FrozenGene commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-596171397 > > I doubt it is because of different LLVM version. > > Do you know the default llvm version in ci test? I can have a try locally. > > > In code `tvm.testing.assert_allclose(tflite_output[i], tvm_output[i], atol=1e-5, rtol=1e-5)` maybe too strict. You could change it to `atol=1e-3, rtol=1e-3` to see it is ok on your machine. > > I don't have a local numerical problem, instead I got segfault for this test locally, so let's make llvm version matched first? > > > Another thing: "Another way is we provide rounding args for qnn.add / qnn.mul / qnn.conconcate, because they use requantize in fact too, so they need rounding". On mobilenet v2 quantized model, we have `quantized add`, I am curious why we could get the same result without support of `quantized add`. > > Hmm, that's interesting... I'm sure requantize is invoked at runtime. CI's LLVM is LLVM 4.0. I think we should supply `quantized add` so that we avoid it is just a lucky.
---------------------------------------------------------------- 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
