lichun-wang opened a new issue #5629: URL: https://github.com/apache/incubator-tvm/issues/5629
Hi, I downloaded resnest from gluon and converted it to mxnet model(json + params). Then I used tvm auto tune to make the model faster on 1080ti. But after tuning , the model became too slow . mxnet model take 15ms to process a image, but after tuning, it will take 380ms, I don't find the reason. ---------------------------------------------------------------- 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]
