UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

cancel
Showing results for 
Search instead for 
Did you mean: 
511 Views
Registered: ‎06-13-2018

How do different Convolutional Neural Network Models work with the same base dnn architecture in chaidnn?

https://github.com/Xilinx/CHaiDNN

 

In the above link, they have shown a demo in which whichever elf file that we run for, that neural network works.

But each of the neural network has a different architecture.

WHen we open the Vivado project for the above link, we see that it has just 4 layers defined, namely conv pool deconvl and gemv.

 

Does that mean that according to the elf, it sees the which CNN (caffe model and deplot protxt) is there and during the run time on the said board (ours zc102) according to the CNN in elf makes the netowork along with the input output file and the base 4 layers architecture

 

Or is there a general architecture which while running the elf for that file is configured and ran.

 

Thanks in Advance,

Kushal.

 

0 Kudos