Learning module assignment at Durham University in the academic year 2022/2023. The project focuses on diffusion-based models and their application in synthesising new, unique images, which could plausibly come from a training data set. Final grade received was 71/100.
This repository presents our work on reproducing the experiment from Federated Learning Clean-Label Attack (Y. Xie and T. Zhu, 2024). We conduct experiments on the MNIST and CIFAR-10 datasets under both IID and non-IID data partitioning across clients.
Project related to my thesis which focuses on Continual Learning carried out on the CIFAR10 dataset.
Deep Neural Network (DNN) and Convolutional Neural Network (CNN) trained to classify image data into 10 categories from the CIFAR-10 dataset.
This project demonstrates the implementation of a Softmax classifier from scratch, featuring both naive (loop-based) and vectorized versions for educational and performance comparison purposes. The implementation is based on CIFAR 10 dataset.
Flow matching implementation for the CIFAR10 dataset.
Classification Card Fraud with Logistic Regression & Regression with Decision Trees. Specially written for Bigdata deployment on Docker, using Spark.
Semi-Supervised Learning with Pseudo-Labeling
In this project we will build multiple CNN models for CIFAR-10 Image Classification
This repository is used for "Computer Vision and Pattern Recognition" course work.
This project implements and tests Convolutional Neural Network (CNN) models to classify images from the CIFAR-10 dataset, which includes 60,000 color images across 10 classes. The models achieve up to 90.45% accuracy, with training stability considerations and evaluation through confusion matrices and training history.
Add a description, image, and links to the cifar-10-dataset topic page so that developers can more easily learn about it.
To associate your repository with the cifar-10-dataset topic, visit your repo's landing page and select "manage topics."