MCPcopy Create free account
hub / github.com/ARM-software/armnn / SetQuantizationOffset

Method SetQuantizationOffset

src/armnn/Tensor.cpp:493–496  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

491}
492
493void TensorInfo::SetQuantizationOffset(int32_t offset)
494{
495 m_Quantization.m_Offset = MakeOptional<int32_t>(offset);
496}
497
498Optional<unsigned int> TensorInfo::GetQuantizationDim() const
499{

Callers 15

GetTensorInfoForTfLiteTensorFunction · 0.80
GetTensorInfoForTfLiteOpaqueTensorFunction · 0.80
SerializerTests.cppFile · 0.80
OneToManyMappingTests.cppFile · 0.80
ExecuteMethod · 0.80
RefEndToEndTests.cppFile · 0.80
RefCreateSoftmaxWorkloadTestFunction · 0.80
ClSoftmaxWorkloadTestFunction · 0.80
NeonCreateSoftmaxWorkloadTestFunction · 0.80
IsMultiAxesReduceSupportedFunction · 0.80
GatherEndToEndFunction · 0.80
GatherMultiDimEndToEndFunction · 0.80

Calls

no outgoing calls

Tested by 15

RefCreateSoftmaxWorkloadTestFunction · 0.64
ClSoftmaxWorkloadTestFunction · 0.64
NeonCreateSoftmaxWorkloadTestFunction · 0.64
GatherEndToEndFunction · 0.64
GatherMultiDimEndToEndFunction · 0.64
DetectionPostProcessEndToEndFunction · 0.64
FullyConnectedWithDynamicWeightsEndToEndFunction · 0.64
StridedSlice3DMaskedEndToEndTestFunction · 0.64
StridedSlice4DEndToEndTestFunction · 0.64
DequantizeEndToEndLayerTestImplFunction · 0.64
GetSoftmaxProfilerJsonFunction · 0.64
GatherNdEndToEndFunction · 0.64