Case studies, examples, and exercises for learning to deploy ML models using AWS SageMaker.

The projects I do in Machine Learning with PyTorch, keras, Tensorflow, scikit learn and Python.

MLOps workshop with Amazon SageMaker

Deploy FastAI Trained PyTorch Model in TorchServe and Host in Amazon SageMaker Inference Endpoint

This is a short example showing how to utilize Amazon SageMaker's real time endpoints with OpenAI's open source Whisper model for audio transcription.

Detect Defects in Products from their Images using Amazon SageMaker

End to end Machine Learning with Amazon SageMaker

Deploy Stable Diffusion Model on Amazon SageMaker Endpont

MLOps on AWS using Amazon SageMaker Pipelines

This workshop will familiarize you with some of the key steps towards building an end-to-end predictive maintenance system leveraging Amazon SageMaker, Amazon Polly and the AWS IoT suite.

My Projects Submission to Udacity's Deep Learning Nanodegree Program

Fast model deployment on AWS Sagemaker

Build end-to-end Machine Learning pipeline to predict accessibility of playgrounds in NYC

This project promulgates an automated end-to-end ML pipeline that trains a biLSTM network for sentiment analysis, experiment tracking, benchmarking by model testing and evaluation, model transitioning to production followed by deployment into cloud instance via CI/CD

In this repo, we show how to host two computer vision models trained using the TensorFlow framework under one SageMaker multi-model endpoint.

This is a solution that demonstrates how to train and deploy a pre-trained Huggingface model on AWS SageMaker and publish an AWS QuickSight Dashboard that visualizes the model performance over the validation dataset and Exploratory Data Analysis for the pre-processed training dataset.

Twin Neural Network Training with PyTorch and fast.ai and its Deployment with TorchServe on Amazon SageMaker

Deep Learning Udacity Nanodegree - SageMaker Deployment of a Sentiment Analysis model

This repo contains demo code for reInvent2021 session AIM408 Achieve high performance and cost-effective model deployment

This GitHub repository showcases the implementation of a comprehensive end-to-end MLOps pipeline using Amazon SageMaker pipelines to deploy and manage 100x machine learning models. The pipeline covers data pre-processing, model training/re-training, hyperparameter tuning, data quality check,model quality check, model registry, and model deployment.