From f01201abec0a102f6e7a517971f83fef1eaffd50 Mon Sep 17 00:00:00 2001 From: Giuseppe Rossini Date: Wed, 6 Nov 2019 14:57:49 +0000 Subject: COMPMID-2305: NEDepthwiseConvolution 3x3: support for QUANT8_PER_CHANNEL_SYMM Change-Id: I9a917cff6a089ce6ae16fb4e6066a4194e2e9487 Signed-off-by: Giuseppe Rossini Reviewed-on: https://review.mlplatform.org/c/2241 Tested-by: Arm Jenkins Reviewed-by: Michele Di Giorgio Comments-Addressed: Arm Jenkins Reviewed-by: Pablo Marquez --- src/core/NEON/kernels/convolution/depthwise/impl_base.hpp | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'src/core/NEON/kernels/convolution/depthwise/impl_base.hpp') diff --git a/src/core/NEON/kernels/convolution/depthwise/impl_base.hpp b/src/core/NEON/kernels/convolution/depthwise/impl_base.hpp index b102a24250..22231cf019 100644 --- a/src/core/NEON/kernels/convolution/depthwise/impl_base.hpp +++ b/src/core/NEON/kernels/convolution/depthwise/impl_base.hpp @@ -292,6 +292,7 @@ MEMBERFN(void)::run( // Parallelise over blocks of channels const auto start_channel = CHANNEL_BLOCK * start; const auto stop_channel = std::min(_n_channels, CHANNEL_BLOCK * stop); + const auto params_size_per_channel = this->get_packed_params_size()/_n_channels; // Compute top and bottom padding for input and output const int input_pad_top = _padding_top; @@ -325,7 +326,7 @@ MEMBERFN(void)::run( // Get the offset into the packed parameters const auto params_ptr = static_cast(_packed_parameters) + - start_channel*(sizeof(TIn)*KernelRows*KernelColumns + sizeof(TBias)); + start_channel*params_size_per_channel; // Process the row process_tile_row( -- cgit v1.2.1