Launch app in AWS Sagemaker
Go to main | Course Page
Section 1: Introduction to Sagemaker
- Introduction to Sagemaker
- Download Resources
- Sagemaker Features
- Intro to the simple end-to-end ML problem
- Free Tier Options
Section 2: Sagemaker Studio
- Sagemaker Studio Setup (Live)
- Exploring the Studio
- How sagemaker works internally
Section 3: Sagemaker Initial Setup
- Setting up Boto and sagemaker packages
- Execution Role and role of S3
Section 4: Getting Data into Sagemaker and S3
- Begin data preprocessing
- How to upload data from S3 from Sagemaker?
Section 5: Preprocessing Jobs
- How to handle compute intensive tasks in dedicated container
- Overview of Docker
- Preprocessing job - part 1
- Preprocessing job - part 2
- Why transfer the Python code file to S3
- Understanding the arguments for running the processing job
- Inspecting Processing Jobs
Section 6: Sagemaker Experiments
- Experiments and Trials
- Steps to conduct an experiment in sagemaker
- Creating tracker
- Create Trial Image
- Running training trial for XGBoost Estimator
Section 7: Model Deployment
- Batch processing vs model serving
- Real Time Inference
- Model Endpoint Part 1 - Creating Model.mp4
- Model Endpoint Pt 2 - Create Endpoint Config
- Model Endpoint Pt 3 - Create Endpoint and monitor
- Remember to delete endpoints
Section 8: Hyper Parameter Tuning in Sagemaker
- Hyper Parameter Tuning with Sagemaker