I wanted to start developing a project with image recognition. I want to know the difference between the Intel Movidius Neural Compute Stick and TensorFlow to develop this project Any help would greatly be appreciated. What is the difference between them and what is better for accuracy? Thanks, Aditya

  • 1
    $\begingroup$ Welcome to AI and good luck with your project! I've taken the liberty of adding a couple of tag I thought relevant. $\endgroup$ – DukeZhou Mar 22 '18 at 19:44
  • $\begingroup$ Tensorflow can run on the Intel Neural Compute Stick. Your question is analogous to asking 'what is the different between an Intel i7 CPU and Python?'. $\endgroup$ – Brian O'Donnell Mar 25 '18 at 21:03

The Intel Movidius Stick is an USB stick for running a neural networks (that are programmed in Tensor Flow) on resource scare devices such as a Raspberry Pi (in order to reduce the traffic by sending data to cloud service or a server with more capacity where your neural network runs).

Tensor Flow is a programming framework which can be used as python library for the implementation of neural networks.

You are comparing an execution environment with an implementation language. The accuracy should not depend on them, instead I would considering on your model architecture (type of cnn) and your training as the most influential factors on accuracy of your test data.

| 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.