intel-image-classification

This repository contains some deep learning architecture for intel image classification dataset.

A novel architecture for enhancing image classification. Reference paper: https://arxiv.org/abs/2104.12294

My extensive work on Multiclass Image classification based on Intel image classification dataset from Kaggle and Implemented using Pytorch 🔦

This Data contains around 25k images of size 150-150 distributed under 6 categories This data was initially published on Intel to host an Image classification Challenge.

Image classifier for 6 scene classes (buildings, forest, glacier, mountain, sea, street) built with PyTorch transfer learning. Fine-tunes a pretrained ResNet-18 on the Intel Image Classification dataset with data augmentation, reaching 89.6% test accuracy. Includes a predict script and Gradio web demo.

Building a classifier on intel image dataset using transfer learning techniques and ResNet model

90% accuracy resnet-like CNN from scratch for Intel Image Classification dataset WITHOUT transfer learning and with complex metrics.

This project aims to classify images from the Intel Image Classification dataset using two renowned deep learning models: AlexNet and ResNet18. The notebook alex-res-net-classification.ipynb encompasses the entire workflow, including data preprocessing, model training, evaluation, and inference.

A CNN Image Classifier Example/Exercise

A Comparative Study of the performance of CNN from scratch compared to a transfer learning approach (InceptionV3)

Multi-class image classification model trained on the Intel Image Classification dataset using CNN architectures. The project focuses on building, training, and evaluating a deep learning model for scene classification.

TensorFlow implementation of twelve CNN architectures for natural scene image classification

ResNet50 transfer learning for 6-class scene classification on Intel Image dataset — 92.5% test accuracy

The notebook contents implementation of image classification using different CNN models: self-written & pretrained, using data Intel Image Classification.

A comprehensive deep learning project for classifying natural scene images into 6 categories using Custom CNN and Transfer Learning (EfficientNet).