ml-deployment

Management Dashboard for Torchserve

An end-to-end Machine Learning project from writing a Jupyter notebook to check the viability of the solution, to breaking down the same into modular code, creating a Flask web app integrated with a HTML template to make a website interface, and deploying on AWS and Azure.

Pushing Deep Learning models into production using torchserve, kubernetes and react web app 😄

CUDA matrix multiplication benchmarking on Jetson Orin Nano. Four implementations, three power modes, five matrix sizes. 99.5% mathematical validation. C++/CUDA and Python.

Serving large ml models independently and asynchronously via message queue and kv-storage for communication with other services [EXPERIMENT]

Deployment of 3D-Detection and Tracking pipeline in simulation based on rosbags and real-time.

An implementation of seminal CVPR 2016 paper: "A Hierarchical Deep Temporal Model for Group Activity Recognition."

A EKS-based ML deployment solution

An ECS-based ML deployment solution

Base classes and utilities that are useful for deploying ML models.

A complete FastAPI learning repository — from basic CRUD operations to advanced ML model deployment with Docker.

Flask + scikit-learn app that predicts hypertension stage from patient data, with a full Docker/CI-CD pipeline to Render.

Machine Learning sentiment analysis model deployed with FastAPI and Docker

This Flask web application performs text sentiment analysis and text generation based on user input. Users can input text, and the application will analyze its sentiment using NLTK's Vader sentiment analysis tool and generate additional text using the GPT-2 model.

A basic example of deploying machine learning applications

ML classification system for pulsar detection from radio telescope data (HTRU2 dataset). FastAPI + Docker deployment.

API REST de Machine Learning para a ONG Turma do Bem — classifica solicitações de atendimento em prioridade ALTA/MÉDIA/BAIXA. Flask + scikit-learn, deployado no Render.

🌐 Language identification for Scandinavian languages

ml-deploy-lite is a Python library designed to simplify the deployment of machine learning models. It allows developers to quickly turn their models into REST APIs or gRPC services with minimal configuration. The library integrates seamlessly with Docker and Kubernetes, providing built-in monitoring and logging for performance and error tracking.

The ASIE is a production-grade MLOps platform designed to solve the "Static Model" problem in ML. A Level 2 MLOps Maturity architecture—a self-healing, closed-loop system that monitors for statistical data drift, triggers automated retraining on GPU-accelerated cloud infrastructure, and redeploys optimized models without manual intervention.