Skip to main content

SpaghettiVision

SpaghettiVision is a machine learning algorithm that we trained to look for spaghetti. If your print looks like spaghetti, that's probably not good.

You'll get an email alert, and if the spaghetti continues, SpaghettiVision will automatically pause your print for you, saving filament and avoiding a huge mess.

Spaghetti detected visual

Caution

SpaghettiVision detects and responds to failed prints, but it is not a replacement for a fire-safety system. Be smart. Take appropriate precautions, and don't leave 3D printers unattended.

SpaghettiVision Overview

SpaghettiVision requires no plugins or additional installation. It is bundled with ClickPrint3D, AutoPrint3D, and AutoFarm3D.

SpaghettiVision runs 24/7, and we do not charge any additional fees for this service. You can use SpaghettiVision 24/7, 365 days of the year, for all of your 3D printers, for no extra cost!

QuinlyVision vs. SpaghettiVision

SpaghettiVision is a small part of a larger project which we call QuinlyVision. QuinlyVision is a failure detection system that can identify 14 different types of 3D print fails based on webcam data and respond accordingly to each one. Since it is a much larger project, we currently have only enabled the spaghetti detection algorithm, and have named it SpaghettiVision.

Quinlyvision demo

Start Using SpaghettiVision

All you need to do is plug in a webcam to your Pi / Hub! SpaghettiVision is enabled by default, and will run on all of your prints unless you disable it.

Spaghetti vision overview

To see what SpaghettiVision sees, click "Open AI View" and there will be a red box around anything detected as spaghetti.

Ai view example

Sensitivity

Use the sensitivity slider to adjust how easy it is to trigger an alert.

  • 10 is very high sensitivity, it will trigger more often, and very quickly after spaghetti appears, but there will be more false-positives.
  • 1 is very low sensitivity, it will trigger less often, and might miss obvious spaghetti sometimes.
  • Usually, it's best to stay somewhere in the middle, although you should experiment to find the setting that works best with your setup.

False Positives

Machine learning algorithms cannot be 100% accurate or reliable. You might occasionally get an alert when your print is fine. This is called a 'false-positive' and it means SpaghettiVision thought your print has failed when it hasn't.

If your 3D printer looks like this, then you can't really blame SpaghettiVision for getting it wrong...

False positive example

There are ways to reduce the risk of a false positive. Set SpaghettiVision up for success by following the recommendations in the Webcam Setup Guide.