tqchen commented on issue #8690:
URL: https://github.com/apache/tvm/issues/8690#issuecomment-896834320


   Trying to followup a bit on the issue. In this case most of the output of 
the conv2d becomes close to zero. We should look into the test-case generation. 
   
   Since approximating something that is super close to zero does not really 
test the functionality of the code.  We should perhaps changes the way the 
input weight/data are generated.


-- 
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.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


Reply via email to