Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6404 Discussions

Segmentation fail on Raspberry Pi 3

idata
Employee
‎09-06-2018 03:00 AM
589 Views

Hi,

 

I am new to Movidius NCS.

 

As I followed the steps of this website ( https://goo.gl/kxC1L6) to build the Graph file from Keras, I encountered the segmentation failure when running inference on Raspberry Pi 3. Can anyone help me with the problem? Thank you.

 

I used NCSDK2 to compile the model.

 

The following are the files that I used to build and run for the NCS inference.

 

     

  1. Generating Keras Model:

     

    http://oz.nthu.edu.tw/~g9512535/problem/generate_model.py

    2.  

  2. Peel of the Keras shell and convert to Tensorflow model:

     

    http://oz.nthu.edu.tw/~g9512535/problem/peel_off_keras.py

    3.  

  3. Load data from MNIST data set for inference test:

     

    http://oz.nthu.edu.tw/~g9512535/problem/convert_to_numpy_array.py

    4.  

  4. Inference the number:

     

    http://oz.nthu.edu.tw/~g9512535/problem/ncs_inference.py

    5.  

0 Kudos

Link Copied

0 Replies
Reply

Community support is provided during standard business hours (Monday to Friday 7AM - 5PM PST). Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.