Machine Learning to optimize images
summary
Introduces using machine learning techniques to optimize images, focusing on applying ML models to improve image processing and compression workflows. Describes technologies and methods for automating image optimization to integrate into software development and deployment pipelines.
AI-written summary · about
chapters (23)
- 0:00Introduction
- 1:01ML for image optimization
- 2:48Basic optimization examples
- 3:55Object detection models
- 6:50COCO dataset and training
- 8:13Selective blur implementation
- 10:01ML responsibility
- 11:24Image analysis tools
- 13:54Real-world web image analysis
- 17:07Lighthouse performance metrics
- 18:54Image formats and benefits
- 20:19Progressive vs interlaced loading
- 23:34WebP in production and support
- 24:35Free compression tools
- 26:25CLI optimization
- 28:36Plugins and automation
- 30:26Google Squoosh tool
- 31:54Jams internal optimizer
- 32:354:2:0 sampling explained
- 35:44Zstd and Butteraugli validation
- 37:33Integration in deployment pipelines
- 38:38Portrait mode and blur on mobile
- 41:45Resources and final conclusions
related talks
39mOptimizing User Support Services by Introducing Machine Learning Technologies
52mBoost Your Apps with Machine Learning APIs
01mMLOps: Applying DevOps to ML
52mMachine learning: from practice to theory
33mML: Automated Machine Learning
56mBuilding Intelligent Apps with Machine Learning
38mFixing the Image Problems of the Web using Machine Learning
28mReinventing Medical Imaging with AWS Machine Learning