Object Detection Demo Can Handle Multi-class?

[cowbaz]

I am successfully to deploy demo single person class. Then I have trained multi class model using training scripts provided and it can be verified itself, i.e. it can have fair mAP meaning the inferencing is going right. Then I compare the architecture of the demo STM pretrained mobilenet and it is sightly different from the mobilenet created by train.py. I have also tried to upload the .h5 file in AI development cloud for anaylsis of the model. It returns the following exception.

/*

stm32ai validate --model best_model.h5 --allocate-inputs --allocate-outputs --relocatable --compression none --optimization balanced --name network --workspace workspace --output output
Neural Network Tools for STM32 family v1.7.0 (stm.ai v8.1.0-19520)
E010(InvalidModelError): Couldn't load Keras model best_model.h5,
error: Exception encountered when calling layer "lambda_5" (type CustomLambda).

name 'gen_anchors' is not defined

Call arguments received by layer "lambda_5" (type CustomLambda):
• inputs=tf.Tensor(shape=(None, 32, 32, 32), dtype=float32)
• mask=None
• training=None
*/

As the network can be loaded to the board, except nothing can be detected. I am wondering anything else I should config or I need to deal with the model architecture?

Many thanks.

[MDUSTM]

Hello
We have indeed identified an issue with multiclass model deployment and we are investigating. We will come back to you very soon.

[MCHSTM]

Hello,
The issue was solved with the latest updates, the deployment should work now for multi class models.