Fully Connected Network

[idata]

Hi!

How was wondering if there is a way to make it run a very simple feed forward neural network with only dense layers.

Is there a possibility or I have to loose all hopes :)

Thx

[idata]

Hi @EscVM ,

Thanks for reaching out. Do you want to do this from scratch? If so making it from scratch should be possible, but I think it would be easier to re-train a network instead. In case you are interested in doing this on Caffe there is an NCSDK blog that goes through the re-training of a network. Find the blog here https://movidius.github.io/blog/deploying-custom-caffe-models/. Please let me know if you have any additional questions.Regards,@Luis_at_Intel

[idata]

Hi @Luis_at_Intel,

what I would like to do is to deploy on Movidius only a feed forward neural netwok without convolutional layers, but only simple plain dense layers.

V.M.

[idata]

@EscVM

What you are trying to do should be possible with the NCSDK and it should work, please let us know if you have any other questions.Regards,@Luis_at_Intel