Skip to content
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

[Bug] Segmentation fault initializing model #2695

Open
Dimfred opened this issue Sep 24, 2024 · 2 comments
Open

[Bug] Segmentation fault initializing model #2695

Dimfred opened this issue Sep 24, 2024 · 2 comments

Comments

@Dimfred
Copy link

Dimfred commented Sep 24, 2024

I am trying to load my model (the issue might be in the model itself). I think there is some bug here:
https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/micro_allocator.cc#L276

So it seems that the segfault is called by trying to get element 0 from zero_point. I printed src_quantiazation->zero_point()->size() and it is 0, hence probably the segfault.

Shouldn't there be a check making sure there exists a zero point before accessing it?

@rascani
Copy link
Contributor

rascani commented Sep 24, 2024

Yes, there is a check on line 269: https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/micro_allocator.cc#L269

Not sure how you could wind up there with that conditional.

@Dimfred
Copy link
Author

Dimfred commented Sep 25, 2024

Oh right, what the hell? I'll look deeper into it, but I am printing it and it is 0.

EDIT: I'll take it back was sitting too long in front of it, it's not 0. Still segfaulting there tho.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants