diff options
| author | Mike Kelly <mike.kelly@arm.com> | 2023-01-03 16:29:44 +0000 |
|---|---|---|
| committer | mike.kelly <mike.kelly@arm.com> | 2023-01-05 11:48:13 +0000 |
| commit | 0506ef0a099f5ba564af5e110e6857a68f462080 (patch) | |
| tree | 2ff1a15e435c41916a7f93f14766456759dd20b1 /src/armnnTfLiteParser/test | |
| parent | 8b4a483e0e2fee508c23be2248ba0409789f1a74 (diff) | |
| download | armnn-0506ef0a099f5ba564af5e110e6857a68f462080.tar.gz | |
GitHub #543 Problem Parsing Mixed-Precision Model
* Fixed bug when converting Constants with Per-Axis Quantization
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ifbea23e60483746ec987da491dae96e74cb33af4
Diffstat (limited to 'src/armnnTfLiteParser/test')
| -rw-r--r-- | src/armnnTfLiteParser/test/Conv2D.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/armnnTfLiteParser/test/Conv2D.cpp b/src/armnnTfLiteParser/test/Conv2D.cpp index 45c4a43519..334c102344 100644 --- a/src/armnnTfLiteParser/test/Conv2D.cpp +++ b/src/armnnTfLiteParser/test/Conv2D.cpp @@ -673,7 +673,7 @@ struct Conv2FloatWithInt8WeightsAndBiasesFixture : Conv2DWithBiasesFixture "[ 1, 2, 2, 1 ]", // filterShape "[ 2,1, 0,6 ]", // filterData "[ 1 ]", // biasShape - "[ 10, 0, 0, 0 ]", // biasData + "[ 10 ]", // biasData "1", // stride w and h "NONE", // activation "1.0", // filterScale |