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.
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!