projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: d1ae3a6) | patch
IVGCVSW-2721 Quantize and Dequantize aren't quite right
authorFrancis Murtagh <francis.murtagh@arm.com>
Fri, 22 Feb 2019 16:35:13 +0000 (16:35 +0000)
committerFrancis Murtagh <francis.murtagh@arm.com>
Mon, 25 Feb 2019 09:46:01 +0000 (09:46 +0000)
commit0d0a78ebd60e058746ea161914b45709245d4e1b
tree0220a0e885a81dd33e3e770f9dc7c02091eb4159tree | snapshot
parentd1ae3a632af09cd065d983a51c40916e2202121dcommit | diff
IVGCVSW-2721 Quantize and Dequantize aren't quite right

 * Add check for infinity and negative infinity in quantize()
 * Add assert for NaN value in quantize and dequantize()
 * Add unit tests for infinity and negative infinity

Change-Id: Ie60e1e15b289ccbf99df4a3281f067b82cc9f9bf
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
include/armnn/TypesUtils.hpp diff | blob | history
src/armnn/test/QuantizerTest.cpp diff | blob | history
Domain: Machine Learning / ML Framework;