aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h
diff options
context:
space:
mode:
authorGeorgios Pinitas <georgios.pinitas@arm.com>2017-08-18 10:16:09 +0100
committerAnthony Barbier <anthony.barbier@arm.com>2018-11-02 16:35:24 +0000
commit409ee0a69799364797263d13dd95936c851bfe80 (patch)
tree297e396b46df7f8079173ba4ccd6f7fb2aad560d /arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h
parentd763cfbc972cded289a2402a6238416d371bdf33 (diff)
downloadComputeLibrary-409ee0a69799364797263d13dd95936c851bfe80.tar.gz
COMPMID-417: Add in-place support for batch-normalization.
Change-Id: I4b0c9348f3bc2addc198a76fadd1b583abf42b60 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/84434 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h')
-rw-r--r--arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h23
1 files changed, 13 insertions, 10 deletions
diff --git a/arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h b/arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h
index 6df7ae4fc7..add1dfbb8c 100644
--- a/arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h
+++ b/arm_compute/core/CL/kernels/CLBatchNormalizationLayerKernel.h
@@ -50,22 +50,25 @@ public:
/** Set the input and output tensors.
*
- * @param[in] input Source tensor. 3 lower dimensions represent a single input with dimensions [width, height, FM]. Data types supported: QS8/QS16/F32.
- * @param[out] output Destination tensor. Output will have the same number of dimensions as input. Data type supported: same as @p input
- * The rest are optional and used for representing batches.
- * @param[in] mean Mean values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as @p input
- * @param[in] var Variance values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as @p input
- * @param[in] gamma Gamma values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as @p input
- * @param[in] beta Beta values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as @p input
- * @param[in] epsilon Small value to avoid division with zero.
+ * @note If the output tensor is a nullptr, the batch normalization function will be performed in-place
+ *
+ * @param[in, out] input Source tensor. In case of @p output tensor = nullptr, this tensor will store the result.
+ * 3 lower dimensions represent a single input with dimensions [width, height, FM].
+ * The rest are optional and used for representing batches. Data types supported: QS8/QS16/F16/F32.
+ * @param[in] mean Mean values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as @p input
+ * @param[in] var Variance values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as @p input
+ * @param[in] gamma Gamma values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as @p input
+ * @param[in] beta Beta values tensor. 1 dimension with size equal to the feature maps [FM]. Data types supported: Same as @p input
+ * @param[in] epsilon Small value to avoid division with zero.
+ * @param[out] output Destination tensor. Output will have the same number of dimensions as input. Data type supported: same as @p input
*/
- void configure(const ICLTensor *input, ICLTensor *output, const ICLTensor *mean, const ICLTensor *var, const ICLTensor *beta, const ICLTensor *gamma, float epsilon);
+ void configure(ICLTensor *input, ICLTensor *output, const ICLTensor *mean, const ICLTensor *var, const ICLTensor *beta, const ICLTensor *gamma, float epsilon);
// Inherited methods overridden:
void run(const Window &window, cl::CommandQueue &queue) override;
private:
- const ICLTensor *_input;
+ ICLTensor *_input;
ICLTensor *_output;
const ICLTensor *_mean;
const ICLTensor *_var;