FrozenGene commented on issue #5230: Adding support for TFLite QnnSubtract operator. URL: https://github.com/apache/incubator-tvm/pull/5230#issuecomment-611288745 > @FrozenGene It is not possible to use depthwise conv inside Relay here. The `groups=1` in this case and Relay code only considers a conv as depthwise when `groups > 1`. So, I don't think there are 2 choices here. Let us know if you are ok with this. Yes. Me meaning is before we decide to change or not, could we do one performance comparation so that we know depthwise with multiplier > 1 is good or becomes normal convolution is good.
---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services
