projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 1f82696) | patch
IVGCVSW-4008 Add profiling mode to ExecuteNetwork
authorAron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Thu, 24 Oct 2019 16:07:43 +0000 (17:07 +0100)
committerMatteo Martincigh <matteo.martincigh@arm.com>
Fri, 25 Oct 2019 14:51:29 +0000 (14:51 +0000)
commitc82c8732fb514b412012002bd951a84039eca696
tree3f332d585fd86ff45ba514eb069be7fe26a2004atree | snapshot
parent1f826967da321f87b192bd1c29152b0f1fc51ed8commit | diff
IVGCVSW-4008 Add profiling mode to ExecuteNetwork

* Removed the requirement for specifying a data file for each
  input tensor
* Added the possibility to generate dummy tensor data (filled
  with 0s) if no data files are specified by the user
* Warn the user when they request to save the output to a file,
  but the input was generate, therefore rendering the output
  useless

Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I8baed116dcd99fe380e419db322dc7e04ab1c653
tests/ExecuteNetwork/ExecuteNetwork.cpp diff | blob | history
tests/InferenceModel.hpp diff | blob | history
tests/NetworkExecutionUtils/NetworkExecutionUtils.hpp diff | blob | history
Domain: Machine Learning / ML Framework;