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

Method SetQuantizationScales

src/armnn/Tensor.cpp:456–459  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

454}
455
456void TensorInfo::SetQuantizationScales(const std::vector<float>& scales)
457{
458 m_Quantization.m_Scales = scales;
459}
460
461float TensorInfo::GetQuantizationScale() const
462{

Callers 4

GetTensorInfoForTfLiteTensorFunction · 0.80
GetTensorInfoForTfLiteOpaqueTensorFunction · 0.80
IsMultiAxesReduceSupportedFunction · 0.80
TensorTest.cppFile · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected