| commit | 7485d5a62685cb745ab50e970adb722cb71557ac | [log] [tgz] |
|---|---|---|
| author | Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com> | Wed Jul 04 09:34:00 2018 +0100 |
| committer | Anthony Barbier <anthony.barbier@arm.com> | Fri Nov 02 16:54:10 2018 +0000 |
| tree | ba01b99ca466c93edc9a3f8c1e34394ff84be060 | |
| parent | 014333d73883c3872e458cedda5ccef586a7ccd4 [diff] [blame] |
COMPMID-970 : Remove QS8 / QS16 support Removed fixed point related code. Change-Id: I487acf138dace3b0450e0d72ca7071eaec254566 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/137678 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
diff --git a/src/runtime/NEON/functions/NEDepthwiseConvolutionLayer.cpp b/src/runtime/NEON/functions/NEDepthwiseConvolutionLayer.cpp index 83c3e21..1d65dde 100644 --- a/src/runtime/NEON/functions/NEDepthwiseConvolutionLayer.cpp +++ b/src/runtime/NEON/functions/NEDepthwiseConvolutionLayer.cpp
@@ -88,7 +88,7 @@ } else { - // Allocate the intermediate accumulator tensor in case of fixed point input + // Allocate the intermediate accumulator tensor in case of quantized input if(_is_quantized) { _accumulator.allocator()->init(TensorInfo(output->info()->tensor_shape(), 1, DataType::S32));