Deploy ML Model in Production with FastAPI and Docker
Deploy ML Model with ViT, BERT and TinyBERT HuggingFace Transformers with Streamlit, FastAPI and Docker at AWS
Lo que serás capaz de hacer
Welcome to Production-Grade ML Model Deployment with FastAPI, AWS, Docker, and NGINX! Unlock the power of seamless ML model deployment with our comprehensive course, Production-Grade ML Model Deployment with FastAPI, AWS, Docker, and NGINX. This course is designed for data scientists, machine learning engineers, and cloud practitioners who are ready to take their models from development to production. You'll gain the skills needed to deploy, scale, and manage your machine learning models in real-world environments, ensuring they are robust, scalable, and secure. What You Will Learn: Streamline ML Operations with FastAPI: Master the art of serving machine learning models using FastAPI, one of the fastest-growing web frameworks. Learn to build robust RESTful APIs that facilitate quick and efficient model inference, ensuring your ML solutions are both accessible and scalable. Harness the Power of AWS for Scalable Deployments: Leverage AWS services like EC2, S3, ECR, and Fargate to deploy and manage your ML models in the cloud. Gain hands-on experience automating deployments with Boto3, integrating models with AWS infrastructure, and ensuring they are secure, reliable, and cost-efficient. Containerize Your Applications with Docker: Discover the flexibility of Docker to containerize your ML applications. Learn how to build, deploy, and manage Docker containers, ensuring your models run consistently across different environments, from development to production. Build and Deploy End-to-End ML Pipelines: Understand the intricacies of ML Ops by constructing end-to-end machine learning pipelines. Explore data management, model monitoring, A/B testing, and more, ensuring your models perform optimally at every stage of the lifecycle. Automate Deployments with Boto3: Automate the deployment of your ML models using Python and Boto3. From launching EC2 instances to managing S3 buckets, streamline cloud operations, making your deployments faster and more efficient. Scale ML Models with NGINX: Learn to use NGINX with Docker-Compose to scale your ML applications across multiple instances, ensuring high availability and performance in production. Deploy Serverless ML Models with AWS Fargate: Dive into serverless deployment using AWS Fargate, and learn how to package, deploy, and manage ML models with AWS ECR and ECS for scalable, serverless applications. Real-World ML Use Cases: Apply your knowledge to real-world scenarios by deploying models for sentiment analysis, disaster tweet classification, and human pose estimation. Using cutting-edge transformers and computer vision techniques, you’ll gain practical experience in bringing AI to life. Deploy Interactive ML Applications with Streamlit: Create and deploy interactive web applications using Streamlit. Integrate your FastAPI-powered models into user-friendly interfaces, making your ML solutions accessible to non-technical users. Monitor and Optimize Production ML Models: Implement load testing, monitoring, and performance optimization techniques to ensure your models remain reliable and efficient in production environments. Why This Course? In today’s fast-paced tech landscape, the ability to deploy machine learning models into production is a highly sought-after skill. This course combines the latest technologies—FastAPI, AWS, Docker, NGINX, and Streamlit—into one powerful learning journey. Whether you're looking to advance your career or enhance your skill set, this course provides everything you need to deploy, scale, and manage production-grade ML models with confidence. By the end of this course, you’ll have the expertise to deploy machine learning models that are not only effective but also scalable, secure, and ready for production in real-world environments. Join us and take the next step in your machine-learning journey!
- Deploy Machine Learning Models with FastAPI: Learn to build and deploy RESTful APIs for serving ML models efficiently.
- Master Cloud-Based ML Deployments with AWS: Gain hands-on experience deploying, managing, and scaling ML models on AWS EC2 and S3.
- Automate ML Operations with Boto3 and Python: Automate cloud tasks like instance creation, data storage, and security configuration using Boto3.
- Containerize ML Applications Using Docker: Build and manage Docker containers to ensure consistent and scalable ML deployments across environments.
- Streamline Model Inference with Real-Time APIs: Develop high-performance APIs that deliver fast and accurate predictions for production-grade applications.
- Optimize Machine Learning Pipelines for Production: Design and implement end-to-end ML pipelines, from data ingestion to model deployment, using best practices.
