Skip to content
View poeticmage's full-sized avatar
🎯
Focusing
🎯
Focusing
28 followers · 45 following

Highlights

  • Pro

Block or report poeticmage

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
poeticmage/README.md

Priyadarshi (poetic mage)

I am Priyadarshi, an engineer who works with Machine Learning and other AI Tools. I have had experience in building many AI algorithms, some of them from scratch, in order to solve real world problem. From Linear Regression, Regularization and Logistic to Trees, Ensemble, Neural Network, Transformers; all these algorithms I have used to build complex machines like MaxVit or Zero-Shot pipelines. I am interested in Computer Vision, Natural Language Processing and Automation with Agentic AI.

Resume

Contact

Mail: mookherjipriyadarshi@gmail.com

Linkedin: www.linkedin.com/in/priyadarshi-codes

Projects

Refer Eye Glaucoma: This is an end to end ML project for detecting whether a case of Glaucoma is severe enough for referal to hospital or it can be checked in private clinic. This app takes Fundus Images (a kind of medical image for eyes cross-section) as input and gives a GradCAM heatmap along with predicted category as output. The GRADCAM tells which parts the MaxViT focused most on. There is also a DBSCAN based gating algorithm to flilter out non medical input. See this for the full app https://funduseyefrontend12.onrender.com/ and the Git Link is this: https://github.com/poeticmage/image (backend) and https://github.com/poeticmage/FundusEyeFrontend (frontend). In the image repository, the full AI algorithms are written in the README file, though they are deployed in Hugging Face Spaces

Pinned Loading

  1. FundusEyeFrontend FundusEyeFrontend Public

    This is the frontend for the Refer Eye Glaucoma app. myreactapp was used to create it. The backend will be found in image repo. It is deployed in render (ci/cd)

    JavaScript 1

  2. image image Public

    This is the backend for Refer Eye Glaucoma app. It handles image for fundus-images, sending them to 2 other apis deployed in Hugging Face spaces.

    JavaScript 1

  3. Notebook-data-pipeline Notebook-data-pipeline Public

    This repository contains jupyter notebooks of data preprocessing of various datasets before being fed to the model. Proper train,test split, class handling and train test loaders are written in cod…

    Jupyter Notebook 1