diff options
author | Mike Kelly <mike.kelly@arm.com> | 2022-05-16 23:10:42 +0100 |
---|---|---|
committer | TeresaARM <teresa.charlinreyes@arm.com> | 2022-05-18 14:19:19 +0000 |
commit | 80512b0e1e98cb6782f5526fc8308ae6a571cd59 (patch) | |
tree | bad2f314defadd4b340343d99b6e157b46622039 /delegate/include | |
parent | d0420cb62b71f9c015d2b0e889011899051e56c0 (diff) | |
download | armnn-80512b0e1e98cb6782f5526fc8308ae6a571cd59.tar.gz |
IVGCVSW-6929 Support for models with implicit expanded
dimensions
* Added allow-expanded-dims to TFLite parser and ArmNN delegate
* If true ArmNN will disregard dimensions with a size of 1 when
validating tensor shapes. Tensor sizes must still match.
* This allows us to support models where tensors have expanded
dimensions (i.e. extra dimensions with a size of 1).
* Fixed bug in Network where it assumed that only the first option
could be ShapeInferenceMethod.
* Fixed bug where m_ShapeInferenceMethod was lost when copying or
moving Graphs.
* Changed Delegate to pass "infer-output-shape", "allow-expanded-dims"
and other BackendOptions through to the Network during construction.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ibe7c5ae6597796fc9164cb07bd372bd7f8f8cacf
Diffstat (limited to 'delegate/include')
-rw-r--r-- | delegate/include/DelegateOptions.hpp | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/delegate/include/DelegateOptions.hpp b/delegate/include/DelegateOptions.hpp index 7f7eaa5bb9..d789ea7285 100644 --- a/delegate/include/DelegateOptions.hpp +++ b/delegate/include/DelegateOptions.hpp @@ -163,6 +163,17 @@ public: * Possible values: [filenameString] \n * Description: Serialize the optimized network to the file specified in "dot" format. * + * Option key: "infer-output-shape" \n + * Possible values: ["true"/"false"] \n + * Description: Infers output tensor shape from input tensor shape and validate where applicable. + * + * Option key: "allow-expanded-dims" \n + * Possible values: ["true"/"false"] \n + * Description: If true will disregard dimensions with a size of 1 when validating tensor shapes but tensor + * sizes must still match. \n + * This is an Experimental parameter that is incompatible with "infer-output-shape". \n + * This parameter may be removed in a later update. + * * @param[in] option_keys Delegate option names * @param[in] options_values Delegate option values * @param[in] num_options Number of delegate options |