Add Docker environment & web demo

[chenxwh]

Hey @zhangmozhe ! 👋

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 try out your model! View it here: https://replicate.ai/zhangmozhe/bringing-old-photos-back-to-life

Claim your page here so you can edit it, and we'll feature it on our website and tweet about it too.

In case you're wondering who I am, I'm from 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. 😊

[jDavidnet]

what type of hardware are you running replicate.ai on? I'm very interested in the production side of ML.

I spent months on this model before the update, and I ran in to a huge memory leak that I was able to track down, but I'm not yet advanced enough in ML to fix the type of code that was in the project at that time. I was working with a group of newbs like myself and we wanted to rewrite the code in tensorflow. but now i'm wondering if we should rewrite it in pytorch lightning.

[jqueguiner]

Awesome.
IMO you should have a try except finally around the clean_folder.
lets assume you have a first image that ran into error you don't this to stay in the input folder

[chenxwh]

Awesome. IMO you should have a try except finally around the clean_folder. lets assume you have a first image that ran into error you don't this to stay in the input folder

Hi @jqueguiner,

Thank you for your comment! You are right! I have updated the PR with the fix :)

[zhangmozhe]

Hi @cjwbw, the web demo looks really cool. Thanks for your contribution!

[CodeMadUser]

Hi @cjwbw, the web demo looks really cool. Thanks for your contribution!

hello，EXCUSE ME,when I run the training code,I don't know where to find the file for training VAE_B_scratch weights, could you please share with me? I'm looking forward to your reply.Thank you.