Shashank Sahoo's Projects
AI Toolkit for Azure IoT Edge
Javascript(Node.js) application for tracking flights
Sample Demo for algorithmia model deploy pipeline
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
All the project works incorporating the use of AWS goes here. It will be helpful for those who wish to explore my work in AWS domain all at one place.
Estimote SDK for Android
Using the matplotlib library to create some interesting animations.
Approaching (Almost) Any Machine Learning Problem
LoraWAN-in-C library, adapted to run under the Arduino environment
A curated list of awesome Deep Learning tutorials, projects and communities.
A topic-centric list of HQ open datasets. PR ☛☛☛
A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
Official community-driven Azure Machine Learning examples, tested with GitHub Actions.
TensorFlow code and pre-trained models for BERT
A Node.js module for implementing BLE (Bluetooth Low Energy) peripherals
Building a Simple Chatbot from Scratch in Python (using NLTK)
Autonomous driving - car detection using the very powerful YOLO model
This classifier use Convolution Neural Network approch for kaggle problem to classify Cat vs Dog images.
This is a web service built using FastAPI and OpenAI's GPT-3.5-Turbo model that enables translation of various types of documents. The service currently supports translation of PDF, Word, CSV, TXT, and PPTX files.
Cognitive Services Face client library for Android.
Python SDK for the Microsoft Face API, part of Cognitive Services
A library with sample apps for continuous analysis of live video, using the Microsoft Cognitive Services Vision APIs.
Android SDK for Microsoft Speaker Recognition API, part of Cognitive Services
Python SDK for the Microsoft Speaker Recognition API, part of Cognitive Services
An iOS app written in Swift 4 that demonstrates Microsoft Cognitive Services Speaker Recognition API
This repo compares three state-of-the-art text generating NLP models viz., GPT-Neo, GPT-2 and XLNet on a common downstream application to fit in vaccine domain tweets corpus.
OpenCV library based various project implementation to solve some classical camera image based problems. It contains simple to complex variations of feature development with Open CV.
A baseline system for ContractNLI (https://stanfordnlp.github.io/contract-nli/)
All solved Coursera assignments for my profile visitors.
This repo describes a Pytorch based approach to identify and classify various document layout components like title, caption, section, header, question, answer and other in a given scanned image version of PDF documents.