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

AI for Art & Design - Droidcon Americas 2020

AI for Art & Design - Droidcon Americas 2020

This talk showcases how to use TensorFlow Lite models on Android to create artistic designs. It starts with a brief overview of how AI can be used to assist and inspire the artists and designers in their creative space. You will also learn about open-source computer vision and deep learning tools. Then we dive into details of TensorFlow lite and the end-to-end scenarios of how to make Android apps with ML models for art and design.

https://www.online.droidcon.com/agenda-dcamericas

Margaret Maynard-Reid

November 17, 2020
Tweet

More Decks by Margaret Maynard-Reid

Other Decks in Technology

Transcript

  1. #dcAmericas | @margaretmz | #TFLite Topics • Computer vision tasks

    • Generative art & design • Datasets & resources AI for Art & Design TensorFlow Lite Android Samples & tutorials • Sample apps • Awesome TFLite • E2E TFLite Tutorials • What is TFLite? • TFLite on Android • Tools & resources 2
  2. #dcAmericas | @margaretmz | #TFLite Art & Design • Photography

    • Sculpture • Drawing • Painting • Fashion design • Product design • UI/UX design 3
  3. Computer Vision Tasks Complexity Image classification (single-label) Classify an image

    to a class Examples Painting style or artist Van Gogh Image classification (multi-label) Classify an image to multiple classes Examples Movie poster genre action, sci-fi Feature extraction Extracting latent features of an image with CNN models Examples Visual search find similar fashion Object detection Identify one or multiple objects within an image and their locations with bounding boxes. detect UI elements Segmentation Classify whether each pixel of the image belongs to a certain class segment UI elements Generative models (GANs) Two or more models trained simultaneously Examples - Generate new images - Super res - Image-to-image 4
  4. Use CNN neural networks Content image + style image =

    styled image Content Style Generated Neural Style Transfer: 50 Shades of Miaw (link) A few more samples of generated images… Style Transfer 2015 7
  5. #dcAmericas | @margaretmz | #TFLite Generative Adversarial Networks 2014 What

    are GANs? Generative Adversarial Networks (GANs) have at least two network models which compete against each other ... 8
  6. #dcAmericas | @margaretmz | #TFLite GANs variations GANs are fun

    but difficult to train! • 2014 Ian Goodfellow’s original GAN’s paper • 2015 DCGAN (Deep Convolutional GAN) (paper) • 2014 cGAN (Conditional GAN) - Generate images conditioned on a class (paper) • 2016 Pix2Pix – paired image to image translation (paper) • 2017 CycleGAN – unpaired Image to image translation • 2018 StyleGAN – Generate images with some control on image characteristics (paper) • Many other GAN variations… 9
  7. #dcAmericas | @margaretmz | #TFLite • Training datasets must be

    paired • A type of conditional GAN Link to TensorFlow tutorial Pix2Pix 2016 10
  8. #dcAmericas | @margaretmz | #TFLite CycleGAN 2017 • Training datasets

    are unpaired • Horses <--> zebras • Summer <--> winter • Photos to paintings (Monet, Van Gogh etc.) Link to TensorFlow tutorial 11
  9. #dcAmericas | @margaretmz | #TFLite BigGAN 2018 Large scale GAN

    that generates high fidelity class-conditional images. Link to paper | TF Hub biggan512, biggan-256, biggan-128 12
  10. #dcAmericas | @margaretmz | #TFLite Control the styles of the

    generated images • Pose • Face shape • Age • Gender • Hair color 4x4 --> 1024x1024 8GPUs trained for 1 week Current examples: faces, bedrooms and cats Link to video StyleGAN 2018 13
  11. #dcAmericas | @margaretmz | #TFLite Sketch2Code Microsoft: Turn your whiteboard

    sketches to working code in seconds with Sketch2Code 14
  12. Datasets Art • The Art Institute of Chicago - 5000

    high res images • Best Artworks of All Time • Art Images: Drawing/Painting/Sculptures/Engravings • Overwatch Heroes Recognition • Chinese Fine Art • Museum of Modern Art Collection UI/UX Design • Rico mobile app datasets • Kaggle ◦ Common Mobile/Web App Icons ◦ Icons-50 16
  13. #dcAmericas | @margaretmz | #TFLite AI & the Future of

    UX https://uxdesign.cc/ai/home 19
  14. #dcAmericas | @margaretmz | #TFLite AI for Art & Design

    AI will assist and inspire artists and designers Everyone can now make art and design! 20
  15. #dcAmericas | @margaretmz | #TFLite What is an ML model?

