Deepankar Varma's repositories
Age-and-Gender-Detection-OpenCV--Keras--TensorFlow
This repository contains Python code for an age and gender detection project using the video stream from the camera. The model is trained on the UTKFace dataset and utilizes deep learning techniques for accurate age and gender estimation. The code includes scripts for data preprocessing, model training, and real-time detection from the camera.
Yawn-Detection-OpenCV-Keras-TensorFlow-Sklearn
This repository contains Python code for generating a yawning detection model and using it to detect yawning instances from a live camera stream. The model architecture consists of convolutional and pooling layers, followed by fully connected layers.
American-Sign-Language-MultiClass-Image-Classification-OpenCV-Keras-TensorFlow
This repository contains Python code for a project that performs American Sign Language (ASL) detection using multiclass classification. It utilizes YOLO (You Only Look Once) and MobileNetSSD_deploy for object detection, achieving an accuracy of 91%. The code offers options to predict signs from both images and videos.
Skin-Cancer-Detection--OpenCV-TensorFlow-Keras
This repository contains Python code for generating a skin cancer detection model and utilizing it to detect skin cancer from user-inputted images or videos. The model architecture follows a sequential structure consisting of convolutional and pooling layers, with the final output layer using a sigmoid activation function.
deepankarvarma
Config files for my GitHub profile.
Nework-Protocol-Analyser-Using-Python
This repository contains a network analyzer and speed test application built using Python and Streamlit. The application provides two main functionalities: packet capture for network analysis and speed testing to measure the download and upload speeds of your network connection.
Weather-Application-Using-Python
This repository contains a Python-based Weather Application that utilizes the OpenWeatherMap API to analyze and display weather conditions for a specified location. The application retrieves current weather data and provides a 24-hour forecast in both tabular and graphical formats.
Background-Remover-Using-Python
This repository contains a Python application built with Streamlit that allows users to remove the background from uploaded images. It utilizes computer vision techniques and the rembg library to automatically remove backgrounds, providing users with a seamless and efficient solution.
Basic-Calculator-Using-Python
This repository contains a basic calculator implementation using Python and hosted on Streamlit. It provides a simple user interface to perform arithmetic calculations.
College_Saathi_Driver
Empowering drivers to efficiently manage e-rickshaw ride requests, the College Saathi Driver App is a cross-platform Flutter application. Boasting a dynamic UI, dual themes, Firebase for authentication and real-time communication, and ongoing payment integration, it provides a streamlined platform for drivers.
College_Saathi_Rider
Revolutionizing campus travel, the College Saathi Rider App is a cross-platform Flutter application for seamless e-rickshaw booking. With a dynamic UI, dual themes, Firebase for authentication and real-time communication, and ongoing payment integration, it elevates the campus commuting experience.
Decentralized-Voting-Application-using-Blockchain
This repository hosts a basic implementation of a decentralized voting application using blockchain technology. The application has been developed using Python and leverages the hashlib library for hashing operations and utilizes the system time for generating timestamps.
Downstreaming-CIFAR-10-Using-Pretrained-ViT-Custom-Architecture
This repository showcases a comprehensive implementation for downstreaming CIFAR-10 dataset utilizing a pretrained Vision Transformer (ViT) model along with a tailored custom architecture. Leveraging the power of ViT, which has shown remarkable performance in various computer vision tasks, this project fine-tunes the pretrained model on cifar-10.
Face-Mask-Type-Multiclass-Image-Classificiation--OpenCV-TensorFlow-Keras
This repository contains Python code for a face mask type detection project using multiclass classification. The project focuses on classifying different types of face masks, including cloth face masks, N95 face masks, N95 face masks with valves, surgical face masks, and images without any face masks.
Fire-Detection--OpenCV-Keras-TensorFlow
This repository contains Python code for generating a fire detection model and utilizing it to detect fire from user-uploaded images. The model architecture consists of convolutional and pooling layers, followed by fully connected layers. The repository includes scripts for training the model and predicting fire from uploaded images.
Full-Stack-Web-Development2023
From crafting dynamic front-end interfaces using HTML, TWCSS (Tailwind CSS), and JavaScript, to building robust back-end functionalities with Django and managing data in PostgreSQL, this repository encapsulates my growth as a full stack developer.
Mobile-Phone-Price-Prediction-Using-Regression
This repository contains code for predicting the price of mobile phones using regression models. It includes the implementation of various regression techniques such as Random Forest Regression, Decision Tree Regressor, Linear Regression, and Lasso Regression.
Monkeypox-Skin-Lesion-Detection-OpenCV-TensorFlow-Keras
This repository contains code and dataset for a multiclass image classification model to detect monkeypox using the ResNet50 architecture. The project focuses on classifying skin lesion images into different categories related to monkeypox, achieving 100% accuracy.
Pneumothorax-Binary-Classification--OpenCV--Keras--Tensorflow
This repository contains code for a binary image classification model to detect pneumothorax using the ResNet-50 V2 architecture. It includes essential steps such as dataset splitting, image augmentation, model training, and a Streamlit application for user image upload and prediction.
Rice-MultiClass-Image-Classification-OpenCV-Keras-Tensorflow
This repository contains Python code for rice type detection using multiclass classification. The project leverages the MobileNetV2 architecture to classify six different types of rice: Arborio, Basmati, Ipsala, Jasmine, and Karacadag. The dataset used for training and evaluation can be found on Kaggle and consists of categorized rice images.
SimCLR
A PyTorch implementation of SimCLR based on ICML 2020 paper "A Simple Framework for Contrastive Learning of Visual Representations"
simclr-google-research
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
SimCLR_Modified
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.
SimCLRV2-Tensorflow-Checkpoints-Conversion-To-Pytorch
Code for conversion of google research SimCLR V2 Tensorflow checkpoints to Pytorch ones. SimCLRV2 Repo:- https://github.com/google-research/simclr
Stock-Tracker-Using-Python
This repository contains code for a simple stock tracker web application built with Python and Streamlit. It uses the yfinance library to fetch stock data and visualizes it using line charts and tables. The application allows users to track the stock prices of different companies by entering the stock ticker symbol.
Sudoku-Solver-Using-Python
This repository contains a Sudoku solver implemented in Python. The solver utilizes a backtracking algorithm to find the solution for a given Sudoku puzzle. The solution is hosted using Streamlit, providing a user-friendly interface for inputting and solving Sudoku puzzles.
To-Do-List-Using-Python
This repository contains code for a simple To-Do List application built using Python and Streamlit. The application allows users to manage their tasks by adding new tasks, marking tasks as completed, and clearing the task list. Tasks are stored in a CSV file for persistence.