This model helps us classify 10 different real-life objects by undergoing training under tensorflow's CIFAR dataset which contains 60,000 32x32 color images with 6000 images of each class. I have made use of a stack of Conv2D and MaxPooling2D layers followed by a few densely connected layers.

🐱 A deep learning model using CNN to classify between cat and dog images

This repository Investigates DCGAN using facedata. Serves as a personal cautionary tale when working with GANS.

Handwriting digit recognition using keras.Conv2D and MNIST database.

In this project, used TensorFlow to build a neural network to classify road signs based on an image of those signs.

This project is to apply Convolutional Neural Networks (CNN) to recognize dog breeds.

This project compares performance between CPU and GPU with CUDA operations. Two simples cases are used: matrix multiplication and 2d convolution.

AI-based system for detecting eye diseases using retinal fundus images. Compares Conv2D, ResNet50 & VGG19 with standard and tuned hyperparameters. Trained on ODIR-5K and evaluated using classification metrics.

Image classifier application to classify flowers to 102 categories, using TnensorFlow hub and Conv2D

This project focuses on detecting driver behavior from images using Convolutional Neural Networks (CNNs). The dataset consists of images categorized into five classes: other_activities, safe_driving, talking_phone, texting_phone, and turning.

Tracking Geographic Coordinates

Manual implementation and parallel acceleration of the Conv2D forward pass using OpenMP, CUDA, and a Hybrid CPU-GPU approach for High Performance Computing (HPC).

Computer Vision Model for Age Estimation from Facial Images

A Simple Trained LeNET Model for handwritten digit recognition

CIFAR10 Dataset.

Implementation of winograd conv2d on Hygon DCU