Deploying A Custom Pytorch Model to SageMaker using Terraform, Docker, FastAPI and Pytorch

preview_player
Показать описание
In this video, we show how to deploy a custom Machine Learning Pytorch model to an AWS Sagemaker endpoint, using Infrastructure as Code (IaaC) Terraform, Docker for containerisation and Pytorch for model training and FastAPI for inference.

-------

  1. MLOps with AM
  2. Pytorch
  3. Terraform
  4. AWS
  5. AWS Sagemaker
  6. Python
Рекомендации по теме
Deploying A Custom 0:45:05

Deploying A Custom Pytorch Model to SageMaker using Terraform, Docker, FastAPI and Pytorch

AWS re:Invent 2020: 0:32:49

AWS re:Invent 2020: Deploying PyTorch models for inference using TorchServe

Production Inference Deployment 0:15:41

Production Inference Deployment with PyTorch

PyTorch in 100 0:02:43

PyTorch in 100 Seconds

Create & Deploy 0:41:52

Create & Deploy A Deep Learning App - PyTorch Model Deployment With Flask & Heroku

torch::deploy: Running eager 0:07:34

torch::deploy: Running eager PyTorch models in production

Torchserve: A Performant 0:08:08

Torchserve: A Performant and Flexible tool for Deploying PyTorch Models into Production

Building Models with 0:14:09

Building Models with PyTorch

Deploying your ML 0:10:39

Deploying your ML Model with TorchServe

Deploy an Image 0:07:36

Deploy an Image Recognition PyTorch model using Flask

Deploying PyTorch, deploying 0:00:48

Deploying PyTorch, deploying Anthos, & more! #Shorts #GoogleCloudUpdates

PyTorch vs TensorFlow 0:03:47

PyTorch vs TensorFlow | Ishan Misra and Lex Fridman

How to Serve 0:16:23

How to Serve PyTorch Models with TorchServe

Build and Deploy 0:02:12

Build and Deploy a Machine Learning App in 2 Minutes

Build and deploy 0:59:12

Build and deploy production ready PyTorch models - Henk Boelman - NDC Porto 2022

PyTorch Beginner Tutorial 0:19:46

PyTorch Beginner Tutorial - Training an Image Classification Model and putting it online!

Deploy a custom 0:05:27

Deploy a custom model to Vertex AI

Build and deploy 0:48:11

Build and deploy PyTorch models with Azure Machine Learning

Deploy ML model 0:12:41

Deploy ML model in 10 minutes. Explained

Deploy ML models 0:18:45

Deploy ML models with FastAPI, Docker, and Heroku | Tutorial

PyTorch Edge: Developer 0:20:21

PyTorch Edge: Developer Journey for Deploying AI Models Onto Edge Devices - Mengwei Liu & Angela...

YOLOv8: How to 0:19:22

YOLOv8: How to Train Objection Model with Custom Dataset

End To End 0:40:25

End To End Machine Learning Project Implementation Using AWS Sagemaker

Deploy Fine Tuned 0:22:54

Deploy Fine Tuned BERT or Transformers model on Streamlit Cloud #nlp #bert #transformers #streamlit

Комментарии
Автор

thank you, please continue producing videos

aminasgharisooreh
Автор

Great content! However, it would be even more helpful if you could provide detailed explanations of the steps involved in configuring AWS IAM for Terraform..

huytube
Автор

Hi, Thank you so much for making this tutorial. I have a question, I see that you have defined a "/invocations" endpoint, is it possible to have multiple post/get endpoints and use it? And I have a pretrained CLIP model from transformers library Im using. Essentially my endpoint would take in a video, read frame by frame and insert these embeddings into a vector database. Currently I have it wrapped in a fastapi application deployed to a CPU instance on EC2. My application would benefit a ton from having a GPU and I was wondering if there are any other ways to deploy this on a GPU instance or any recommendations at all :)) I would really appreciate your input!

Tetrax
Автор

How to make the final request via postman?

samsantechsamsan