There are 2 repositories under cifar10-classification topic.
PyTorch-1.0 implementation for the adversarial training on MNIST/CIFAR-10 and visualization on robustness classifier.
Implementation of Conv-based and Vit-based networks designed for CIFAR.
AI Nexus 🌟 is a streamlined suite of AI-powered apps built with Streamlit. It features 👗 StyleScan for fashion classification, 🩺 GlycoTrack for diabetes prediction, 🔢 DigitSense for digit recognition, 🌸 IrisWise for iris species identification, 🎯 ObjexVision for object recognition, and 🎓 GradeCast for GPA prediction with detailed insights.
Designed a smaller architecture implemented from the paper Deep Residual Learning for Image Recognition and achieved 93.65% accuracy.
The aim of this project is to train autoencoder, and use the trained weights as initialization to improve classification accuracy with cifar10 dataset.
Contains my project code for two CNN models, one trained for binary classification while the other made for multi-class classification. It utillises the CIFAR-10 dataset.
Cifar classification model using Pytorch CNN module with ResNet9 model, with CUDA for training to archive 75% accuracy
A step-by-step implementation of a ResNet-18 model for image classification on the CIFAR-10 dataset
contains exercise solution
A deep learning framework that implements Early Exit strategies in Convolutional Neural Networks (CNNs) using Deep Q-Learning (DQN). This project enhances computational efficiency by dynamically determining the optimal exit point in a neural network for image classification tasks on CIFAR-10.
ConvMixer - Patches Are All You Need?
使用了 https://github.com/SaeedShurrab/SimSiam-pytorch 作为Simsiam backbone,添加了中文注释和简单的训练过程
DigiPic-Classifier is a powerful image classification app built with Streamlit. It features two models: CIFAR-10 Object Recognition to classify objects like airplanes, cars, animals, and more, and MNIST Digit Classification for recognizing handwritten digits. With a sleek interface and real-time predictions, DigiPic-Classifier offers a seamless
Classification of CIFAR dataset with CNN which has %91 accuracy and deployment of the model with FLASK.
This repository contains an implementation of the Vision Transformer (ViT) from scratch using PyTorch. The model is applied to the CIFAR-10 dataset for image classification.
Implemeting SVM to classify images with hinge loss and the softmax loss.
Implemented the Deep Residual Learning for Image Recognition Paper and achieved better accuracy by customizing different parts of the architecture.
The cifar10 classification project completed by tensorflow, including complete training, prediction, visualization, independent of each module of the project, and convenient expansion.
Implementing a neural network classifier for cifar-10
Deep Learning Projects
the CIFAR10 dataset
Classifies the cifar-10 database by using a vgg16 network. Training, predicting and showing learned filters are included.
Implemented Deep Residual Learning for Image Recognition Paper and achieved lower error rate by customizing different parts of the architecture.
Создание и обучение сверточной нейронной сети (CNN) для классификации изображений из набора данных CIFAR-10 с аугментацией и предотвращением переобучения
This repository contains all the work I have done during the course Deep Learning with PyTorch : Zero to GANs under Jovian.ai.
CapsNet models
Vitis AI tutorial for MNIST and CIFAR10 classification
Categorizes 10 different classes from CIFAR-10 dataset
The model design incorporates a compact architecture utilizing depthwise separable convolutions to minimize parameters and FLOPs, inverted residual blocks (inspired by MobileNetV2) to balance depth and width efficiently, and channel reduction techniques.But the model has not reached target of 95% accuracy,I invite other hackers to try. hack
Image classification on the CIFAR-10 dataset using Convolutional Neural Networks (CNNs). The project covers model building, training, evaluation, and visualization using TensorFlow/Keras. Key techniques include normalization, softmax classification, and EarlyStopping regularization.
Implemented Cifar-10 without using any pre-trained model with an accuracy of 75%.
This project uses TensorFlow to classify images from the CIFAR-10 dataset. It compares the performance of an Artificial Neural Network (ANN) and a Convolutional Neural Network (CNN), covering data preprocessing, model training, evaluation, and prediction on new images.