Get started with ML in minutes with Amazon SageMaker JumpStart
summary
Amazon SageMaker JumpStart provides 150 pre-trained models for vision and text plus one-click fine-tune and deploy from the Studio catalog, with endpoints spinning up in about 5–10 minutes and small fine-tuning jobs taking ~5 minutes. The demo fine-tunes Inception v3 on TF Flowers and upgrades ImageNet outputs to recognize sunflowers. A fraud solution uses XGBoost and Random Cut Forest behind API Gateway, Lambda, Kinesis and S3 and reports 90% balanced accuracy despite datasets with less than 1% fraud—remember to delete endpoints to avoid charges.
AI-written summary · about
chapters (11)
- 0:00Introduction to JumpStart
- 0:27Machine learning workflow
- 1:31Overview of SageMaker
- 2:13Open source models
- 3:33Model deployment and tuning
- 9:16Fine-tuning workflow
- 13:13Testing and managing models
- 15:26SageMaker solutions
- 17:39Fraud detection demo
- 26:39Getting started resources
- 28:28Conclusion and results
related talks
52mGenerate ML predictions without writing any code
19mUsing Amazon SageMaker to develop and deploy ML models
49mUse Amazon SageMaker to build high-quality ML models faster
01h 41mGetting started with Machine Learning on AWS.
44mPragmatic Machine Learning in the Cloud
33mBuild, train, and deploy ML models using Amazon SageMaker
30mBring AutoML to all users across your business
27mScaling ML to the next level: Hosting thousands of models on SageMaker