[Feature] Deliver Models and Large Files as Artifacts

[AmitMY]

Problem

At the moment, models are included in the build distribution.
This makes the build quite heavy, and native files too large and unappealing.

Description

Make an "artifacts management" system that can download artifacts like necessary models, and store them in the app's documents folder.

When a new artifact is available, it should prompt to download.

When a user tries to use a feature requiring a missing artifact, it should prompt the user to download and wait until finishes.

---

For the web, and maybe Android, can store .tflite models on firebase ML

For iOS, can use Core ML Model Deployment https://developer.apple.com/icloud/core-ml/

[AmitMY]

Firebase ML has two issues:

1. Does not allow large files
2. Not available for the web

Alternative solution: Cloud storage, upload h5 file, auto converts to coreml and tflite

[AmitMY]

For CoreML, the convolutions might be too much:

2022-07-02 22:57:13.178238+0200 benchmark[20833:399499] Error: Convolution configuration cannot fit in KMEM (Given: 73728b, Max: 65536b)

[AmitMY]

Proposal:

• upload model files to storage.
• automatically convert to tflite and coreml files
• create a assets module, that can download and store models in navigator.storage / Capacitor Filesystem
• create a assets page, that can:
  • delete
  • download
  • update
  • show when update is available
• store all models and large files here:
  • pose-to-person/generator
  • pose-to-person/upscaler
  • bergamot model files
  • avatar glb and usdz files
  • holistic pose estimation (50+ mb)