Skip to main content
ACapo
ACapo
Associate II
March 15, 2019
Solved

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

  • March 15, 2019
  • 4 replies
  • 6620 views

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

This topic has been closed for replies.
Best answer by Romain LE DONGE

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

0690X00000883u0QAA.png

4 replies

fauvarque.daniel
fauvarque.daniel
ST Employee
March 15, 2019

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

​In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
ACapo
ACapoAuthor
Associate II
March 15, 2019

Dear @fauvarque.daniel​,

unfortunally I am using the 3.4.0.

Alessandro

Romain LE DONGE
Romain LE DONGEAnswer
Associate
March 15, 2019

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

0690X00000883u0QAA.png

ACapo
ACapoAuthor
Associate II
March 18, 2019

Dear Romain,

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

Best,

Alessandro

EShai
EShai
Associate
March 30, 2019

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

ACapo
ACapoAuthor
Associate II
April 1, 2019

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

Terms & ConditionsAccessibility statement