diff options
author | Matteo Martincigh <matteo.martincigh@arm.com> | 2018-12-06 12:03:17 +0000 |
---|---|---|
committer | Matteo Martincigh <matteo.martincigh@arm.com> | 2018-12-07 16:25:45 +0000 |
commit | f9afc791662f9ffd639a9500de8c4e33394c8c39 (patch) | |
tree | 26b3203c189f0a0f280e8fab4fd081f2d6112da3 /src/backends/neon/test/NeonTimerTest.cpp | |
parent | ba563c6d81bfb20f01b1b54e27fe1ac4a494ece1 (diff) | |
download | armnn-f9afc791662f9ffd639a9500de8c4e33394c8c39.tar.gz |
IVGCVSW-2268 Remove the input swizzling from ParseConcat
* Removed the input swizzling when the concatenation dimension is 3
in ParseConcat in the TF parser
* No longer using the helper ProcessConcatInputTensorInfo, where
the input was being swizzled if the concatenation dimension was 3
* Added a new convenience constuctor to TensorShape that initializes
a shape to all zeros given only the number of dimensions
Change-Id: I82a207e41bddc5fea21a0b5a38eafa24ad75d1c2
Diffstat (limited to 'src/backends/neon/test/NeonTimerTest.cpp')
0 files changed, 0 insertions, 0 deletions