-
Notifications
You must be signed in to change notification settings - Fork 23
This issue was moved to a discussion.
You can continue the conversation there. Go to discussion →
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Unable to load custom model on firmware 11 #160
Comments
Hi @Duckypu First, I'd recommend to make sure that you are using the correct Firmware version with the correct SDK version we test only for that: Do you have this issue also when you try the model provided in the example? For debugging, upload first your model in the camera and run on the device |
Hi @Corallo I did the prompt you mentioned
I got:
And then
I got:
In addition, I also tried to compare 'ssd_mobilenet_v2_coco_quant_postprocess.tflite" and "my_custom.tflite" in netron. ssd_mobilenet_v2_coco_quant_postprocess.tflite: Lastly, I'm happy to provide my unweighted model to you personally if you want. |
Thanks for the detailed report. This looks like a bug on our side. If you can't share publicly your model, the best is that you open a Ticket here: |
Thank you, I've already opened a Ticket (#02150437) If you have any problem attaching models, Please let me know. |
Hi @Duckypu Could you try to run again the larod-client command, like this: You can find the system log in the GUI going in System -> Logs -> View the system log |
Hi @Corallo I'm glad to receive your messages. I did the prompt you mentioned
I got:
and then check the GUI in System -> Logs -> View the system log I got:
In my opinion, I don't think the issue is related to memory. After all, in the OS 10 version, the model could be successfully loaded. Or is it the case that there is a default model running on the device after the OS 11 version? |
I have been trying your model on a P3265-LVE with 11.5 and 11.6, it works fine for me. The only thing I can reproduce is that warning message about OP32, even tho it doesn't result in a crash for me. |
Hi @Corallo After digging deep into this, I found a mistake on my end. My model is actually P3265-LV, not P3265-LVE. Now, I've managed to successfully load the model with version 11.5.64 and SDK 1.9 randomly. However, even after making sure I have the correct firmware version, I'm still facing problems loading the model in other versions:
Additionally, I'd be happy to share the conversion method with you privately. Can I send it to you through a private channel? |
Hi @Duckypu Yes, I actually tested on P3265-LV too, but the two device should be equivalent. What do you mean with "randomly"? It is not consistent/reproducible? |
Hi @Corallo |
@Duckypu |
Hi @Corallo, I am facing the same issue when I try to load my custom model as well. |
@ThenoobMario Please open a new discussion or issue and provide some more context :) |
Moving this issue into discussions, as for now it doesn't seem like a bug. |
This issue was moved to a discussion.
You can continue the conversation there. Go to discussion →
Description
Thank you for your attention. I've trained custom ssdlite_mobiledet model using the TensorFlow API. Following the efforts of previous work, I made changes to the Dockerfile.model and env.aarch64.artpec8 paths, and I was able to successfully run it in the following environment:
However, when I upgraded Axis firmware to version 11, I encountered the following issue during inference:
Issue environment
(also tried 11.2.68 vs 1.6, 11.4.63 vs 1.8, 11.5.64 vs 1.10)
Please help me, thanks in advance.
The text was updated successfully, but these errors were encountered: