Can not deploy Model from Mind+ to Huskylens
Thomas.Rogenmoser 2024-12-03 08:26:31 467 Views2 Replies I try to train a model with Mind+ and use it on the Huskylens Pro.
I am following the example here
https://wiki.dfrobot.com/HUSKYLENS_PRO_SKU_SEN0336#target_6
I am able to connect Huskylens, i can use simple blocks like “show custom text” or “switch algorithm to …”
I can add images from a folder, start classification and deploy.
But the deploy fails after some percentage with the message cannot switch to the "object classification" algorithm
If i use less images, the progress bar runs faster and gets to a higher percentage before it fails.
But even down to only 2 images, it still fails at 99%
With 50 images, it fails at 14%.
In some cases i saw a different error, “Deploy Data” failed.
I tried smaller images, down to around 200x300px grayscale, 15kb.
Huskylens has the latest firmware.
Any ideas on what i am doing wrong?
Please check if you are missing something here:
https://wiki.dfrobot.com/HUSKYLENS_PRO_SKU_SEN0336
The issue might be related to the size or number of images in your dataset.
lia.ifat Thanks.
No, i think i did things as described in the wiki.
Yes, image size is what i also suspect, but as i describe above, there are only down to 2 images of tiny size…
So, what should be a non-problematic size and amount?
Is it normal to just fail with the described error, or should i not see a more specific error if it is related to the data size?
