Add Replicate demo and API

[ArielReplicate]

Hey @JackLee396 ! 👋

Thanks for this very cool project. I was happy to see depth from stereo is an ongoing research area.

This pull request makes it possible to run your model inside a Docker environment, which makes it easier for other people to run it. We're using an open source tool called Cog to make this process easier.

This also means we can make a web page where other people can run your model! View it here: https://replicate.com/arielreplicate/crestereo

Replicate also have an API, so people can easily run your model from their code:

import replicate
model = replicate.models.get("arielreplicate/crestereo")
depth_map = model.predict(left_image=<path>, right_image=<path>)

If you'd like to modify the Replicate page, let me know and I can transfer ownership to your account.
Also, If you want to allow control over more inference parameters like inference resize shape to the API please consult me.

In case you're interested, In Replicate, where we're trying to make machine learning reproducible. We got frustrated that we couldn't run all the really interesting ML work being done. So, we're going round implementing models we like. blush

[RobbertC5]

Hey @ArielReplicate

It would be nice if there is an option to get the raw disparity image, instead of the inferno colormap, as output. This way, one can actually use it in production.