diff options
| author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-07-03 13:34:52 +0100 |
|---|---|---|
| committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-07-07 15:25:46 +0000 |
| commit | f9b595adbdc3f6f51ffa2c1f2aa70d0262d0db2d (patch) | |
| tree | 382f3ab76355de2ed5114a5e4bfc7e8f7c0422f4 /arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h | |
| parent | 0cc50ed757f06f4f076e261cb7253dd67264dec6 (diff) | |
| download | ComputeLibrary-f9b595adbdc3f6f51ffa2c1f2aa70d0262d0db2d.tar.gz | |
COMPMID-3532: Align data type support between doxygen and implementation - NEON
Change-Id: I70662cfb43890873b706b3f22b348f5d8cdd63ca
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3506
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-by: Sheri Zhang <sheri.zhang@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h')
| -rw-r--r-- | arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h index e7da1006e0..8bff3ba431 100644 --- a/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h +++ b/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h @@ -64,21 +64,21 @@ public: /** Set the input and output tensors. * * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. - * Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/BFLOAT16/F16/F32. + * Data type supported: All. * @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. - * Data type supported: Same as @p weights, S32 if @p weights is QASYMM8/QASYMM8_SIGNED, FP32 if @p weights is BFLOAT16 - * @param[out] output Destination tensor. - * Data types supported: Same as @p weights, FP32 if @p weights is BFLOAT16 + * Data type supported: same as @p weights. + * @warning Appending biases to weights reshaped matrix is not supported for quantized asymmetric types. + * @param[out] output Destination tensor. Data types supported: same as @p weights. */ void configure(const ITensor *weights, const ITensor *biases, ITensor *output); /** Static function to check if given info will lead to a valid configuration of @ref NEConvolutionLayerReshapeWeights * * @param[in] weights Weights tensor info. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. - * Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/BFLOAT16/F16/F32. + * Data type supported: All. * @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. - * Data type supported: Same as @p weights, S32 if @p weights is QASYMM8/QASYMM8_SIGNED, FP32 if @p weights is BFLOAT16 - * @param[in] output Destination tensor. - * Data types supported: Same as @p weights FP32 if @p weights is BFLOAT16 + * Data type supported: same as @p weights. + * @warning Appending biases to weights reshaped matrix is not supported for quantized asymmetric types. + * @param[in] output Destination tensor. Data types supported: same as @p weights. * * @return an error status */ |