diff options
| author | Nikhil Raj <nikhil.raj@arm.com> | 2024-05-10 13:16:45 +0100 |
|---|---|---|
| committer | Nikhil Raj <nikhil.raj@arm.com> | 2024-05-13 11:25:36 +0100 |
| commit | 37be3457274d738aaa1d91d8f0effad9a984657d (patch) | |
| tree | f7e5b162a80fca78ebd3a8461edb645a2ae2accc /src | |
| parent | 2c2f3aa6fbdd50ab5157bfc40f9335337f14abac (diff) | |
| download | armnn-37be3457274d738aaa1d91d8f0effad9a984657d.tar.gz | |
IVGCVSW-8259 Reivew and update documentation related with operators for 24.05
* Debug layer supported data types updated
* Added deprecation notices in md files to functionalities that will be removed
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8673bdc2d596bfa4de751fc95dae010b195ad0b1
Diffstat (limited to 'src')
| -rw-r--r-- | src/armnnConverter/README.md | 2 | ||||
| -rw-r--r-- | src/backends/reference/RefWorkloadFactory.cpp | 2 |
2 files changed, 3 insertions, 1 deletions
diff --git a/src/armnnConverter/README.md b/src/armnnConverter/README.md index 6c8ab27458..a1f29d9fbe 100644 --- a/src/armnnConverter/README.md +++ b/src/armnnConverter/README.md @@ -1,5 +1,7 @@ # The ArmnnConverter +## Note: Arm NN will be dropping support for ArmnnConverter in 24.08. + The `ArmnnConverter` is a program for converting neural networks from other formats to Arm NN format. Currently the program supports models in Onnx and Tensorflow Lite FlatBuffers formats. Run the program with no arguments to see command-line help. diff --git a/src/backends/reference/RefWorkloadFactory.cpp b/src/backends/reference/RefWorkloadFactory.cpp index 086f8eea8d..76c18a4fd6 100644 --- a/src/backends/reference/RefWorkloadFactory.cpp +++ b/src/backends/reference/RefWorkloadFactory.cpp @@ -279,7 +279,7 @@ std::unique_ptr<IWorkload> RefWorkloadFactory::CreateWorkload(LayerType type, { return std::make_unique<RefDebugBooleanWorkload>(*debugQueueDescriptor, info); } - return MakeWorkload<RefDebugFloat32Workload, RefDebugQAsymmU8Workload>(*debugQueueDescriptor, info); + return MakeWorkload<RefDebugFloat32Workload, RefDebugQAsymmU8Workload>(*debugQueueDescriptor, info); } case LayerType::DepthToSpace: { |