Simple object detection app with streamlit. Upload an image and perform object detection. Adjust the confidence threshold to see how this affects predictions.
From the root dir:
docker build -t robmarkcole/object-detection-app .
docker run -p 8501:8501 robmarkcole/object-detection-app:latest
Then visit localhost:8501
Using devcontainer, see basic python example repo and more advanced repo. Use this streamlit docker template. Note you cannot docker run at the same time as the devcontainer as the ports clash.
I took a lot of inspiration from this article by Adrian Rosebrock.