Temario
UNIDAD 1 - Introduction · 3 leccionesUNIDAD 1 - Introduction
UNIDAD 1 - Introduction
- Course Introduction
- Install Requirements.txt
- Resources [Code Files]
UNIDAD 2 - Introduction to ML Ops and Pipeline · 8 leccionesUNIDAD 2 - Introduction to ML Ops and Pipeline
UNIDAD 2 - Introduction to ML Ops and Pipeline
- What is Machine Learning Pipeline
- Type of ML Model Deployment
- ML Infrastructure and Integration Tools
- Benefits of ML Pipeline
- Challenges in ML Model Deployment
- Data and Model Management
- A/B Testing for ML Model
- ML Model Bias and Security
UNIDAD 3 - Introduction to AWS Services · 7 leccionesUNIDAD 3 - Introduction to AWS Services
UNIDAD 3 - Introduction to AWS Services
- Getting Started with AWS
- Exploring EC2 Dashboard
- AWS Cost Calculator
- Creating EC2 Windows Server Part 1
- Creating EC2 Windows Server Part 2
- Create EC2 Ubuntu Machine
- Create S3 Bucket
UNIDAD 4 - Managing AWS EC2 Servers with Boto3 · 11 leccionesUNIDAD 4 - Managing AWS EC2 Servers with Boto3
UNIDAD 4 - Managing AWS EC2 Servers with Boto3
- Introduction
- AWS Credentials Setup with AWS CLI for Boto3
- AWS Boto3 - SSH Key Pair Setup
- AWS Boto3 - Launch EC2 with Python Part 1
- AWS Boto3 - Launch EC2 with Python Part 2
- AWS Boto3 - Exploring Security Groups using AWS Console
- AWS Boto3 - Create Custom Security Group with Python
- AWS Boto3 - Configure Custom Security Group Using Python
- AWS Boto 3 - Attach and Detach Security Groups to EC2 with Python
- AWS Boto3 - Check EC2 Instance Status
- AWS Boto3 - Start, Stop and Terminate EC2 Instance with Python
UNIDAD 5 - Managing AWS S3 with Boto3 · 8 leccionesUNIDAD 5 - Managing AWS S3 with Boto3
UNIDAD 5 - Managing AWS S3 with Boto3
- Introduction
- AWS Boto3 - Create S3 Bucket with Python
- AWS Boto3 - Upload File to S3 with Python
- AWS Boto3 - List S3 Objects or Files in the Bucket
- AWS Boto3 - Download S3 File to Local System
- AWS Boto3 - Upload All Files in Dir to S3 using Python
- AWS Boto3 - Download Full S3 Dir to Local
- AWS Boto3 - Delete All Files in an S3 Bucket
UNIDAD 6 - Sentiment Classification using TinyBERT Transformer · 9 leccionesUNIDAD 6 - Sentiment Classification using TinyBERT Transformer
UNIDAD 6 - Sentiment Classification using TinyBERT Transformer
- Introduction
- Getting Started with Sentiment Classification
- Load Data with Hugging Face Datasets Library
- Data Tokenization
- Build Model Evaluation Function
- Model Building and Training
- Model Save and Load for Inference
- Push Model to AWS S3 Part 1
- Push Model to AWS S3 Part 2
UNIDAD 7 - Disaster Tweets Classification using TinyBERT Transformer · 8 leccionesUNIDAD 7 - Disaster Tweets Classification using TinyBERT Transformer
UNIDAD 7 - Disaster Tweets Classification using TinyBERT Transformer
- Introduction
- Getting Started with Disaster Tweets Classification
- Loading Disaster Tweets
- Load Data with Hugging Face Datasets Library
- Tweets Tokenization
- Model Building and Training
- Model Save and Load for Inference
- Push Model to AWS S3
UNIDAD 8 - Human Pose Image Classification using Vision Transformers (ViT) · 11 leccionesUNIDAD 8 - Human Pose Image Classification using Vision Transformers (ViT)
UNIDAD 8 - Human Pose Image Classification using Vision Transformers (ViT)
- Introduction
- Getting Started with Image Classification
- Human Pose Dataset Preparation
- Image Preprocessing Part 1
- Image Preprocessing Part 2
- ViT Model Building
- Vision Transformer (ViT) Fine Tuning
- Model Prediction on Test Dataset
- Classification Report and Confusion Matrix
- Human Pose Prediction on Real Images
- Push Model to AWS S3
UNIDAD 9 - Deploy ML Model at Streamlit Server · 12 leccionesUNIDAD 9 - Deploy ML Model at Streamlit Server
