Gokuleshwaran Narayanan's repositories
Contribution-bot
This repository provides a detailed, step-by-step guide to setting up the GitHub Contribution bot. You’ll learn how to script in JavaScript and integrate with Windows Task Scheduler to automate your commits and maintain your GitHub streak.
Titanic-Survival-Prediction
This web app is a simple Titanic Survival Prediction web app. The web app uses a logistic regression model to predict whether the mail is spam or not.
Iris-Detection
This project focuses on iris detection using deep learning techniques. The model architecture combines the power of ResNet152V2, a pre-trained convolutional neural network (CNN), with additional convolutional layers to accurately detect and localize iris regions in images.
Fashion-MNIST-GAN
This script outlines the implementation of a Generative Adversarial Network (GAN) designed to generate fashion images using the Fashion MNIST dataset. The GAN consists of a generator and a discriminator, which are trained simultaneously in an adversarial manner.
Toxic-Comment-Classifier
This project employs a deep neural network architecture for the classification of toxic comments, utilizing the Kaggle competition dataset from the Jigsaw Toxic Comment Classification Challenge.
AI-Virtual-Mouse
This project leverages OpenCV for hand tracking and gesture recognition and AutoPy for mouse control to create a real-time hand gesture mouse control application. Users can control the mouse cursor's movement and perform mouse clicks using hand gestures detected by the camera.
AI-Virtual-Painter
This project utilizes OpenCV and MediaPipe's hand tracking capabilities to create a real-time hand gesture drawing application. The user can draw on the screen by moving their index finger, and erase the drawing by raising their index and middle fingers simultaneously.
AI-Personal-Trainer
This project utilizes MediaPipe, OpenCV, and a pose estimation module to create a real-time fitness tracker focusing on counting dumbbell curls. The user stands in front of a camera, and the program calculates the angle between the shoulder, elbow, and wrist to determine the movement direction and count the number of curls performed.
Finger-Counter
This Python script utilizes the OpenCV library to perform real-time hand gesture recognition using a webcam. It employs a pre-trained hand detection model from the HandTrackingModule to detect and track landmarks on the hand.
Hand-Gesture-Volume-Control
This project demonstrates real-time hand gesture-based volume control using a webcam feed. Leveraging the HandTrackingModule, MediaPipe, and OpenCV, the program tracks hand movements and recognizes gestures to adjust system volume.
Face-Mesh-Detection-Mediapipe
This project utilizes MediaPipe and OpenCV to perform real-time face mesh detection using a webcam feed. The program captures video frames and processes them using the MediaPipe Face Mesh module to detect facial landmarks and contours.
Face-Detection-Mediapipe
This project employs the MediaPipe library and OpenCV for real-time face detection. Leveraging a webcam feed, it accurately identifies and annotates faces within the frame.
Pose-Estimation
This project utilizes MediaPipe and OpenCV for real-time pose detection. By processing webcam input, it accurately identifies and annotates key points on the human body.
Hand-Tracking
This project showcases real-time hand tracking using MediaPipe and OpenCV. Leveraging computer vision, it accurately detects and annotates hand landmarks from webcam footage, offering insights into hand poses and gestures.
Face-Detection
This project uses OpenCV and deep learning to detect faces in images and videos.
Happy-Sad-Classification
This model is trained on google images of happy and sad faces, and is able to classify new images as happy or sad.
LLM-chatbot
This repository is for building a streamlit app for Gemini-Pro LLM chatbot.
Plant-Disease-Prediction
This is a web app for predicting plant diseases using Convolutional Neural Networks (CNN). The model is trained on the PlantVillage dataset which contains images of healthy and diseased plant leaves. The dataset consists of 38 classes of plant diseases. The model is built using TensorFlow and Keras and trained on Google Colab.
Fashion-MNIST-Image-Classification
The web app uses a Convolutional Neural Network (CNN) model trained on the Fashion MNIST dataset to classify images of clothing.
Face-Mask-Detection-CNN
This web app is created to demonstrate the face mask detection model using Convolutional Neural Networks (CNN). The model is trained on a dataset containing images of people with and without masks. The model is built using TensorFlow and Keras libraries in Python.
Object-Recognition-ResNet50
This is a web app to predict the object in an image using the ResNet50 model. The ResNet50 model is a pre-trained model on the ImageNet dataset. The model is trained to classify 10 different objects.
Dog-vs-Cat-Classification
This web app is a simple image classification app that uses a pre-trained model to classify images of dogs and cats. The model is trained using the MobileNet V2 architecture with ImageNet pre-trained weights. This is a SavedModel in TensorFlow 2 format. Using it requires TensorFlow 2 (or 1.15) and TensorFlow Hub 0.5.0 or newer.
Handwritten-Digit-Classification
This web app is a simple handwritten digit classification model built using a neural network with the MNIST dataset. The MNIST dataset is a collection of 70,000 small square 28x28 pixel grayscale images of handwritten single digits between 0 and 9. The model is built using TensorFlow and Keras, and the web app is built using Streamlit.
Breast-Cancer-Classification-DL
This Deep Learning model utilizes Neural Networks to detect the presence of breast cancer. The dataset is imported from sklearn.datasets, containing 30 columns and 569 entries.
Wine-Quality-Prediction
This web app is created to predict the quality of red wine based on the input features. The model is trained using the Random Forest Classifier algorithm.
Breast-Cancer-Classification
This web app is created to classify the Breast Cancer into Benign and Malignant. The model is built using the Logistic Regression algorithm.