YunKan-Trainer

YunKan-Trainer is an optional NVIDIA GPU sidecar container for YunKan that fine-tunes its on-device object-detection model using your own camera footage,…

  • AI
  • Home Automation
  • Productivity
  • Tools & Utilities
YunKan-Trainer is an optional NVIDIA GPU sidecar container for YunKan that fine-tunes its on-device object-detection model using your own camera footage, entirely on your local network. It is a separate, single-purpose container you install only when you want a detector more accurate for the specific people, vehicles, and packages in your lighting; it receives a labeled sample set from the main YunKan app over HTTP, retrains it with Ultralytics on your NVIDIA GPU, and returns the updated ONNX model, with no data leaving your LAN.

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.

37/100 Low

Maintained
58last commit 173 days ago
Popular
61 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data

Based on 3 of 4 factors.

Availability: platform listings confirmed today, links checked 26 days ago

GitHub stars
1
Open issues
0
Last commit
2026-06-01
Activity
stale

Checked 13 days ago - source: GitHub (mrtian2016/yunkan)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is not supported.

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

First-install notes

  • How to install Treat YunKan-Trainer as a companion to the main YunKan app: it requires an NVIDIA GPU, runs a small standalone HTTP API on port 28900, and is started and configured from the YunKan web admin rather than used on its own. source
  • Install Install YunKan first; add YunKan-Trainer only if you want to fine-tune detection with an NVIDIA GPU. source

Fetched 5 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Do I need YunKan-Trainer to run YunKan?

No. It is an optional, single-purpose GPU sidecar that runs alongside a main YunKan container rather than replacing it.

What port does YunKan-Trainer use?

It uses its own port 28900 so it does not collide with the main YunKan container.

How do I install YunKan-Trainer on Unraid?

You can find YunKan-Trainer for Unraid in Community Apps and install it from your server.

Does training data leave my local network?

No. The sidecar fine-tunes the on-device object-detection model on your camera footage entirely on your LAN.

Answers sourced from ca.unraid.net, github.com

Community

Collected 48 days ago - public community threads