search

YoadTew / zero-shot-image-to-text

Implementation of Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic
262 stars 42 forks source link

Add Docker environment & web demo #1

Closed chenxwh closed 2 years ago

chenxwh commented 2 years ago

Hey @YoadTew ! 👋

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! We have implemented the captioning model at the moment. View it here: https://replicate.com/yoadtew/zero-shot-image-to-text

We noticed you have signed up for Replicate, so you can add examples and customise the Example gallery as you like and push any future update to the web demo.

YoadTew commented 2 years ago

Thanks @CJWBW it looks great!

YoadTew commented 2 years ago

@CJWBW Hey, I see the cog.yaml and predict.py files from this pull requests are empty, do you have the files you used to create the web-page demo? We want to add more parameters tuning to the web-page :)

chenxwh commented 2 years ago

@CJWBW Hey, I see the cog.yaml and predict.py files from this pull requests are empty, do you have the files you used to create the web-page demo? We want to add more parameters tuning to the web-page :)

hey @YoadTew I am so sorry, didn't realise those files were empty! I have opened a new PR with the added files. If you have any questions regarding pushing update to the wed demo, don't hesitate to write us! :)

YoadTew commented 2 years ago

@CJWBW No problem, thank you for uploading the files!