COMPMID-926 Add depth multiplier support to NEON/CL/GLES depthwise convolution
Change-Id: I03f32c62350e5ea43e77bb15fc5a832d83719e3b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/126657
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
diff --git a/arm_compute/core/utils/misc/ShapeCalculator.h b/arm_compute/core/utils/misc/ShapeCalculator.h
index 7d07d46..a0bc4ea 100644
--- a/arm_compute/core/utils/misc/ShapeCalculator.h
+++ b/arm_compute/core/utils/misc/ShapeCalculator.h
@@ -125,7 +125,7 @@
return shape_transposed;
}
-inline TensorShape compute_depthwise_convolution_shape(const ITensorInfo &input, const ITensorInfo &weights, PadStrideInfo conv_info)
+inline TensorShape compute_depthwise_convolution_shape(const ITensorInfo &input, const ITensorInfo &weights, PadStrideInfo conv_info, unsigned int depth_multiplier)
{
const TensorShape input_shape{ input.tensor_shape() };
const TensorShape weights_shape{ weights.tensor_shape() };
@@ -133,6 +133,7 @@
const DataLayout data_layout = input.data_layout();
const int width_idx = get_data_layout_dimension_index(data_layout, DataLayoutDimension::WIDTH);
const int height_idx = get_data_layout_dimension_index(data_layout, DataLayoutDimension::HEIGHT);
+ const int channel_idx = get_data_layout_dimension_index(data_layout, DataLayoutDimension::CHANNEL);
unsigned int output_width = 0;
unsigned int output_height = 0;
@@ -143,6 +144,7 @@
TensorShape output_shape{ input_shape };
output_shape.set(width_idx, output_width);
output_shape.set(height_idx, output_height);
+ output_shape.set(channel_idx, input_shape[channel_idx] * depth_multiplier);
return output_shape;
}