Deepstack object detection UI

I created a streamlit UI for exploring the predicitons of an object detection API called Deepstack (exposes Yolo V3). The user can upload an image and filter objects by class, confidence (%) and location in the image. These are actually configurable parameters for an application which is using Deepstack as an engine, so its useful to have an app to explore the effect of these parameters. As usual the app is running in a docker container, as is deepstack.
Cheers

5 Likes

You’re on :fire: @robmarkcole :slight_smile: !

1 Like

Seriously! Thanks so much for sharing all these examples for the community to learn from :+1:

1 Like

This is awesome. I can also be used to power self-driving-elephants, by the way! :stuck_out_tongue_winking_eye:

1 Like

I found an article by Vicki Boykis where she does something very similar to what I have done here, but takes it a step further and deploys to to ECS using Github actions, which is definitely something I want to learn more about (bye bye jenkins?)

@robmarkcole I found one more repository which tries to do something similar to what you have done. Have a look!

1 Like