Image Classification of 4 Categories of Corn Diseases Using CNN in TensorFlow and Keras, with the model deployed via a Flask API. The model accuracy is 95%.

Final project for Signal Processing course that focuses on Parkinson's Disease detection.

Image Caption Generator - Deep Learning

Demo showcasing Federated Learning with Flower for yoga pose classification, enabling collaborative training across distributed datasets while preserving data privacy.

NutrientDeficency & Disease Detection Web Application : Created a web app using Streamlit for image uploading,provided options to detect diseases or nutrient deficiencies from the uploaded images.

proposing an approach to detect fake news of COVID-19 in social media while using natural language processing and machine learning techniques.

Image Classification with CNNs with keras on CIFAR-10 Dataset

This study was conducted in collaboration with the University of Prishtina (Kosovo) and the University of Oslo (Norway). This implementation is part of the paper entitled "Attack Analysis of Face Recognition Authentication Systems Using Fast Gradient Sign Method", published in the International Journal of Applied Artificial Intelligence by Taylo…

Config files for my GitHub profile.

본 시스템은 Yolo v3를 이용하여 Object Detection할 수 있는 프로그램입니다. 이미지, 동영상, WebCam모드를 지원합니다.

A deep learning model to generate captions for images. Flickr 8K dataset is used for training of this model. This project uses a CNN model for feature extraction. These features are converted to image captions by RNN.

Face Recognition using number of different approaches.

NLP with LSTM for Sentiment Analysis of Ukrainian texts

Classify images as cats 🐱 or dogs 🐶

Transformed raw text data into images with the help of Stanford developed GloVe word embeddings. Used with a custom designed ConvNet, in 1D.

Classification CNN models

A face recognition system, built with Keras

CNN network implemented using the Pytorch Framework from the scratch for classifying the Fashion - MNIST data set, activation layer of RELU is used for the nolinearity and cross entropy for the final backward error propagation, for better visualisation Tensorboard is also incorporated which helped in fine tuning of the hyper params