I am wondering what is true. Does the detection work onboard or in the cloud?
On the wiki page for spaghetti
Thanks to the powerful on-chip NPU, we can achive onboard spaghetti detection just inside the printer.
[…]
To have the detector work properly, there are a few requirements.
The detector needs to be enabled in the Print Options. You can adjust the sensitivity from {low, medium, high}. If you are off the printer for a relatively long time (e.g. a whole night), you can set the sensitivity to low, so it’s less often to pause the printing for small defects.
The chamber light needs to be open. The spaghettic detector needs a good lighting condition to capture the details of prints. By default we open the light when the first layer starts to print. If the light is shutdown manually, it will not be open back.
No requirement for cloud connection listed in the requirement list.
But then on the wiki page for enabling LAN only mode:
When LAN Mode is enabled, the following features do not work:
[…]
AI Spaghetti Detection is not available (for X1 Series)
What’s the point of doing it local, if it depends on the cloud?
BambuLab, could you please explain why using LAN only mode disables the spaghetti detection?
If the detection is done local, it should work without cloud? It would be nice to be able to use this feature.
I suspect that Bambu is using there servers to process the camera image and detect spaghetti. When the machine runs in lan mode there is no computer to process the camera feed, hence no spaphetti detection. This process is too hardware intensive for the printer controller to handle.
If that’s the case, they would be lying on their wiki page. While I question some of their poor decisions, I don’t think they are lying like that.
From a technical view, it’s possible to run a detection like this on small hardware, obviously training has to be done with powerful hardware, but deploying is no problem nowadays, especially if it’s a chip designed for AI, like the one used in Carbon printers.
This is why I don’t understand it, why does the feature depend on their cloud?
Might be just due to notifications of failures, or just something they haven’t got round to doing yet in the lan only branch within their firmware.
Does octoprint do spagetti detection locally to the raspberry pi?
I guess one way to test would be to run a known spaghetti print on connected mode and arrange for the connection to be lost - by turning off router for example - then seeing if spaghetti is still detected ok by the x1c.
Yes image detection can be done on a Pi but don’t forget that the control board also has to run the printer without interruption while processing which can be difficult. We also don’t know how intense of image detection they are doing. They may very well be doing all of the processing on board but it would make sense to me to try to off load it.
An official statement, about why the supposed local spaghetti detection depends on the cloud connection, is needed, but it’s been a week without response.
@BambuLab@BrotherC@SirWill@Chloe@rocky.chen please someone explain this.
I think it is customer deception to promise local spaghetti detection without listing cloud connection as requirement, but deliver one that depends on the cloud.
I apologize for the delay in replying. I did not see this topic before.
I believe that our Wiki article is not clear and doesn’t contain the right information.
The X1 series has the capability to detect failures/spaghetti based on the processing power it has. This system uses a machine-learning algorithm and all the data processing is done locally.
When the printer is used in LAN mode, the printer behaves just like when it is not connected to the internet and uses local processing to provide this feature.
If the printer is not connected to the cloud, and the user improvement option is not enabled, the printer will rely only on the information it has in the latest firmware for failure detection, which might be outdated compared to the cloud-connected experience where the AI model is updated regularly.
We will update the Wiki to provide more information on this topic, to make it clearer
If there are any questions on this topic, please let us know and we will help
Thank you for this explanation; it addresses all the questions I had.
So, based on this information, the spaghetti detection does indeed work with LAN-only mode, and it turns out that the wiki article for LAN-only mode contains incorrect information. In this case, that’s good news.
