graffitist icon indicating copy to clipboard operation
graffitist copied to clipboard
verified publisher icon Xilinx

depth_to_sparse operation supported?

Open linbaiwpi opened this issue 5 years ago • 0 comments

In my network, there is a depth_to_sparse operation, which contains no learn-able parameters. What I want is to skip this to do a quantization aware training with this layer NOT trained (skipped during back-propagation). Can I do retrain my model using Graffitist?

linbaiwpi avatar Feb 18 '20 20:02 linbaiwpi