DeepStack UI

DeepStack UI is a homelab web interface for the DeepStack computer vision API that lets users upload images for object detection and face recognition,…

  • AI
  • Home Automation
  • Other
  • Tools & Utilities
DeepStack UI is a homelab web interface for the DeepStack computer vision API that lets users upload images for object detection and face recognition, register known faces, and explore filtering parameters without writing API calls.

Platform availability

Available on 1 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

38/100 Low

Maintained
0GitHub repository is archived
Popular
43136 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
701 GB minimum RAM
Security check
85no serious findings, CI

Availability: platform listings confirmed today, links checked 49 days ago

GitHub stars
136
Open issues
13
Last commit
2022-07-05
Latest release
v0.10
License
GPL-3.0
Activity
stale

Checked 20 days ago - source: GitHub (robmarkcole/deepstack-ui)

Resources & Compatibility

Minimum requirements: 1 GB RAM. ARM (e.g. Raspberry Pi) is not supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Run the CPU or GPU setup script Before starting, open PowerShell (Windows' command window) and run the script that matches your machine: .\setup_docker_cpu.ps1 for CPU-only or .\setup_docker_gpu.ps1 for supported GPU hardware. If you skip the matching setup, DeepStack may not install correctly or may not use the hardware it is meant to run on. source
  • Set API and admin keys before start When launching DeepStack, set API-KEY (the password for normal vision requests) and ADMIN-KEY (the password for admin actions), and open a local port, for example -p 80:5000. If these keys are missing or wrong, requests fail with a 401 error (which means authentication failed), and if the port is not open you cannot reach the app in a browser. source
  • Keep your datastore volume safe Keep the Docker local volume (a saved folder kept separate from the container) mounted to /datastore and back it up, because it holds your custom models and face-recognition database. If you lose that volume, any custom models and trained face data are gone, and you would have to train or re-add them. source
  • Configure DeepStack connection Set the environment variables that point to your running DeepStack instance (host IP and API key) when deploying the Deepstack-UI container; the UI reads these at startup to connect to the backend. source
  • Run DeepStack Start a separate DeepStack instance with Docker, for example docker run -e VISION-DETECTION=True -p 80:5000 deepquestai/deepstack:latest, and note its IP address for the UI connection settings. source
  • Run DeepStack API Start DeepStack with docker run -e VISION-DETECTION=True -p 80:5000 deepquestai/deepstack:latest, then note its host IP for the UI. source

Fetched 29 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

How do I make Deepstack-UI use a custom DeepStack model?

Pass the model name in the DEEPSTACK_CUSTOM_MODEL environment variable when starting the container.

How do I lower the confidence threshold while testing?

Set DEEPSTACK_UI_DEBUG_MODE to True. This lowers the minimum confidence threshold to 1%.

What DeepStack data should be backed up when using the UI for faces and custom models?

Back up the Docker volume mounted at /datastore. It stores custom models and the face-recognition database.

Answers sourced from context7.com, github.com

Community

Collected 53 days ago - public community threads