masahi opened a new pull request #5089: [Torch, QNN] Add missing upcast to uint8 avg_pool conversion URL: https://github.com/apache/incubator-tvm/pull/5089 Previously we were missing an upcast to int32 for avg_pool2d, fixed now. It seems avg_pool is used in inception v3, but I don't know why our accuracy is not affected by the missing upcast. Beside the accuracy issue, without upcast it also causes a mysterious typing problem for inception v3 when compiling for AVX512. For AVX2 and other, there have been no issue. cc @anijain2305
---------------------------------------------------------------- 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
