I am building a speech recognition application to be run on Raspberry Pi 3. I have developed a Tensorflow model for this purpose that I am able to run on Raspberry Pi through command line.

How do I make a call to this model from my application (both on Raspberry Pi)? Should I install and run Tensoflow Serving on Raspberry Pi to serve the model (I tried this and got an Exec format error on running tensorflow_model_server)?

I want both the model and my speech recognition application to run locally on Raspberry Pi to avoid any network delay.

  • Do you have tensorflow installed on your RPi? Which version of Raspbian are you running it on? – Seamus May 3 '18 at 15:55

Yes, you can use it for low-cost computational problems.

However, for large datasets it can take a long time to process. Use this for install and configure: Deep Learning on Pi: Install TensorFlow on Raspberry Pi 3

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.