You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello I trained a two class yolov8n model using Ultralytics version 8.2.93
Then I tried to use the conversion tool to export my model as a blob to use it on my device. However when the tool is doing the conversion it shows and the following error message.
Then I used the old tool http://blobconverter.luxonis.com/, which converted my model as a blob. However, when I tried to use my converted file with the YOLO node in my pipeline I got the following error
[DetectionNetwork(4)] [error] Mask is not defined for output layer with width '4620'. Define at pipeline build time using: 'setAnchorMasks' for 'side4620'.
Therefore I decided to use the NeuralNetwork node and decode the output by myself but when I do this I get the following error
Hello I trained a two class yolov8n model using
Ultralytics version 8.2.93
Then I tried to use the conversion tool to export my model as a blob to use it on my device. However when the tool is doing the conversion it shows and the following error message.
Then I used the old tool http://blobconverter.luxonis.com/, which converted my model as a blob. However, when I tried to use my converted file with the
YOLO
node in my pipeline I got the following error[DetectionNetwork(4)] [error] Mask is not defined for output layer with width '4620'. Define at pipeline build time using: 'setAnchorMasks' for 'side4620'.
Therefore I decided to use the NeuralNetwork node and decode the output by myself but when I do this I get the following error
[system] [critical] Fatal error. Please report to developers. Log: 'Fatal error on MSS CPU: trap: 00, address: 00000000' '0' Traceback (most recent call last):
I would like to ask what is the right approach to deploy my custom model into the device.
Thanks for your help
The text was updated successfully, but these errors were encountered: