diff options
author | David Monahan <David.Monahan@arm.com> | 2021-11-01 10:16:37 +0000 |
---|---|---|
committer | David Monahan <david.monahan@arm.com> | 2021-11-01 16:32:24 +0000 |
commit | 2d9956162dd002a41f7fb4fa6753195d33524c7f (patch) | |
tree | 35b88472ff1bc5374c40365785c626cfb1ddec2c /tests/InferenceTest.inl | |
parent | 6b9eba2f785093747f04af245da0cec7aca3931c (diff) | |
download | armnn-2d9956162dd002a41f7fb4fa6753195d33524c7f.tar.gz |
IVGCVSW-6359 Added support for Float16 (Half) to Execute Network
* Allows the user to specify float16 as a datatype
* Does not contain support for float16 on the TfLiteDelegate via
ExecuteNetwork
Signed-off-by: David Monahan <David.Monahan@arm.com>
Change-Id: Icba56feedab32662e2cf671cc46ada899cf40c6c
Diffstat (limited to 'tests/InferenceTest.inl')
-rw-r--r-- | tests/InferenceTest.inl | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/tests/InferenceTest.inl b/tests/InferenceTest.inl index b6087c5e5a..94dbfe78b8 100644 --- a/tests/InferenceTest.inl +++ b/tests/InferenceTest.inl @@ -67,6 +67,14 @@ struct ClassifierResultProcessor }); } + void operator()(const std::vector<armnn::Half>& values) + { + SortPredictions(values, [](armnn::Half value) + { + return value; + }); + } + void operator()(const std::vector<int8_t>& values) { SortPredictions(values, [](int8_t value) |