How to deploy custom deep learning model in Raspberry Pi 4?

I have trained my deep learning model, saved and tested in MATLAB. Now I want to deploy that model in Raspberry Pi 4. The tutorials given have deployed pretrained models (like resnet50) and there are no tutorials for custom deep learning model.

Answer 1

[Ram Kokku]

Hi Paras,

We have many examples for deploying neural networks to various hardware. please take a look the examples below

https://www.mathworks.com/help/coder/ug/code-generation-for-deep-learning-networks-with-arm-compute-library.html

https://www.mathworks.com/help/rtw/ug/generate-generic-code-for-rul-from-simulink.html

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

Answer 2

[Sergio Matiz Romero]

Hi @Paras Dhekale,

There is also this code generation example for an LSTM network. Your custom pretrained network can be loaded in a similar way:

https://www.mathworks.com/help/coder/ug/code-generation-for-lstm-network-on-raspberry-pi.html

Answer 3

[Yazan]

Hi @Paras Dhekale;

I have the same problem; did you find a solution.

Can share your solution please?

Thank you!