search

ariel415el / GPDM

Original Pytorch implementation of the GPDM model introduced in "Generating natural images with direct patch distributions matching"
Apache License 2.0
61 stars 7 forks source link

Add Web Demo & Docker environment #1

Closed chenxwh closed 2 years ago

chenxwh commented 2 years ago

Hey @ariel415el ! 👋

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.com/ariel415el/gpdm. The docker file can be found under the tab ‘run model with docker’. We have implemented style transfer, it support webcam input too!

Do claim the page so you can own the page, customise the Example gallery as you like, add other functionalities/push any future update to the web demo, and we'll feature it on our website and tweet about it too. You can find the 'Claim this model' button on the top of the page ~

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. 😊

ariel415el commented 2 years ago

Hi,

Great to hear about your work, this is a very cool demo you made. I saw you created the changes in a separate branch. Does merging the pull request will put the changes in the main branch? If not how do I do this. Also, Can you move predict.py to the scripts folder and still make the demo work? I want to make the main folder rather clean.

Thanks for your help, Ariel

On Wed, 30 Mar 2022 at 18:55, Chenxi @.***> wrote:

Hey @ariel415el https://github.com/ariel415el ! 👋

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 https://github.com/replicate/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.com/ariel415el/gpdm. The docker file can be found under the tab ‘run model with docker’. We have implemented style transfer, it support webcam input too!

Do claim the page so you can own the page, customise the Example gallery as you like, add other functionalities/push any future update to the web demo, and we'll feature it on our website and tweet about it too. You can find the 'Claim this model' button on the top of the page ~

In case you're wondering who I am, I'm from Replicate https://replicate.com/home, 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. 😊

You can view, comment on, or merge this pull request online at:

https://github.com/ariel415el/GPDM/pull/1 Commit Summary

File Changes

(3 files https://github.com/ariel415el/GPDM/pull/1/files)

Patch Links:

— Reply to this email directly, view it on GitHub https://github.com/ariel415el/GPDM/pull/1, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHY2J3GFKMU6KWPIE5D5TZDVCR2PXANCNFSM5SCM3MWQ . You are receiving this because you were mentioned.Message ID: @.***>

chenxwh commented 2 years ago

Hi @ariel415el :),

Yes merging will include the changes in the main branch! Sure I moved the predict.py to script folder, but cog.yaml would need to be in the root directory. The pull request is updated now!