frame

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Sign In

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Survey: Feedback and Improvements

Please feel free to add any comments by replying to this thread.

What improvements would be most helpful to you?
  1. Would you like to see a YouTube tutorial?16 votes
    1. Yes
      68.75%
    2. No
      31.25%
  2. Would you like to see more documentation? Please specify in comment section.16 votes
    1. Yes
      87.50%
    2. No
      12.50%
  3. Does the current documentation need improvements? Please specify in comment section.16 votes
    1. Yes
      87.50%
    2. No
      12.50%
  4. Would you like to see better Caffe support?16 votes
    1. Yes
      62.50%
    2. No
      37.50%
  5. Would you like to see better TensorFlow support?16 votes
    1. Yes
      87.50%
    2. No
      12.50%
  6. Would you like to see more layer/operation support? Please specify in comment section.16 votes
    1. Yes
      100.00%
    2. No
        0.00%
  7. Does the Neural Compute SDK need improvements? Please specify in comment section.16 votes
    1. Yes
      93.75%
    2. No
        6.25%
  8. Does the installation process need improvement? Please specify in comment section.16 votes
    1. Yes
      81.25%
    2. No
      18.75%
  9. What programming language would you like to see more examples in?16 votes
    1. C++
      56.25%
    2. C
        0.00%
    3. Python
      43.75%
  10. Would you like to see more examples using other networks? Please specify in comment section.16 votes
    1. Yes
      93.75%
    2. No
        6.25%
  11. Would you like to see more written tutorials? Please specify in comment section.16 votes
    1. Yes
      81.25%
    2. No
      18.75%
  12. Would you like to see more RPi examples/articles?16 votes
    1. Yes
      56.25%
    2. No
      43.75%

Comments

  • 14 Comments sorted by Votes Date Added
  • Api corresponding to distributed processing to multiple sticks is necessary, not cyclic processing.

  • Support for Tensorflow mobilenet SSD. The blog posts at movidius.github.io are quite good - additional topics by the same authors would be helpful.

  • I hope to see support for Mask R-CNN very soon.

  • @GoldenWings Thanks for the input. Any other suggestions or features you guys would want to see?

  • Would like to see support for squeezenet and Tensorflow mobilenet SSD object detection.

  • I would in general like to see more support for different tensorflow ops. This would enable greater freedom in design of networks which would be really cool. :) Also more tutorials for maybe custom Networks. :)

  • Tutorials on getting new networks not already in the ncappzoo working on the sticks. Like DSOD - Densely Supervised Object Detectors. MobileNets-SSD is slow to train on Caffe. (and will remain until they start supporting an efficient Depthwise Separable Layer, in Caffe-SSD)

  • @trevor you should be able to use this link for training SSD with efficient DWS convolution with CUDNN9: https://github.com/listenlink/caffe/tree/ssd

  • Please support Keras. I have everything setup with Keras in Ubuntu. I do not see particular reason to add Caffe in my system other than Movidius stick. Untill then example graph files that can be deployed in RPi would be appreciated.

  • How to use retrain.py and your own classifications, mnvcompile and use it on the stick.

  • edited July 31 Vote Up0Vote Down
    1. Yolo support in all flavors ( not just tiny .. I prefer correct classification above fast&wrong )
      I would like to try Yolo v2 and v3...
    2. tested and forgiving installation script ( It's not fun to install NCSDK2 under Ubuntu studio/Mate 16.04/18.04 )
    3. Update all samples from appzoo to run under version 2
    4. Movidius "under the hood", low level api ?

    Release date for Movidius X ??? ( this year !? )

  • It would be great if the stick will support Pytorch in the future

  • 1) NCS kit in general is messy and loaded with Python dependencies. Straight C/C++ solutions would be best and a little python maybe for conversion / support.
    2) install.sh just fails in so many ways on a vanilla clean install Ubuntu 16.04 - like it was never really tested.
    3) find a way to enable a broader support community by open sourcing more tools (e.g. myriad compilers) and selecting a few outside partners to support smaller hobbyist / maker types.
    4) get a partner program going - important to all of the above items

  • 1 request is MobileNet SSD for TensorFlow.

    It would also be nice for better Raspberry Pi / TinkerBoard support during installation and compilation.

Sign In or Register to comment.