diff options
author | Finn Williams <Finn.Williams@arm.com> | 2021-06-29 15:50:08 +0100 |
---|---|---|
committer | finn.williams <finn.williams@arm.com> | 2021-07-21 18:44:56 +0000 |
commit | b49ed18ac76cbab23201598f08972cfed19cce4c (patch) | |
tree | b100d19df7fdbfe009b2b8bf8048494bdab82a1a /src/armnnTfLiteParser/test/InputOutputTensorNames.cpp | |
parent | 9542f90d82a42096166d72109683abc165072297 (diff) | |
download | armnn-b49ed18ac76cbab23201598f08972cfed19cce4c.tar.gz |
IVGCVSW-6176 Add support for shape_signature in the tflite parser
* tflite shape_signatures will now be the preferred way to detect dynamic tensors
* add test utility to the parser that converts a model's tensors to dynamic
* by default tests will run a dynamic version of the model in addition to the original
* fix dynamic shape inference of unpack operator
* reactivate and fix quantize test
* add shape inference to expand dims
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: If11ba19d813cd3590707583dff1e4eb0e6412a1d
Diffstat (limited to 'src/armnnTfLiteParser/test/InputOutputTensorNames.cpp')
-rw-r--r-- | src/armnnTfLiteParser/test/InputOutputTensorNames.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/armnnTfLiteParser/test/InputOutputTensorNames.cpp b/src/armnnTfLiteParser/test/InputOutputTensorNames.cpp index 97d9381413..f090d39f0b 100644 --- a/src/armnnTfLiteParser/test/InputOutputTensorNames.cpp +++ b/src/armnnTfLiteParser/test/InputOutputTensorNames.cpp @@ -1,5 +1,5 @@ // -// Copyright © 2017 Arm Ltd. All rights reserved. +// Copyright © 2017 Arm Ltd and Contributors. All rights reserved. // SPDX-License-Identifier: MIT // @@ -22,7 +22,7 @@ struct EmptyNetworkFixture : public ParserFlatbuffersFixture TEST_CASE_FIXTURE(EmptyNetworkFixture, "EmptyNetworkHasNoInputsAndOutputs") { - Setup(); + Setup(false); CHECK(m_Parser->GetSubgraphCount() == 1); CHECK(m_Parser->GetSubgraphInputTensorNames(0).size() == 0); CHECK(m_Parser->GetSubgraphOutputTensorNames(0).size() == 0); |