UNIDAD 9 - Deploy ML Model at Streamlit Server
- Introduction
- Streamlit Application Walkthrough
- Streamlit Basics Part 1
- Streamlit Basics Part 2
- Streamlit Basics Part 3
- Streamlit Basics Part 4
- Streamlit Basics Part 5
- Streamlit Basics Part 6
- Streamlit App with ML Model Part 1
- Streamlit App with ML Model Part 2
- Upload Streamlit App on GitHub for Pipeline
- Deploying ML App at Streamlit Server
UNIDAD 10 - ML Model Deployment with Streamlit at AWS EC2 Server · 14 leccionesUNIDAD 10 - ML Model Deployment with Streamlit at AWS EC2 Server
UNIDAD 10 - ML Model Deployment with Streamlit at AWS EC2 Server
- Introduction
- Automating AWS EC2 Instance Creation with Boto3
- Automating Security Group Configuration
- Automating Server Start and Stop
- Create Instance with Automated Script
- Terminate Instance
- Fasted and Shortest Way to Create Server During POC
- Connect with SSH to Your Server
- Connect VS Code with the Server
- Connect GitHub with the Server
- Run Streamlit on AWS Server
- Create S3 Full Access and Attach to EC2 Server
- Run Streamlit Application Automatically and Server Start Up
- Attach Permanent Fixed IP with EC2 Server
UNIDAD 11 - Building REST API with FastAPI · 15 leccionesUNIDAD 11 - Building REST API with FastAPI
UNIDAD 11 - Building REST API with FastAPI
- Introduction
- Introduction to ML Model Serving over REST API
- API Requests Type
- API Response Types
- How to Inspect Browser for API Requests and Response
- What is FastAPI?
- Build Your First FastAPI Application
- Working with GET Requests
- Working with POST Requests
- Exploring FastAPI Interactive API Docs
- Call GET API Through CURL and Python
- Call POST API Through CURL and Python
- Explore GET Requests with Postman
- Explore POST Requests with Postman
- Send POST Data as Data Payload
UNIDAD 12 - ML Model Serving over REST API for Production Deployment · 18 leccionesUNIDAD 12 - ML Model Serving over REST API for Production Deployment
UNIDAD 12 - ML Model Serving over REST API for Production Deployment
- Introduction
- Pydantic Data Class Introduction
- Building Data Classes for ML Models
- Running and Testing Your Application with Data Validation
- Building Sentiment, Disaster and Human Pose Classifier APIs
- Integrating S3 with API for CI-CD
- Load All ML Models
- Serving All ML Models Over the API
- Doing Data Validation and Modelling for Output
- Doing Data Validation and Modelling for Image Classifier
- API Load Testing
- Get Presigned Image URL from S3
- Serving ML Models Through API in Streamlit Application Part 1
- Serving ML Models Through API in Streamlit Application Part 2
- Serving ML Models Through API in Streamlit Application Part 3
- Deploying ML Model in Production with FastAPI Part 1
- Deploying ML Model in Production with FastAPI Part 2
- Deploying ML Model in Production with FastAPI Part 3
UNIDAD 13 - Introduction to Docker for ML Model Deployment · 11 leccionesUNIDAD 13 - Introduction to Docker for ML Model Deployment
UNIDAD 13 - Introduction to Docker for ML Model Deployment
- Introduction
- Docker Introduction Part 1
- Docker Introduction Part 2
- Docker Introduction Part 3
- Basic Docker Command
- Your First Dockerfile
- Inspect Docker Image
- Write Dockerfile for FastAPI
- Run FastAPI inside Docker
- Pushing Docker Image to Docker Hub
- Pulling Docker Image from Docker Hub
UNIDAD 14 - Scale ML Model with NGINX Server · 8 leccionesUNIDAD 14 - Scale ML Model with NGINX Server
UNIDAD 14 - Scale ML Model with NGINX Server
- Introduction
- Why to Use NGINX in Production
- Use Docker-Compose to Run Docker
- Scaling Your Application to N-Instances
- Scaling with NGINX Part 1
