lobe / ios-bootstrap Goto Github PK

Hello, love the app, first of all. This is how training should be!

I did run into a snag: I've successfully trained the model to recognize screenshots from audible, youtube, and apple podcasts and that model works very well on desktop using the "Play" section.

However, when I export the model and use it in the iOS Bootstrap, it does very bad at recognizing any screenshot accurately.

All I've done with code is replaced LobeModel with SavedModel directly from Lobe.

Any suggestions?

Video demo link: https://www.youtube.com/watch?v=_rtKnlmsxzM

Tracking changes to u/elbosc/main branch:

• Open Screen
  • Import model
  • Switch between models
  • Delete models
  • Name and rename projects
  • Update folder path schema for saving projects
• Play View
  • Taskbar buttons for flipping camera, photo picker
  • Camera zoom
• Bugs
  • Landscape orientation doesn't work with camera
  • Flip camera not working
  • Fix orientation and cropping issues with images sent to prediction
  • Fix screenshot functionality to save the image sent as input for processing
  • Fix "image not found" logs
  • Squared image for image preview doesn't appear to be perfectly centered for portrait orientation
• Refactoring
  • Move prediction and view model logic out of view controller
  • Hook project picker import to view model
  • Move capture session logic out of view controller
  • Remove frame-rate check
• Engineering Systems
  • CI pipeline
  • Environment variable for viewing image sent for inference
  • Linting
  • Unit testing
• Polish
  • Set tint to Lobe Green
  • Consider remove stack list style for open screen list
  • Remove header background that appears on landscape mode for iPhone
  • Add UI transition animation for camera flip
  • Update icon to new logo
  • Loading screens for launch, open screen, and play view
  • Handling errors in all views
• Docs
  • Update README's with new files