Deploying Deep Learning model with Sequential Input as C++

Hey Guys,

Is there any way around to convert my deep neural network model with sequential input to C++ file which can run on normal computers and not special one like ARM.

I have already check te below mentioned link containing supporting layers and network for code generation and as it seems Sequential Input is not supported for Intel Processor. Is there any other way to deploy??

https://uk.mathworks.com/help/coder/ug/networks-and-layers-supported-for-c-code-generation.html

I have already check these links and nothig seems useful.

https://uk.mathworks.com/help/coder/deep-learning-with-matlab-coder.html

https://uk.mathworks.com/help/deeplearning/deep-learning-code-generation.html

Thanks in Advance.

Answer 1

[Hiro Yoshino]

We have just released 2020a and it looks sequential input layer is now included in the list.

So the solution is updating your MATLAB to the latest one. Hope this helps.

[Kiran Ashraf]

But it is only supported for ARM processors and not for Intel Processors.

[Hiro Yoshino]

oops, sorry. You're right. It's on the list but no for Intel cpu.

In 2019b, that layer was not available. Hopefully it will come in 6 months time!?

I'm sorry for that.