Soumyajit Datta's Projects
Digital garden and photography portfolio built using NextJS, Typescript, MDX, Contentful, Stitches, and Radix.
We are building an interface that helps users with a situation by the use of an AI that asks questions on the basis of a code which the aspirant has written, asked from a diverse pack of frequently asked coding questions. Then the AI asks the aspirant questions related to his code and some staple questions. At the end of this experience, the user receives his interview profile showing him his flaws in answering questions, his fluency, and his ability to handle the situation verbally. This can be done on various levels and be stored for future scrutiny by the user. We can also provide a growth curve that helps the aspirant to judge his progress.
JavaScript animation engine
Just another random portfolio on the internet. Built using NextJS with all engineering that we know :P
π Papers & tech blogs by companies sharing their work on data science & machine learning in production.
Classifying asteroids based on NASA JPL data records
Machine learning, statistics, and data mining for astronomy and astrophysics
π€ AutoTrain Advanced
Awesome-LLM: a curated list of Large Language Model
The lastest paper about detection of LLM-generated text and code
Brain Tumor Detection, Classification and Segementation. [ViT vs CNN, Mask RCNN]
Master programming by recreating your favorite technologies from scratch.
Minimalist ML framework for Rust
Captcha Recognizer trained with 6 different datasets using LACC
pre processing for OCR in license plates
A dataset consisting of 502 English dialogs with 12,000 annotated utterances between a user and an assistant discussing movie preferences in natural language. It was collected using a Wizard-of-Oz methodology between two paid crowd-workers, where one worker plays the role of an 'assistant', while the other plays the role of a 'user'. The 'assistant' elicits the 'userβs' preferences about movies following a Coached Conversational Preference Elicitation (CCPE) method. The assistant asks questions designed to minimize the bias in the terminology the 'user' employs to convey his or her preferences as much as possible, and to obtain these preferences in natural language. Each dialog is annotated with entity mentions, preferences expressed about entities, descriptions of entities provided, and other statements of entities.
A simple 3-layer NN based model with predefined responses
A light-weight,secure,end-to-end encrypted chatting app.
Advanced Chess Clock For Profession Players
The official GitHub mirror of the Chromium source
Contains various CNN Projects like mnist, cifar-10, YOLO along with cats and dog classifier with custom images
Semantic Segmentation of colon polyps implemented by U-Nets on CVCclinic database. A Flask API and a GUI app to do real-time detection
The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
A computer vision project that can solve a real life problem.