MCPcopy Create free account
hub / github.com/ARM-software/ComputeLibrary / configure

Method configure

src/runtime/CL/functions/CLGEMMConvolutionLayer.cpp:72–84  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

70CLGEMMConvolutionLayer::~CLGEMMConvolutionLayer() = default;
71
72void CLGEMMConvolutionLayer::configure(const ICLTensor *input,
73 const ICLTensor *weights,
74 const ICLTensor *biases,
75 ICLTensor *output,
76 const PadStrideInfo &conv_info,
77 const WeightsInfo &weights_info,
78 const Size2D &dilation,
79 const ActivationLayerInfo &act_info,
80 unsigned int num_groups)
81{
82 configure(CLKernelLibrary::get().get_compile_context(), input, weights, biases, output, conv_info, weights_info,
83 dilation, act_info, num_groups);
84}
85
86void CLGEMMConvolutionLayer::configure(const CLCompileContext &compile_context,
87 const ICLTensor *input,

Callers

nothing calls this directly

Calls 3

Conv2dInfoClass · 0.50
infoMethod · 0.45
workspaceMethod · 0.45

Tested by

no test coverage detected