aboutsummaryrefslogtreecommitdiff
path: root/delegate/include
diff options
context:
space:
mode:
authorRyan OShea <ryan.oshea3@arm.com>2023-03-07 11:44:23 +0000
committerryan.oshea3 <ryan.oshea3@arm.com>2023-03-22 13:12:55 +0000
commit238ecd9279f08a1b05189e03ffa73a9201b1c0ce (patch)
tree942386ab532039fb423ac951f375c484352faece /delegate/include
parent3ec3077b4eaedcc0c20ab5774bdbe365da541445 (diff)
downloadarmnn-238ecd9279f08a1b05189e03ffa73a9201b1c0ce.tar.gz
IVGCVSW-7526 Upgrade ArmNN to Tensorflow 2.12
When creating a flatbuffers model, we need to provide an empty buffer 0 that is reserved by tensorflow. When creating empty buffers for inputs and outputs we can not pass in an empty vector, or tflite will assume that we know how many bytes to allocate in advance. Instead we need to only pass in the builder. * Update libraries in FindTfLite.cmake * Add nullptr to delegate struct for OpaqueDelegateBuilder * Fix issue in unit tests where Flatbuffers model was not being parsed by tflite * Tensorflow 2.12 now includes C++ 17 features. Update our cmake build to require a compiler to support these features. * Change minimum cmake in Arm NN to 3.7 as that's the minimum for the delegate build. Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I7d15b196b8c59b1914f8fc1c4c2f8960630c069c
Diffstat (limited to 'delegate/include')
-rw-r--r--delegate/include/armnn_delegate.hpp1
1 files changed, 1 insertions, 0 deletions
diff --git a/delegate/include/armnn_delegate.hpp b/delegate/include/armnn_delegate.hpp
index 159d590423..9cfc397550 100644
--- a/delegate/include/armnn_delegate.hpp
+++ b/delegate/include/armnn_delegate.hpp
@@ -81,6 +81,7 @@ private:
nullptr, // .CopyToBufferHandle
nullptr, // .FreeBufferHandle
kTfLiteDelegateFlagsNone, // .flags
+ nullptr, // .opaque_delegate_builder
};
/// ArmNN Runtime pointer