Convert per channel fake quant attributes to type
authorFeng Liu <fengliuai@google.com>
Mon, 9 Sep 2019 21:57:29 +0000 (14:57 -0700)
committerA. Unique TensorFlower <gardener@tensorflow.org>
Mon, 9 Sep 2019 21:57:59 +0000 (14:57 -0700)
commit27d776fa6d04e3ca47c42f5b9a90413c7243c35a
tree768b80b031b26ce20d166c5a022812fea12814e3
parent893c86fff7efa87c8d81e6f6e7a200a0b3f7ece5
Convert per channel fake quant attributes to type

For per channel fake quant attributes, the returned type should be
UniformQuantizedPerAxisType. Currently, this method isn't under test because we
haven't added the quant_ConstFakeQuantPerAxis op and the convert method.

PiperOrigin-RevId: 268084017
mlir/include/mlir/Dialect/QuantOps/FakeQuantSupport.h
mlir/lib/Dialect/QuantOps/Utils/FakeQuantSupport.cpp