This repository presents an approach as part of my final year project for automatic traffic sign recognition using Convolutional Neural Network

Handwriting Recognition with Deep Convolutional Neural Network (DCNN)

Build a model using CNN algorithm for classification of the abnormal images

recognize mouse-written numbers using KNN, Neural Network, and Convolutional Neural Network models

A Deep Learning Model to classify CIFAR-10 dataset using 1.) Convolutional Neural Network 2.) Transfer Learning using ResNet-18 in PyTorch.

CNN for image classification of the CIFAR10 dataset

OCR from scratch using Chars74 Dataset: http://www.ee.surrey.ac.uk/CVSSP/demos/chars74k/ applied to the case of Spanish car license plates or any other with format NNNNAAA. The hit rate is lower than that achieved by pytesseract: in a test with 21 images, 12 hits are reached while with pytesseract the hits are 17.

A PyTorch image classifier implemented as convolutional neural network

Begginer project usin a convolutional neuronal network to clasificate a set of hand-written characters.

Introduction to Convolutional Neural Network (CNN) and investigating the effects of its parameters on how the network works

Automated Facial Expression Recognition using Artificial Neural Networks is a machine learning project that uses convolutional neural networks (CNNs) to classify facial expressions in images into various categories such as anger, fear, surprise, sadness, happiness, and neutral.

The goal of this project is to design and train deep convolutional neural networks using PyTorch. I will design a deep net architecture to classify (small) images into 100 categories and evaluate the performance of the architecture by uploading the predictions to the Kaggle competition.

Web application to diagnosis illnesses on the leaves of diverse plants

Pytorch basic tutorial for CNN

Implemented deep learning model comparative study between 2 different architecture of CNN to identify the disease in potato crop after analyzing the images of leaves. have performed and compare which of architecture outperform with respect to accuracy parameter In the context of plant disease prediction,.

Python GUI for handwriting recognition CNN with 80% accuracy trained on the EMNIST dataset with detailed documentation included.

Face detection based on Haar cascade classifier + face classification using a convolutional neural network

Train CNN models with PyTorch