Akshat Surolia's Projects
Sensing Depth from 2D Images and Inpainting Background behind the Foreground objects to create 3D Photos with Parallax Animation.
AceTech is a chat bot used as web extension to serve tech and programming queries with concise answers up to 100 words and video/articles cards. It is implemented in Python and Dialogflow with real time web scraping and applying NLP techniques for query based extractive summarization, deployed in Heroku using Flask API.
This is my profile ReadMe
Classifying Music Genre with Urban Sound Dataset, Preprocessing with Librosa and Torch audio, Model made in Tensorflow and PyTorch
This repository includes API to get ICD-10 codes from descriptions. The Model is a transformer based on BERT. The embeddings are being finetuned based on the following paper: https://arxiv.org/abs/1904.03323 .
PIRDS - Prescription Image Recognition and Digitalizing System is a OCR make with Tensorflow that digitalises images of Prescription of Handwritten Texts by Doctors.
Diverse Facial Edit with StyleGAN, StyleGAN2, StyleClip with ViT, and Other Features like Background Removal and Face Swap
Educational Android App for Kids with various fun activities
Face Mask Detection API powered by FastAPI, RetinaFace Detector and Res10.
This repository holds the downstream task of Face Mask Classification performed on Self Currated Custom Dataset with various State of the Art deep learning models like ViT, BeIT, DeIT, LeViT, ConvNeXt, VGG16, EfficientNetV2, RegNet and MobileNetV3.
Image Enhancement, Contrast, Illumination, Saturation Adjustment and Noise Reduction and Upscaling with GANs.
Instagram Analytics to check followers/ Unfollowers, Download Media etc.
Maze Runner is based on Travelling Salesman Problem, to minimize the travelling cost to find the best possible solution. The user input maze image of m x n dimension which is converted to a graph, extracting the nodes and making connections which is used to traverse the maze via different algorithms. So, the user can compare different algorithms to get the most efficient path, while generating nodes in a graph. The maze can be a source to find the shortest easy path, from the multiple path that leads to the solution.
Advance Calculator with gradient flowing GUI and Advance Notepad
This is an TensorFlow Implementation of Ooze - Handwritten Text Generator by Akshat Surolia, This is an Image to Image translation approach to generate realistic hand written sentences by taking text as an input.
Personalized voice assistant 'Alice' with Language classification, Speech Recognition, Machine Translation, Restoring Punctuation, Conversational and Speech Synthesis.
My Portfolio Backend made with FastAPI with custom validation by Pydantic Models, supported by frontend made with React, Deployed on Heroku.
Blog for my Portfolio made with Next JS, GraphQL and TailwindCSS
My Portfolio Frontend made with React designed with Material UI, supported by backend made with FastAPI, Deployed on Netlify.
This repository contains PyTorch implementation of various architectures and some helper functions for data augmentation, custom dataset building etc...
Real Time Call Transcription and Sentimental Analysis, Call Initiates with Twilio, Streams in MuLAW, Preprocessed and converted into .wav, Transcribed with Wav2Vec2.0 and Analysing sentiment with BERT.
Recommendation System based on Artist and Music Embeddings
This repository contains recommendation system for dating apps based on personality evaluation by automatic question generation and sentiment + zero shot classification and user embeddings based on swipe history, made with FastAPI, validated by Pydantic Models