FrozenGene commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-611306583 > Ok. I forgot the accuracy issue of Object detection models. > > I will also go through the blog to see if we can do something in the short term. If possible, we should make a plan for what all things that we need to do to get the performance speedup. I will share the results in a discussion post in few days. Maybe you can share your experience from there. Yeah. Because of the different design, my original plan is we could achieve the same result of TFLite, then we start to consider how to achieve better performance leveraging our previous implementation of `q_conv2d`. :-)
---------------------------------------------------------------- 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