    • A complex mathematical function • A representation of learnings from training data 22
  16. #dcAmericas | @margaretmz | #TFLite Model training, conversion & inference

    23 Model • tf.Keras (TensorFlow) • Python libraries: Numpy, Matplotlib etc SavedModel or Keras model Serving • Cloud • Web • Mobile • IoT • Micro controllers • Edge TPU Training Inference Data
  17. #dcAmericas | @margaretmz | #TFLite What is TensorFlow Lite? A

    framework with a set of tools for deploying ML models to mobile & embedded: • A converter • An interpreter • Ops / kernels • Interface to hardware accelerations: ◦ NN AIP ◦ Edge TPu • A bunch of other tools... 25
  18. #dcAmericas | @margaretmz | #TFLite Android app with TensorFlow Lite

    • ML model: ◦ Train / find a model ◦ Convert to .tflite format ◦ Run inference in Python ◦ Benchmark (optional) ◦ Add model metadata • Build Android app ◦ UI navigation ◦ Input image: canvas, gallery or camera ◦ Load model & run inference ◦ Display results in UI 27
  19. #dcAmericas | @margaretmz | #TFLite TensorFlow Lite tools 1. Train

    a model • Teacheable machine • Model Maker ( w/ transfer learning) • ML Kit AutoML Vision • TensorFlow Hub 28 2. Convert • Converter • Optimization toolkit • Benchmarking tool 3. Deploy • ML Model Binding • Task API
  20. #dcAmericas | @margaretmz | #TFLite ML Kit Digital Ink Recognition

    Recognize handwritten text and drawings • Text models: 300+ languages • Non-text models ◦ Autodraw ◦ Emoji ◦ Shapes Blog: Digital Ink Recognition in ML Kit Sample app: Overview | GitHub 31 Example: Draw & recognize emojis
  21. Part 2: ML Model Binding from Android Studio TensorFlow Lite

    Model Maker Part 1: TensorFlow Lite Model Maker • Image/Text classification 32
  22. #dcAmericas | @margaretmz | #TFLite Style transfer Google Arts &

    Culture app: https://play.google.com/store/apps/details?id=com.google.android.apps.cultural Blog post: 4/2/2020 - Transform your photo in the style of an iconic artist 33
  23. Selfie2Anime • U-GAT-IT paper • Image to image translation •

    Written in TF1 code • Unpaired selfie and anime images • 50 & 100 epochs checkpoints • Collaboration with Sayak & Khanh • Links: project repo | blog 34
  24. #dcAmericas | @margaretmz | #TFLite Cartoonizer • Model: Whitebox CartoonGAN

    ◦ Faster & smaller ◦ Not just for selfies • Link to project repo • Link to TF Hub models • Collaboration with Sayak & Khanh • Links: project repo | blog 35
  25. #dcAmericas | @margaretmz | #TFLite Segmentation + Style Transfer Demo

    by Khanh LeViet TFLite inference in Python, Already implemented in Android (and iOS)... (project repo) 36
  26. Awesome TensorFlow Lite A curated list of models, apps, tutorials

    and learning resources… Thanks to the ML GDE and Android community! Support of TensorFlow Lite team https://github.com/margaretmz/awesome-tflite 38
  27. #dcAmericas | @margaretmz | #TFLite Follow me on Twitter, Medium

    or GitHub to learn more about deep learning, TensorFlow and on-device ML. @margaretmz @margaretmz margaretmz Thank you! 39