diff options
| author | Ioan-Cristian Szabo <ioan-cristian.szabo@arm.com> | 2017-11-30 17:17:17 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:47:40 +0000 |
| commit | b4e3e1c371d8091e86ee1c6e704057559bbe1554 (patch) | |
| tree | d072c9f9d7471e4df9ef5aa6b50cb09c35b0c361 /arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h | |
| parent | c1b6e37233e0ebd21cb44bf8863a09c0ba5feeb1 (diff) | |
| download | ComputeLibrary-b4e3e1c371d8091e86ee1c6e704057559bbe1554.tar.gz | |
COMPMID-617: Add validate support for NEON FullyConnectedLayer
Change-Id: I08987022c8d4cc335c00b8af27bd3edb8fe64d3b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111596
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Alexander Gilday <alexander.gilday@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h')
| -rw-r--r-- | arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h | 14 |
1 files changed, 8 insertions, 6 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h index c3c7f825a9..ac5f4caa78 100644 --- a/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h +++ b/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h @@ -141,12 +141,14 @@ public: private: /** Configures the appropriate matrix multiply routine * - * @param[in] input Input tensor. Data types supported: QS8/QASYMM8/QS16/F16/F32. - * @param[in] weights Weights tensor. Data type supported: Same as @p input. - * @param[out] output Output tensor. Data types supported: Same as @p input, - * except for input of QASYMM8 type where output should be of S32 type. + * @param[in] input Input tensor. Data types supported: QS8/QASYMM8/QS16/F16/F32. + * @param[in] weights Weights tensor. Data type supported: Same as @p input. + * @param[out] output Output tensor. Data types supported: Same as @p input, + * except for input of QASYMM8 type where output should be of S32 type. + * @param[in] is_interleaved (Optional) True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMTranspose1xWKernel + * @param[in] reshape_info (Optional) GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped */ - void configure_mm(const ITensor *input, const ITensor *weights, ITensor *output); + void configure_mm(const ITensor *input, const ITensor *weights, ITensor *output, bool is_interleaved, const GEMMReshapeInfo &reshape_info = GEMMReshapeInfo()); /** Prepare the appropriate assembly optimized kernel * * @param[in] ci CPU information @@ -178,7 +180,7 @@ private: bool _is_fully_connected_convolution; bool _are_weights_reshaped; bool _is_quantized; - bool _is_interleaved_transposed; + bool _is_interleaved; }; } #endif /* __ARM_COMPUTE_NECONVOLUTIONGEMMLAYER_H__ */ |