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

AI for Art and Design-DSC at UW

AI for Art and Design-DSC at UW

Margaret Maynard-Reid

January 31, 2021
Tweet

More Decks by Margaret Maynard-Reid

Other Decks in Technology

Transcript

  1. @margaretmz | #AIArt | #TensorFlow | #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 3
  2. @margaretmz | #AIArt | #TensorFlow | #TFLite Art & Design

    • Photography • Sculpture • Drawing • Painting • Fashion design • Product design • UI/UX design • ... 4
  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 resolution - Image-to-image 5
  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 8
  5. @margaretmz | #AIArt | #TensorFlow | #TFLite Generative Adversarial Networks

    2014 What are GANs? Generative Adversarial Networks (GANs) have at least two network models which compete against each other ... 9
  6. @margaretmz | #AIArt | #TensorFlow | #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… 10
  7. @margaretmz | #AIArt | #TensorFlow | #TFLite • Training datasets

    must be paired • A type of conditional GAN Link to TensorFlow tutorial Pix2Pix 2016 11
  8. @margaretmz | #AIArt | #TensorFlow | #TFLite CycleGAN 2017 •

    Training datasets are unpaired • Horses <--> zebras • Summer <--> winter • Photos to paintings (Monet, Van Gogh etc.) Link to TensorFlow tutorial 12
  9. @margaretmz | #AIArt | #TensorFlow | #TFLite BigGAN 2018 Large

    scale GAN that generates high fidelity class-conditional images. Link to paper | TF Hub biggan512, biggan-256, biggan-128 13
  10. @margaretmz | #AIArt | #TensorFlow | #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 14
  11. @margaretmz | #AIArt | #TensorFlow | #TFLite Sketch2Code Microsoft: Turn

    your whiteboard sketches to working code in seconds with Sketch2Code 15
  12. @margaretmz | #AIArt | #TensorFlow | #TFLite Fashion++ Facebook AI:

    “Fashion++: Minimal Edits for Outfit Improvement” (news | paper) 16
  13. @margaretmz | #AIArt | #TensorFlow | #TFLite 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 17 https://github.com/margaretmz/awesome-ai-art-design
  14. @margaretmz | #AIArt | #TensorFlow | #TFLite AI & the

    Future of UX https://uxdesign.cc/ai/home 20
  15. @margaretmz | #AIArt | #TensorFlow | #TFLite AI for Art

    & Design AI will assist and inspire artists and designers Everyone can now make art and design! 21
  16. @margaretmz | #AIArt | #TensorFlow | #TFLite What is an

    ML model? • A complex mathematical function • A representation of learnings from training data 23
  17. @margaretmz | #AIArt | #TensorFlow | #TFLite Model training, conversion

    & inference 24 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
  18. @margaretmz | #AIArt | #TensorFlow | #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 API ◦ Edge TPU • A bunch of other tools: quantization, pruning, benchmarking... 26
  19. @margaretmz | #AIArt | #TensorFlow | #TFLite TensorFlow Lite Support

    0.1.0 • Task API • Support Library • Metadata Library • Codegen • Custom Ops • Model Maker • ML Model Binding 28
  20. @margaretmz | #AIArt | #TensorFlow | #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 30
  21. @margaretmz | #AIArt | #TensorFlow | #TFLite TensorFlow Lite tools

    1. Train a model • Teacheable machine • Model Maker ( w/ transfer learning) • ML Kit AutoML Vision • TensorFlow Hub 31 2. Convert • Converter • Optimization toolkit • Benchmarking tool 3. Deploy • ML Model Binding • Task API
  22. @margaretmz | #AIArt | #TensorFlow | #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 34 Example: Draw & recognize emojis
  23. @margaretmz | #AIArt | #TensorFlow | #TFLite ESRGAN on Android

    with TFLite • Enhanced Super Resolution GAN • Pre-trained ESRGAN model from TF Hub • Convert to TFLite model ◦ Dynamic range quantization ◦ Input image 50x50 • TensorFLow C API, GPU library • Android NDK 35 https://blog.tensorflow.org/2020/12/how-to-generate-super -resolution-images-using-tensorflow-lite-on-android.html
  24. @margaretmz | #AIArt | #TensorFlow | #TFLite Part 2: ML

    Model Binding from Android Studio TensorFlow Lite Model Maker Part 1: TensorFlow Lite Model Maker • Image/Text classification 36
  25. @margaretmz | #AIArt | #TensorFlow | #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 37
  26. @margaretmz | #AIArt | #TensorFlow | #TFLite 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 38
  27. @margaretmz | #AIArt | #TensorFlow | #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 39
  28. @margaretmz | #AIArt | #TensorFlow | #TFLite Segmentation + Style

    Transfer Demo by Khanh LeViet TFLite inference in Python, Already implemented in Android (and iOS)... (project repo) 40
  29. @margaretmz | #AIArt | #TensorFlow | #TFLite 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 42
  30. @margaretmz | #AIArt | #TensorFlow | #TFLite Follow me on

    Twitter, Medium or GitHub to learn more about deep learning, TensorFlow and on-device ML. @margaretmz @margaretmz margaretmz Thank you! 43