You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2019/11/08 08:27:33 UTC

[GitHub] [incubator-tvm] cbalint13 commented on issue #4276: [TOPI][CUDA] Fix Winograd Kernel Size Support

cbalint13 commented on issue #4276: [TOPI][CUDA] Fix Winograd Kernel Size Support
URL: https://github.com/apache/incubator-tvm/pull/4276#issuecomment-551433546
 
 
   > Thanks for the suggestion. The unit test has been added and I've confirmed the unit test covers the desire part.
   > 
   > One miner issue is that I have to adjust the error tolerance to 1e-3. Here are the max absolute differences by different shapes:
   > 
   > Kernel 3x3, Padding 1: ~1.6e-5
   > Kernel 3x3, Padding 0: ~5e-5
   > Kernel 7x7, Padding 2: ~1.6e-4
   > 
   > I assume this was caused by floating point error, because the reference numpy implementation is not based on Winograd algorithm but a normal conv2d. Please help confirm.
   
   @comaniac 
   * It is normal to have increased error when tile size are beyond (3x3) in case of winograd.
   
   

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services