aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h
diff options
context:
space:
mode:
Diffstat (limited to 'arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h')
-rw-r--r--arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h18
1 files changed, 10 insertions, 8 deletions
diff --git a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h
index b1c730d9a7..3b7fc7b7dc 100644
--- a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h
+++ b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2018 ARM Limited.
+ * Copyright (c) 2018-2019 ARM Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -41,31 +41,33 @@ public:
*
* @param[in] input Source tensor. DataType supported: QASYMM8/F16/F32.
* @param[in] weights Weights tensor. A 3D tensor with dimensions [3, 3, IFM]. Data type supported: Same as @p input.
- * @param[in] biases (Optional) Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
+ * @param[in] biases Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
* Data type supported: Same as @p input.
* @param[out] output Destination tensor. Data type supported: Same as @p input.
* @param[in] conv_info Padding and stride information to use for the convolution.
* @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU for QASYMM8 supported.
+ * @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
*/
void configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier,
- ActivationLayerInfo act_info) override;
+ ActivationLayerInfo act_info, const Size2D &dilation) override;
/** Static function to check if given info will lead to a valid configuration of @ref CLDepthwiseConvolutionLayer3x3NCHWKernel
*
- * @param[in] input Source tensor. DataType supported: F16/F32/QASYMM8.
- * @param[in] weights Weights tensor. A 3D tensor with dimensions [3, 3, IFM]. Data type supported: Same as @p input.
- * @param[in] biases Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
+ * @param[in] input Source tensor info. DataType supported: F16/F32/QASYMM8.
+ * @param[in] weights Weights tensor info. A 3D tensor with dimensions [3, 3, IFM]. Data type supported: Same as @p input.
+ * @param[in] biases Biases tensor info. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
* Data type supported: Same as @p input.
* @param[in] output Destination tensor. Data type supported: Same as @p input.
* @param[in] conv_info Padding and stride information to use for the convolution.
- * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1.
+ * @param[in] depth_multiplier Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU are supported.
* @param[in] gpu_target (Optional) GPU target to validate the kernel for. Defaults to midgard.
+ * @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier,
- ActivationLayerInfo act_info = ActivationLayerInfo(), GPUTarget gpu_target = GPUTarget::MIDGARD);
+ ActivationLayerInfo act_info = ActivationLayerInfo(), GPUTarget gpu_target = GPUTarget::MIDGARD, const Size2D &dilation = Size2D(1U, 1U));
void run(const Window &window, cl::CommandQueue &queue) override;
BorderSize border_size() const override;