Keras import "NOT IMPLEMENTED: Unsupported layer type: ReLU"

[ACapo]

Dear Community,

I am trying to import a standard Mobilenet Model from Keras.

Unfortunally I am getting this error during the load of the model inside cubemx.ai:

 [AI:Generator] Command ***/STM32Cube/Repository//Packs/STMicroelectronics/X-CUBE-AI/3.4.0/Utilities/windows/generatecode --auto -c C:/Users/ALESSA~1/AppData/Local/Temp/mxAI256000625112004454394714515898287/config.ai
  [AI:Generator] NOT IMPLEMENTED: Unsupported layer type: ReLU
  [AI:Generator] Python generation ended
  [AI:Generator] Invalid network

According to the user manual UM2526 (Page 46) https://www.st.com/resource/en/user_manual/dm00570145.pdf should be supported.

Activation: nonlinear activation layer, decoded also when part of Conv2D, DepthwiseConv2D, SeparableConv2D, or Dense. The following attributes are supported:

– nonlinearity: type of nonlinear activation; the following functions are supported: linear, relu, relu6, softmax, tanh, sigmoid, and hard_sigmoid.

Some of you has some insight about the problem?

Thanks,

Alessandro

[fauvarque.daniel]

Are you on the latest X-Cube-AI 3.4.0 or on 3.3.0 ? some layers implementation bugs have been fixed in X-Cube-AI 3.4.0.

Regards

Daniel

[ACapo]

Dear @fauvarque.daniel​,

unfortunally I am using the 3.4.0.

Alessandro

[Romain LE DONGE · Accepted solution]

Hi alessandro,

I found a solution to solve your problem.

I suppose that you have used the "ReLU" layer of Keras.

I propose you to replace this layer by this one : "Activation('relu')" which will be the relu function through a layer of type Activation

Romain

[ACapo]

Dear Romain,

thanks I think your solution could work! I will try it soon.

Best,

Alessandro

[EShai]

But what about the already trained models with the "ReLU" layer ? Will the CubeMX.AI be corrected for normal work with "ReLU" ?

[ACapo]

Here you can find a notebook I created to do such operation:

https://github.com/alessandrocapotondi/mobilenet_stmcube_ai/blob/master/keras_model/keras_mobilenet_stm_cubemx_ai.ipynb