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 2020/07/03 12:31:07 UTC

[GitHub] [incubator-tvm] chrschinab commented on pull request #5363: [Topi, ARM] Disbale Winograd for quantized tensors.

chrschinab commented on pull request #5363:
URL: https://github.com/apache/incubator-tvm/pull/5363#issuecomment-653525662


   I currently face the issue that Winograd implementation for quantized int8 operators destroys accuracy (see my [topic](https://discuss.tvm.ai/t/tvm-auto-tuning-winograd-conv2d-implementation-for-int8-gives-wrong-classification-results/7182) on discuss.tvm.ai) as described above.
   
   Is the functionality to disable Winograd for quantized operators already implemented? How to do that?


----------------------------------------------------------------
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