$30 off During Our Annual Pro Sale. View Details »

Ready to use Deep Learning Models: All You Need is 5 Minutes

Ready to use Deep Learning Models: All You Need is 5 Minutes

Talk at Data Science GO 2018, San Diego, CA 2018-10-13

- Conference website: https://www.datasciencego.com

You can find other presentations on my website: https://k-roz.com/talks/

Gabriela de Queiroz

October 13, 2018
Tweet

More Decks by Gabriela de Queiroz

Other Decks in Technology

Transcript

  1. GABRIELA DE QUEIROZ
    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 :
    A L L Y O U N E E D I S
    5 M I N U T E S
    SENI OR DEVELOPER ADVOCATE (ML /DL/A I) @ IBM
    @gdequeiroz | www.k-roz.com | [email protected]

    View Slide

  2. GABRIELA DE QUEIROZ
    ‣ Sr Developer Advocate, IBM
    ‣ Founder, R-Ladies
    ‣ Lead Data Scientist
    ‣ Data Scientist
    ‣ Statistician/Epidemiologist/
    Researcher
    About me
    Data +
    Community +
    Mentor +
    Advocate
    @gdequeiroz | www.k-roz.com | [email protected]

    View Slide

  3. 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
    30+ open source developers!
    Watson West Building
    505 Howard St.
    San Francisco, California
    Improving Enterprise AI lifecycle in Open Source
    Gather
    Data
    Analyze
    Data
    Machine
    Learning
    Deep
    Learning
    Deploy
    Model
    Maintain
    Model
    Python
    Data Science
    Stack
    Fabric for
    Deep Learning
    (FfDL)
    Mleap +
    PFA
    Scikit-Learn
    Pandas
    Apache
    Spark
    Apache
    Spark
    Jupyter
    Model
    Asset
    eXchange
    Keras +
    Tensorflow
    CODAIT
    codait.org

    View Slide

  4. Improving Enterprise AI lifecycle in Open Source
    Gather
    Data
    Analyze
    Data
    Machine
    Learning
    Deep
    Learning
    Deploy
    Model
    Maintain
    Model
    Python
    Data Science
    Stack
    Fabric for
    Deep Learning
    (FfDL)
    Mleap +
    PFA
    Scikit-Learn
    Pandas
    Apache
    Spark
    Apache
    Spark
    Jupyter
    Model
    Asset
    eXchange
    Keras +
    Tensorflow
    CODAIT: Enabling End-to-End AI in the Enterprise

    View Slide

  5. Have you ever wanted to classify images,
    recognize faces or places or generate captions
    of images?
    @gdequeiroz | www.k-roz.com | [email protected]

    View Slide

  6. With the
    Model Asset
    eXchange,
    you can!

    View Slide

  7. The Model Asset eXchange enables domain experts to use deep learning in the enterprise.
    Q: What is deep learning?

    A: Machine learning using deep neural networks.

    Q: What is a deep neural network?

    A: A neural network with multiple hidden layers.


    View Slide

  8. What is a neural network?

    View Slide

  9. ! = #$%
    + &$'
    + c$)
    Linear regression
    What is a neural network?

    View Slide

  10. ! = #$%
    + &$'
    + c$)
    x
    1
    x
    2
    x
    3
    y
    a
    b
    c
    Linear regression
    What is a neural network?
    Nodes
    Edges

    View Slide

  11. What is a neural network?
    x
    1
    x
    2
    x
    3
    y
    3
    y
    1
    y
    4
    y
    2
    Multiple linear regressions
    at the same time

    View Slide

  12. What is a neural network?
    Second layer
    of linear
    regressions
    Multilayer Perceptron Neural Network

    View Slide

  13. What is a neural network?
    Second layer
    of linear
    regressions
    Multilayer Perceptron Neural Network
    Dense
    (3×4)
    Dense
    (4×2)
    Input
    (3)
    Output
    (2)
    Same network in a more compact notation

    View Slide

  14. What is a deep neural network?
    A neural network with multiple hidden layers
    Dense
    (3×8)
    Dense
    (8×6)
    Input
    (3)
    Output
    (2)
    Dense
    (6×4)
    Dense
    (4×2)
    “toy" deep neural network

    View Slide

  15. Applying Deep Learning: Perception
    Data ???
    Train
    model
    ??? $$$
    Get
    model
    ???
    Deploy
    model
    ??? $$$
    Training – Data Scientist
    Consumption – App Developer, Domain Expert

    View Slide

  16. 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]

    View Slide

  17. Step 1: Find a model
    … that does what you need
    … that is free to use
    … that is performant enough

    View Slide

  18. 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

    View Slide

  19. 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

    View Slide

  20. 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)

    View Slide

  21. Step 4 (a): Train the model

    View Slide

  22. Step 4 (a): Train the model

    View Slide

  23. 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 weigths together
    … deploy your package

    View Slide

  24. Step 5: Consume your model
    … plug in into your application

    View Slide

  25. Step 6: Profit
    … hopefully

    View Slide

  26. Applying Deep Learning: Reality
    Find
    model
    Get
    code
    Test,
    verify,
    fix
    Train
    model
    Deploy
    model
    Use
    model
    Discovery Execution Consumption
    1 2 3

    View Slide

  27. Model Asset eXchange
    • A one-stop place for developers/data scientists to
    find and use free and open source deep learning
    models
    ibm.biz/model-exchange

    View Slide

  28. Model Asset eXchange
    • Wide variety of domains (text, audio, image, etc)
    • Multiple deep learning frameworks
    • Vetted and tested code and IP
    • Build and deploy a model web service 

    in seconds
    • Training on Fabric for Deep Learning (FfDL) or Watson
    Machine Learning in minutes
    ibm.biz/model-exchange

    View Slide

  29. Trainable Models
    TRAINING
    DATA
    TRAINING
    CODE
    TRAINING
    DEFINITION
    STANDARDIZED
    SCRIPT
    https://github.com/IBM/FfDL

    View Slide

  30. DATA MODEL
    COMPUTER
    RESOURCES
    EXPERTISE
    Input/Output
    Processing
    Pre-Trained Model
    REST API
    Deep Learning Asset on Model Asset Exchange
    ibm.biz/model-exchange
    Deployable Models

    View Slide

  31. Swagger
    Specification
    Deep Learning Asset on Model Asset Exchange
    ibm.biz/model-exchange
    Deployable Models
    Deploy
    Inference
    Endpoint
    Metada
    Endpoint
    Microservice
    REST API

    View Slide

  32. OPEN SOURCE
    &
    FREE
    ibm.biz/model-exchange

    View Slide

  33. Highlights
    • Image, audio, text, healthcare, time-series and
    more
    • Pre- / post-processing & inference wrapped up
    in Docker container
    • Generic API framework code - Flask RESTPlus
    • Swagger specification for API
    • One-line deployment locally and on a
    Kubernetes cluster

    View Slide

  34. •Code Patterns demonstrating how to easily consume MAX models
    ibm.biz/max-developers

    View Slide

  35. All that is available
    for YOU for FREE

    View Slide

  36. DEMO!
    Wish me luck
    ibm.biz/model-exchange
    ibm.biz/max-developers

    View Slide

  37. There is no failure, only feedback

    View Slide

  38. Thank you!
    MITJA BOSNIČ
    KIRILL EREMENKO PAULO REALPE SEBASTIAN MONCADA
    MARÍA VIRGINIA PERDOMO MARTÍN DURÁN RUBY ANGELA PAGALAN

    View Slide

  39. Thank you
    GDQ@IBM,COM K-ROZ.COM @ G D E Q U E I R O Z

    View Slide