https://github.com/redhat-na-ssa/flyingthings
Computer vision demo
https://github.com/redhat-na-ssa/flyingthings
ai artificial-intelligence computer-vision data-science openshift tekton yolo yolov5
Last synced: 3 months ago
JSON representation
Computer vision demo
- Host: GitHub
- URL: https://github.com/redhat-na-ssa/flyingthings
- Owner: redhat-na-ssa
- Created: 2023-06-26T23:35:57.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-11T17:55:20.000Z (3 months ago)
- Last Synced: 2024-11-11T18:38:14.569Z (3 months ago)
- Topics: ai, artificial-intelligence, computer-vision, data-science, openshift, tekton, yolo, yolov5
- Language: Shell
- Homepage:
- Size: 69.9 MB
- Stars: 23
- Watchers: 1
- Forks: 19
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Computer Vision Demo / Workshop
[](https://github.com/redhat-na-ssa/flyingthings/actions/workflows/linting.yaml)
This demo / [workshop](docs/WORKSHOP.md) is designed to showcase OpenShift as a platform for developing and operationalizing AI/ML applications.
Specifically it focuses on a computer vision implementation and covers a workflow for custom training and serving for integration with other applications and services. It uses many tools in the Red Hat ecosystem as well as 3rd party applications and services.
Here is a video series explaining the [workshop](docs/WORKSHOP.md) and a runthrough of the setup and use cases.
[](https://youtu.be/agL8PrEPFR8?si=AL0G352nzrH2mfjP)
## Prerequisites
CLI tools
- `bash`, `git`
- `oc` - Download [mac](https://formulae.brew.sh/formula/openshift-cli), [linux](https://mirror.openshift.com/pub/openshift-v4/clients/ocp), [windows](https://mirror.openshift.com/pub/openshift-v4/clients/ocp/stable/openshift-client-windows.zip)
Infrastructure
- OpenShift 4.12+
- role: `cluster-admin`
- Nvidia GPU hardware
- Internet access
Optional
- OpenShift Dev Spaces 3.8.0+
- AWS (auto scaling)
[Red Hat Demo Platform](https://demo.redhat.com) Options (Tested)
- AWS with OpenShift Open Environment
- 1 x Control Plane - `m5.4xlarge`
- 1 x Workers - `m5.2xlarge`
- One Node OpenShift
- 1 x Control Plane - `m5.4xlarge`
- MLOps Demo: Data Science & Edge Practice
## Quickstart
You can use [OpenShift Dev Spaces for AI / ML](https://github.com/redhat-na-ssa/demo-ai-devspaces) or your local machine to explore this demo.
```sh
# cluster tasks
scripts/bootstrap.sh
```
```sh
# namespace only tasks
oc new-project let-me-fly-away
oc apply -k gitops/user-components
# create a new pipeline run
oc create -f components/pipelines/manifests/pipeline-run.yaml
```
## Workshop Instructions
See [docs/WORKSHOP.md](docs/WORKSHOP.md)
## Additional Resources
- [OpenShift Dev Spaces for AI / ML](https://github.com/redhat-na-ssa/demo-ai-devspaces)