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

Plant AI: Project Showcase

Rishit Dagli
October 16, 2021
100

Plant AI: Project Showcase

Rishit Dagli

October 16, 2021
Tweet

Transcript

  1. Motivation • Read a disturbing headline • Researched a bit

    about the problem • Crop losses Source: National Academy of Science, Singh et al.
  2. Motivation • Read a disturbing headline • Researched a bit

    about the problem • Crop losses • We 🧡 tech and doing social good
  3. The Project • Turns out almost all farmers have access

    to smartphones - Research Study by Hughes et al.
  4. The Project • Turns out almost all farmers have access

    to smartphones • What does this do? ◦ Uses AI to diagnose diseases from plant images early
  5. The Project • Turns out almost all farmers have access

    to smartphones • What does this do? ◦ Uses AI to diagnose diseases from plant images early ◦ Provides actionable ways to solve diseases
  6. The Project • Turns out almost all farmers have access

    to smartphones • What does this do? ◦ Uses AI to diagnose diseases from plant images early ◦ Provides actionable ways to solve diseases ◦ Specific ways to solve
  7. The Project • Turns out almost all farmers have access

    to smartphones • What does this do? ◦ Uses AI to diagnose diseases from plant images early ◦ Provides actionable ways to solve diseases ◦ Specific and actionable ways to solve, AI also identifies species ◦ Works Offline, PWA
  8. The Project • Turns out almost all farmers have access

    to smartphones • What does this do? ◦ Uses AI to diagnose diseases from plant images early ◦ Provides actionable ways to solve diseases ◦ Specific and actionable ways to solve, AI also identifies species ◦ Works Offline • Approximated decrease in plant losses: 67% -> 25%
  9. Existing Solutions • CropNet (Google): only Cassava plants • Plant

    Village (Hughess et al): only a dataset • Plant Disease detector (Ramesh et al): unsatisfactory performance
  10. Existing Solutions • CropNet (Google): only Cassava plants • Plant

    Village (Hughess et al): only a dataset • Plant Disease detector (Ramesh et al): unsatisfactory performance • Some other disease detectors: not optimized or usable on small devices
  11. How we built this? - The Model • Collected data

    • Experimented with multiple architectures and hyperparameters
  12. How we built this? - The Model • Collected data

    • Experimented with multiple architectures and hyperparameters
  13. How we built this? - The Model • Collected data

    • Experimented with multiple architectures and hyperparameters • Optimize the model to run on-device (in a PWA)
  14. How we built this? - The Model • Collected data

    • Experimented with multiple architectures and hyperparameters • Optimize the model to run on-device (in a PWA) • Optimized the model to be just 12 MBs
  15. How we built this? - The Model • Collected data

    • Experimented with multiple architectures and hyperparameters • Optimize the model to run on-device (in a PWA) • Optimized the model to be just 12 MBs
  16. How we built this? - The Model • Collected data

    • Experimented with multiple architectures and hyperparameters • Optimize the model to run on-device (in a PWA) • Optimized the model to be just 12 MBs Wait, this is fast!💡
  17. How we built this? - Web App • Offline Support

    PWA • Run the optimized model with TFJS
  18. How we built this? - Web App • Offline Support

    PWA • Run the optimized model with TFJS ◦ Individually fetch data flow graph and weights ◦ Normalize images ◦ Resize with nearest neighbour interpolation
  19. How we built this? - Web App • Offline Support

    PWA • Run the optimized model with TFJS ◦ Individually fetch data flow graph and weights ◦ Normalize images ◦ Resize with nearest neighbour interpolation • Finally, deploy the web app to test out with real life scenarios🚀
  20. Business Plan • Farmers don't get charged • Potential plant

    product companies place ads • After a quality check their ads appear under “How to Solve”
  21. Business Plan • Farmers don't get charged • Potential plant

    product companies place ads • After a quality check their ads appear under “How to Solve” • Data, data and data
  22. Business Plan • Farmers don't get charged • Potential plant

    product companies place ads • After a quality check their ads appear under “How to Solve” • Data, data and data • Collect non sensitive but useful information
  23. Business Plan • Farmers don't get charged • Potential plant

    product companies place ads • After a quality check their ads appear under “How to Solve” • Data, data and data • Collect non sensitive but useful information • Plant images are used anonymously to improve the ML
  24. Business Plan • Farmers don't get charged • Potential plant

    product companies place ads • After a quality check their ads appear under “How to Solve” • Data, data and data • Collect non sensitive but useful information • Plant images are used anonymously to improve the ML • Usage data is shared to plant product companies
  25. Impact • Can reduce crop losses by 67% -> 25%🚀

    • Tested on real scenarios • Featured on Microsoft Blog and YouTube🤗
  26. Thank you! And we 🧡 open-source https://git.io/JujAg View on GitHub

    Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC)