anijain2305 commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-583004126 Thanks for this PR. It will help reduce/remove those 1-off deviations. One request that I have is - While setting the rounding mode to TFLite in TFLite parser, it might be better to set it by adding an extra arg in `from_tflite` API. The main reason is that the lowering here might involve many more number of Relay ops, which might degrade performance. So, to enable TVM user to choose different accuracy-performance tradeoff points, we can add a new argument in the TF parser API, and then pass it along to the QNN ops. The default value of this arg can be tflite rounding. @FrozenGene Are you ok with this? @u99127 @mbarrett97 will also be interested in this. Also, I think we can have small PRs merged. And incrementally improve test coverage.
---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
