Model Deployment
Serve ML models as REST APIs — containerised with Docker, deployed to the cloud.
0%
Confidence · no data yet
After this skill you can…
- Wrap a model in a FastAPI endpoint
- Containerise and deploy to a cloud service
- Implement batch and online inference pipelines
Prerequisites
Watch (10 videos)
Tutorial 11- How To Deploy End To End ML Projects In Production AWS Cloud Using CI CD Pipeline
→ Deploy ML models on AWS Cloud→ Use CI/CD pipelines for automated deployment
Use Amazon SageMaker with PyTorch (Hebrew)
→ Deploy a PyTorch model with SageMaker→ Train a model remotely using SageMaker
Run AI Models Inference on Amazon SageMaker HyperPod EKS | Amazon Web Services
→ Deploy AI models on Amazon SageMaker HyperPod EKS→ Use HyperPod Inference Operator for model inference
Day 3- MLOPS End To End Implementation With Deployment- Machine Learning
→ Deploy ML models→ Implement MLOPS pipelines
MLOps in R: Deploying machine learning models using vetiver
→ Deploy ML models to production→ Use vetiver for efficient deployment
Production ML with Hugging Face
→ Deploy ML models to production→ Implement MLOps pipelines
Automate, Evaluate and Deploy ML Models Confidently
→ Automate ML model deployment→ Evaluate ML model performance
Deploying machine learning models for inference- AWS Virtual Workshop
→ Deploy ML models to production environments→ Optimize ML model performance with SageMaker
Ryan Herr - After model.fit, before you deploy| JupyterCon 2020
→ Deploy scikit-learn models→ Create APIs for machine learning models
Deploy & Optimize ML Services Confidently
→ Deploy ML models to production→ Create RESTful inference services
DeepCamp AI