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

Face-detect with different kmodel #9

Open
macsimo opened this issue May 5, 2020 · 0 comments
Open

Face-detect with different kmodel #9

macsimo opened this issue May 5, 2020 · 0 comments

Comments

@macsimo
Copy link

macsimo commented May 5, 2020

Hello,

I am trying to run the face-detect application, present in the kendryte/kendryte-freertos-demo repository, with a different kmodel but no one, except the existing kmodel, seams to work properly. All models are correctly loaded but than the function kpu_run() never returns.

The kmodel that I am using is a very simple model with a single convolutional layer with padding (32x32x1 input -> 32x32x1 output). The model has been generated using the Kendryte ncc tool present in the kendryte/nncase repository.

I can also confirm that the model works perfectly using the KPU functions of the kendryte/tensorflow-workshop repository.

Do you have any suggestion?

I am using a Sipeed MAix BiT board with Kendryte K210.

Thank you very much!

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

1 participant