MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT / getOutputDimensions

Method getOutputDimensions

plugin/gridAnchorPlugin/gridAnchorPlugin.cpp:183–189  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

181}
182
183Dims GridAnchorGenerator::getOutputDimensions(int32_t index, Dims const* inputs, int32_t nbInputDims) noexcept
184{
185 // Particularity of the PriorBox layer: no batchSize dimension needed
186 // 2 channels. First channel stores the mean of each prior coordinate.
187 // Second channel stores the variance of each prior coordinate.
188 return Dims3(2, mParam[index].H * mParam[index].W * mNumPriors[index] * 4, 1);
189}
190
191int32_t GridAnchorGenerator::initialize() noexcept
192{

Callers

nothing calls this directly

Calls 1

Dims3Class · 0.85

Tested by

no test coverage detected