diff options
| author | Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com> | 2019-11-04 14:42:08 +0000 |
|---|---|---|
| committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2019-11-14 16:25:06 +0000 |
| commit | 951b8a4c01de2810349b6f16cf9bbba7578484fa (patch) | |
| tree | 8b3ab1c04279da7be3afd6632a9894b6197c1e1b /arm_compute/core/utils/quantization/AsymmHelpers.h | |
| parent | cd4e9abf7a165f15ccd10ac4541365d4f8a6db19 (diff) | |
| download | ComputeLibrary-951b8a4c01de2810349b6f16cf9bbba7578484fa.tar.gz | |
COMPMID-2309 : CLConvolutionLayer: support QUANT8_SYMM_PER_CHANNEL filters
Change-Id: I16f6758b768ede404a064db057302ded706e1e8a
Signed-off-by: Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com>
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2215
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/utils/quantization/AsymmHelpers.h')
| -rw-r--r-- | arm_compute/core/utils/quantization/AsymmHelpers.h | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/arm_compute/core/utils/quantization/AsymmHelpers.h b/arm_compute/core/utils/quantization/AsymmHelpers.h index 6b6cb007e3..0bf6ff5c95 100644 --- a/arm_compute/core/utils/quantization/AsymmHelpers.h +++ b/arm_compute/core/utils/quantization/AsymmHelpers.h @@ -84,15 +84,21 @@ std::pair<int, int> get_min_max_values_from_quantized_data_type(DataType data_ty * per-channel, multipliers and shifts will end up being the same for each * channel. * - * @param[in] input Input tensor. - * @param[in] weights Weights tensor. - * @param[in] output Output tensor. + * @param[in] input Input tensor info. + * @param[in] weights Weights tensor info. + * @param[in] output Output tensor info. + * @param[in] idx_ofms Dimension index to get OFMs from the weights tensor. * @param[out] output_multipliers_ptr Pointer to the buffer where to store per-channel multipliers. * @param[out] output_shifts_ptr Pointer to the buffer where to store per-channel shifts. * * @return min and max values for the quantized data type */ -void compute_quantized_multipliers_and_shifts(const ITensor *input, const ITensor *weights, const ITensor *output, int32_t *output_multipliers_ptr, int32_t *output_shifts_ptr); +void compute_quantized_multipliers_and_shifts(const ITensorInfo *input, + const ITensorInfo *weights, + const ITensorInfo *output, + unsigned int idx_ofms, + int32_t *output_multipliers_ptr, + int32_t *output_shifts_ptr); } // namespace quantization } // namespace arm_compute #endif /* __ARM_COMPUTE_IO_FILE_HANDLER_H__ */ |