Deepankar Varma's Projects
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.
This repository contains the source code for a simple News Aggregator web application built using the NewsAPI and Streamlit. The app allows users to filter news by country and category and displays the top headlines from various sources in one place.
This repository contains code for parameter optimization of Support Vector Machines (SVM) using the Dry Bean Dataset. The code is implemented in Python using scikit-learn library. The goal of this project is to find the best parameters for the SVM model in order to achieve the highest accuracy possible for the Dry Bean Dataset.
This repository contains a password generator app built with Python and Streamlit. The app allows users to generate a random password based on their preferences for length, including uppercase letters, numbers, and symbols.
This is a simple photo collage maker app built using Streamlit and PIL library in Python. With this app, you can upload your own images and create a photo collage by selecting the number of rows and columns.
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.
This repository includes a simple and interactive Streamlit app that allows users to customize the timer length for Pomodoro sessions, short breaks, and long breaks. Users can also upload their favorite music files in mp3 format to play in the background during the Pomodoro session.
An Amazing Questions Setter Website (mainly for teachers) made using Chat GPT-3
This repository contains code for a minimalistic quote generator website that displays a new quote every 5 seconds. The quotes are fetched from the quotable API and displayed on a clean background image. The website is built using Streamlit, a Python web framework for data science and machine learning applications.
This is a Chrome extension that generates random quotes using the quotable API. The extension fetches a random quote and displays it in a popup, along with a countdown to the next quote. Users can customize the behavior of the extension by modifying the code in the popup.js file.
This repository contains the code for a rating review classification project that was submitted for the Kaggle Wars competition hosted by ACM Thapar. The project aims to classify reviews based on their rating, using data pre-processing and a convolutional neural network (CNN) model.
This repository contains code for a recipe finder web application that allows users to search for recipes based on the ingredients they have and their dietary restrictions. The application makes an API call to the Spoonacular API to retrieve recipe information and displays the results in a tabular format.
This repository implements regression models to predict the quality of Red Wine based on user-inputted parameters. It includes code for exploratory data analysis, outlier analysis, and the application of Random Forest, Linear Regression, and Ridge Regression models.
Lecture video links for preparation of Placements
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.
A PyTorch implementation of SimCLR based on ICML 2020 paper "A Simple Framework for Contrastive Learning of Visual Representations"
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.
Code for conversion of google research SimCLR V2 Tensorflow checkpoints to Pytorch ones. SimCLRV2 Repo:- https://github.com/google-research/simclr
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.
This repository contains the code for building a spam detection system for SMS messages using deep learning techniques in TensorFlow2. Three different architectures, namely Dense Network, LSTM, and Bi-LSTM, have been used to build the spam detection model. The final model has been deployed as a Streamlit app to showcase its working.
This repository contains the source code for a Spend Analyser app built with Python using the Streamlit library. The app allows users to input their spending data, which is then stored in a CSV file. The app then reads the CSV file and displays the spending data as a table and a chart.