https://github.com/sam99dave/vqa-e2e
End to end deep learning app. Applying containerization & kubernetes to practice. Task is of token classification.
https://github.com/sam99dave/vqa-e2e
docker fastapi huggingface poetry pytest ruff streamlit
Last synced: about 2 months ago
JSON representation
End to end deep learning app. Applying containerization & kubernetes to practice. Task is of token classification.
- Host: GitHub
- URL: https://github.com/sam99dave/vqa-e2e
- Owner: sam99dave
- Created: 2023-12-21T18:04:47.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-12-23T11:36:22.000Z (over 2 years ago)
- Last Synced: 2025-01-20T21:56:09.643Z (over 1 year ago)
- Topics: docker, fastapi, huggingface, poetry, pytest, ruff, streamlit
- Language: Python
- Homepage:
- Size: 9.77 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# vqa-e2e
End to end visual question and answering application
## Docker Commands
Building docker
`docker build -t vqa-e2e .`
Running docker
`docker run -p 8501:8501 -p 8000:8000 vqa-e2e`
Running docker interactive, **//** is important to turn off GitBash's automatic path conversion
`docker run -it --rm vqa-e2e //bin/bash`
Streamlit App
> localhost:8501
FastAPI
> localhost:8000/docs
## Kubernetes
Save the Docker image locally
`docker save vqa-e2e:latest -o image.tar`
Use Minikube's docker daemon via minikube ssh to load the image.
This command will SSH into the Minikube VM and execute the docker load command to load the Docker image from the image.tar file.
`minikube ssh -- docker load -i image.tar`
Create a Kubernetes deployment using the loaded Docker image.
`kubectl apply -f deployment.yaml`