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

AI for Art & Design - TFUG India Summit

AI for Art & Design - TFUG India Summit

This talk showcases how to use TensorFlow Lite models on mobile devices to create artistic designs. There is 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 the open-source computer vision and deep learning tools, and use cases of AI for art and design. This talk is for you whether you are an artist or designer who would like to learn more about AI/ML; or an engineer and anyone who is interested in creating art & design with AI, in particular with mobile apps.

Margaret Maynard-Reid

September 04, 2020
Tweet

More Decks by Margaret Maynard-Reid

Other Decks in Technology

Transcript

  1. AI for Art & Design with Lite Margaret Maynard-Reid, Sept

    4 2020 #TFUGIndiaSummit @margaretmz
  2. #TFUGIndiaSummit | @margaretmz | #TFLite Topics • Computer vision tasks

    • Generative art & design • Datasets 2 AI for Art & Design TensorFlow Lite Samples & tutorials • Samples & tutorials • Community • Tools & resources • What is TFLite? • How to make apps
  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 3
  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
  5. #TFUGIndiaSummit | @margaretmz | #TFLite Generative Adversarial Networks 2014 What

    are GANs? Generative Adversarial Networks (GANs) have at least two network models which compete against each other ... 7
  6. #TFUGIndiaSummit | @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… 8
  7. #TFUGIndiaSummit | @margaretmz | #TFLite • Training datasets must be

    paired • A type of conditional GAN Link to TensorFlow tutorial Pix2Pix 2016 9
  8. #TFUGIndiaSummit | @margaretmz | #TFLite CycleGAN 2017 • Training datasets

    are unpaired • Horses <--> zebras • Summer <--> winter • Photos to paintings (Monet, Van Gogh etc.) Link to TensorFlow tutorial 10
  9. #TFUGIndiaSummit | @margaretmz | #TFLite BigGAN 2018 Large scale GAN

    that generates high fidelity class-conditional images. Link to paper | TF Hub biggan512, biggan-256, biggan-128 11
  10. #TFUGIndiaSummit | @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 12
  11. #TFUGIndiaSummit | @margaretmz | #TFLite Sketch2Code Microsoft: Turn your whiteboard

    sketches to working code in seconds with Sketch2Code 13
  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 15 UI/UX Design • Rico mobile app datasets • Kaggle ◦ Common Mobile/Web App Icons ◦ Icons-50
  13. #TFUGIndiaSummit | @margaretmz | #TFLite What is TensorFlow Lite? A

    framework with a set of tools for deploying ML to mobile & embedded: • A converter • An interpreter • Ops / kernels • Interface to hardware accelerations: ◦ NN AIP ◦ Edge TPu • A bunch of other tools... 17
  14. #TFUGIndiaSummit | @margaretmz | #TFLite How to make a TensorFlow

    Lite app? • 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: gallery or camera ◦ Run model inference ◦ Display result in UI 19
  15. #TFUGIndiaSummit | @margaretmz | #TFLite What is an ML model?

    • A complex mathematical function • A representation of learnings from training data 20
  16. #TFUGIndiaSummit | @margaretmz | #TFLite How to get an ML

    model? • Train your own • Transfer learning • Download from TensorFlow Hub • Use ML Kit 21
  17. #TFUGIndiaSummit | @margaretmz | #TFLite ML Kit Digital Ink Recognition

    Draw & recognize emojis Blog post: https://developers.googleblog.com/2020/08/digital-ink- recognition-in-ml-kit.html Sample app: https://developers.google.com/ml-kit/vision/digital-ink-r ecognition 24
  18. Part 2: ML Model Binding from Android Studio TensorFlow Lite

    Model Maker Part 1: TensorFlow Lite Model Maker • Image/Text classification 25
  19. #TFUGIndiaSummit | @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 26
  20. 27 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
  21. #TFUGIndiaSummit | @margaretmz | #TFLite 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 28
  22. #TFUGIndiaSummit | @margaretmz | #TFLite Segmentation + Style Transfer Demo

    by Khanh LeViet TFLite inference in Python, to be implemented on mobile... (project repo) 29
  23. 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 32
  24. #TFUGIndiaSummit | @margaretmz | #TFLite AI for Art & Design

    AI will assist and inspire artists and designers Everyone can now make art and design! 36
  25. #TFUGIndiaSummit | @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! 37