- Scaling with NGINX Part 2
- Design ML REST API Services with NGINX Server
- Run ML REST API with NGINX Server
UNIDAD 15 - Deploy ML Model in Production with Docker, FastAPI and NGINX on AWS EC2 · 7 leccionesUNIDAD 15 - Deploy ML Model in Production with Docker, FastAPI and NGINX on AWS EC2
UNIDAD 15 - Deploy ML Model in Production with Docker, FastAPI and NGINX on AWS EC2
- Introduction
- Package ML App as an Docker Image Part 1
- Package ML App as an Docker Image Part 2
- Package ML App as an Docker Image Part 3
- Run API Services Inside Docker at EC2 Part 1
- Run API Services Inside Docker at EC2 Part 2
- Load Testing of Model Deployed in the Production with Docker
UNIDAD 16 - Deploy Serverless ML Model in Production at AWS Fargate with AWS ECR and AWS ECS · 11 leccionesUNIDAD 16 - Deploy Serverless ML Model in Production at AWS Fargate with AWS ECR and AWS ECS
UNIDAD 16 - Deploy Serverless ML Model in Production at AWS Fargate with AWS ECR and AWS ECS
- Introduction
- Introduction to Deploy ML Model with AWS ECR ECS and Serverless Fargate
- [MUST WATCH] Minor Code Modification for AWS Serverless Deployment
- Building and Pushing Docker Image on AWS ECR
- How ECR, Task Definition, Service and Cluster Works Together
- How to Create Task Definition for ECS Service
- Launch ECS Service on Fargate for Serverless ML Model API
- ML Service is Launched at AWS Fargate
- Exploring AWS ECS Services
- Simulating Real-time Users to Do Load Testing on ML API
- Resource Cleanup. Thank You
Tu certificado lo emite la SEP, no solo una plataforma
Al demostrar la competencia recibes un certificado emitido por la Secretaría de Educación Pública a través del Gobierno del Estado de México: un documento oficial que puedes presentar con confianza ante cualquier empleador o institución.
Tu certificado con INEC
- Lo emite la Secretaría de Educación Pública (SEP), a través del Gobierno del Estado de México
- Documento oficial con folio verificable en línea
- Lo otorga la Universidad Tecnológica Fidel Velázquez
Otras plataformas en línea
- Constancia privada emitida por la misma plataforma
- Solo acredita horas cursadas o asistencia
- Sin respaldo de una autoridad educativa
Tu itinerario, de la inscripción al certificado
- 1
Inscripción con pago único
Pagas $2,800 MXN una sola vez y entras de inmediato al curso.
- 2
Estudias a tu ritmo
16 unidades con videos, lecturas y actividades, disponibles 24/7 durante 12 meses.
- 3
Cuestionarios por unidad
Cuestionarios para comprobar lo aprendido.
- 4
Certificado
Emitido por la SEP a través del Gobierno del Estado de México, con folio verificable.
Un certificado oficial de la SEP
Muestra · verificable por folio y QR
- Emitido por la Secretaría de Educación Pública (SEP), a través del Gobierno del Estado de México. No es una constancia privada: es un documento oficial, y ese respaldo marca la diferencia frente a otras plataformas en línea.
- Contenido impartido por Laxmi Kant | KGP Talkie.
- Folio y QR verificables para compartirlo con quien te contrate.
Empieza hoy, a tu ritmo
Un solo pago y acceso inmediato al curso completo durante 12 meses.
- 16 unidades · 161 lecciones · 60 h
- 12 meses de acceso
- Certificado emitido por la SEP (Gob. del Estado de México) con folio verificable
Sobre tu inscripción
¿Cómo es el pago?
Un solo pago de $2,800 MXN. No hay mensualidades ni cargos recurrentes.
¿Cuánto tiempo tengo acceso?
12 meses desde tu inscripción, 24/7, para avanzar a tu ritmo.
¿Quién imparte el contenido?
El curso es impartido por Laxmi Kant | KGP Talkie; INEC gestiona tu inscripción, evaluación y certificado.
¿Qué pasa cuando vence mi acceso?
Puedes renovar tu cuenta tú mismo desde la plataforma, sin trámites ni esperas.
