diff options
| author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2018-09-13 16:22:01 +0100 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:55:45 +0000 |
| commit | ed5a492ba791d8c8b3334749d4ae946b8f11d13d (patch) | |
| tree | 89c8cd6f705dc88a21c61668164aad079800aff7 /tests/validation/fixtures/ConvolutionLayerFixture.h | |
| parent | 7e9391bb14d219cda310bff355669b5964b1f576 (diff) | |
| download | ComputeLibrary-ed5a492ba791d8c8b3334749d4ae946b8f11d13d.tar.gz | |
COMPMID-1586: Add support for NHWC CLDeconvolutionLayer
COMPMID-1651: Fix QASYMM8 CLDeconvolutionLayer
This patch also extends the range of values used for testing Convolution and
Deconvolution to cover quantized [-1.0f, 1.0f].
Change-Id: I8b280669db67bb3ec25bf5d411c8f5954f5b0dab
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149869
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
Diffstat (limited to 'tests/validation/fixtures/ConvolutionLayerFixture.h')
| -rw-r--r-- | tests/validation/fixtures/ConvolutionLayerFixture.h | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/tests/validation/fixtures/ConvolutionLayerFixture.h b/tests/validation/fixtures/ConvolutionLayerFixture.h index 3b420eac09..795b9de6cd 100644 --- a/tests/validation/fixtures/ConvolutionLayerFixture.h +++ b/tests/validation/fixtures/ConvolutionLayerFixture.h @@ -77,7 +77,8 @@ protected: { case DataType::QASYMM8: { - std::uniform_int_distribution<uint8_t> distribution(0, 3); + std::pair<int, int> bounds = get_quantized_bounds(tensor.quantization_info(), -1.0f, 1.0f); + std::uniform_int_distribution<uint8_t> distribution(bounds.first, bounds.second); library->fill(tensor, distribution, i); break; } |