diff options
| author | Gunes Bayir <gunes.bayir@arm.com> | 2023-10-13 16:58:41 +0100 |
|---|---|---|
| committer | SiCong Li <sicong.li@arm.com> | 2023-10-31 11:08:15 +0000 |
| commit | 93a77cd48609277a3849269c4cea5bf4b1ceb76a (patch) | |
| tree | e0a454b1a3dd5c3998187ce397ba18848ec7ec12 /src/runtime/CL/functions/CLFFTConvolutionLayer.cpp | |
| parent | fde45d836cf753a94915ac42d8a13da7edc52221 (diff) | |
| download | ComputeLibrary-93a77cd48609277a3849269c4cea5bf4b1ceb76a.tar.gz | |
Use dynamic quantization in Convolution and Dilated Convolution tests
This patch calculates the output quantization info based on the inputs'
quantization information.
The previous approach was using the same quantization information for
input, weights and output.
This implementation does not cover the cases where we have fused
activation function.
Resolves: COMPMID-6482
Change-Id: I4a9d87cfef8ad18ef241d457d23f44c8519a1389
Signed-off-by: SiCong Li <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10541
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/CL/functions/CLFFTConvolutionLayer.cpp')
0 files changed, 0 insertions, 0 deletions