docs: include Roadmap

[alestiago]

Description

As a user (or potential user) of the package, I would like to know the upcoming or possible features and what the team is working on. Is there any publically available documentation or board that indicates so?

Additional context

• https://github.com/tensorflow/flutter-tflite/issues/64#issuecomment-1561965053 makes reference to the roadmap

[CaptainDario]

@PaulTR mentioned this is mainly a community based project and there is no real roadmap see here

But for TF it seems like delegate support will be the major area of work from now on

Now that we're on 2.12, acceleration service and delegates are going to be the next big focus for features I think. I'll talk to product when they're ready to see what priorities should be from there as I ramp up on how this all works under the hood.

I am trying to get this running on desktop (#64) right now, if you have some MacOS experience that would be greatly appreciated.

[PaulTR]

So a quick update. I'm going to try and push for additional samples through a vendor we work with. I want to get the UI cleaned up on existing samples (scale images to take up full view area, support a live camera feed), then add additional samples based on ones that we already support for native Android and iOS, particularly:

Audio classification Bert QA Digit classifier Gesture classification Image segmentation Model personalization (maybe) Pose estimation

I also want to move the models to a remote location and download them at build time through a script for each example. My goal there is to reduce repo size going forward.

[gregorscholz]

Maybe a simple solution would be to have a simple script just for us to execute before building the app. Then we can put assets/model/ path in .gitignore and remove it from here. Here maybe for the text_classification example:

# Delete old models
rm -r assets/model/

# Create folder if not already exists
mkdir assets/model

# Download model
curl https://storage.googleapis.com/download.tensorflow.org/models/tflite/text_classification/text_classification.tflite \
    -o assets/model/text_classification.tflite

# Unzip model to get labels and vocab
unzip assets/model/text_classification.tflite \
    -d assets/model/