Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Ready to use deep learning models

Ready to use deep learning models

Gabriela de Queiroz

September 21, 2019
Tweet

More Decks by Gabriela de Queiroz

Other Decks in Technology

Transcript

  1. R E A D Y T O U S E

    D E E P L E A R N I N G M O D E L S —
 Gabriela de Queiroz
 Sr. Engineering & Data Science Manager, IBM Founder, R-Ladies Founder, AI Inclusive @gdequeiroz | www.k-roz.com Slides: http://bit.ly/max-gdgdevfest19
  2. Center for Open Source Data and AI Technologies (CODAIT) -

    CODAIT aims to make AI solutions easier to create, deploy, and manage in the enterprise - Relaunch of the Spark Technology Center (STC) to reflect expanded mission Watson West Building 505 Howard St. San Francisco, California CODAIT codait.org @gdequeiroz | www.k-roz.com | [email protected]
  3. 30+ open source developers! • TensorFlow • PyTorch • Keras

    • Apache Arrow • ONNX • Jupyter • Apache Spark • Kubeflow • And more
  4. Have you ever wanted to classify images, identify objects or

    generate captions of images? @gdequeiroz | www.k-roz.com | [email protected] Slides: http://bit.ly/max-gdgdevfest19
  5. Applying Deep Learning: Perception Data ??? Train model ??? $$$

    Get model ??? Deploy model ??? $$$ Training – Data Scientist Consumption – App Developer, Domain Expert Slides: http://bit.ly/max-gdgdevfest19
  6. Applying Deep Learning: Reality Find model Get code Test, verify,

    fix Train model Deploy model Use model Discovery Execution Consumption 1 2 3 4A 4B 5 @gdequeiroz | www.k-roz.com | [email protected]
  7. Step 1: Find a model … that does what you

    need … that is free to use … that is performant enough
  8. Step 2: Get the code Is there a good implementation

    available? … that does what you need … that is free to use … that is performant enough TensorFlow code to build ResNet50 neural network graph
  9. Or … Step 2: Get the pre-trained weights Is there

    a good pre-trained model available? … that does what you need … that is free to use … that is performant enough
  10. Step 3: Verify the model you found Check … …

    that does what you need … that is free to use (license) … that is performant enough (computation & accuracy)
  11. Step 4 (b): Figure out how to deploy your model

    … adjust inference code (or write from scratch) … package inference code and model code, and pre-trained weights together … deploy your package
  12. Applying Deep Learning: Reality Find model Get code Test, verify,

    fix Train model Deploy model Use model Discovery Execution Consumption 1 2 3
  13. Model Asset eXchange • One-stop place for developers/data scientists to

    find and use free and open source deep learning models ibm.biz/model-exchange @gdequeiroz | www.k-roz.com | [email protected]
  14. Model Asset eXchange (MAX) • Wide variety of domains (text,

    audio, image, etc) • Multiple deep learning frameworks • Vetted and tested code and IP • Trainable and Deployable versions • Build and deploy a model web service in seconds ibm.biz/model-exchange
  15. Find* a state-of-art open source deep learning model specific to

    domain Validate license terms Perform model health check & code clean up Wrap models in MAX framework and provide REST API Publish the deployable model as Docker images on Docker Hub Use the MAX training framework to create an image for custom model training Review and Continuous Integration * or build from scratch Model Asset eXchange (MAX) ibm.biz/model-exchange BEHIND THE SCENES
  16. 2) WEB APP • User uses Web UI to send

    an image to Model API • Model API returns object data and Web UI displays detected objects •
  17. MAX-Framework MAX-Skeleton •A pip installable python library •Wrapper around flask

    •Abstracts out all basic functionality of the MAX model into MAXModelWrapper and MAXApi abstract classes github.com/IBM/MAX-Framework •Template to create a deployable MAX model •Contains all the code scaffolding and imports MAX Framework github.com/IBM/MAX-Skeleton
  18. Data Asset eXchange (DAX) • Curated free and open datasets

    under open data licenses • Standardized dataset formats and metadata • Ready for use in enterprise AI applications • Complement to the Model Asset eXchange (MAX) • ibm.biz/data-asset-exchange
  19. Thank you! K- ROZ .COM @GDEQUEIROZ GABRI EL A DE

    QU EI ROZ ai-inclusive.org Our mission is to increase the representation and participation of gender minority groups in AI. [email protected] ibm.biz/model-exchange Slides: http://bit.ly/max-gdgdevfest19