MCPcopy Create free account
hub / github.com/darglein/ADOP / PointRenderModuleImpl

Method PointRenderModuleImpl

src/lib/rendering/RenderModule.cpp:10–14  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

8
9#include <torch/torch.h>
10PointRenderModuleImpl::PointRenderModuleImpl(std::shared_ptr<CombinedParams> params)
11 : params(params), num_layers(params->net_params.num_input_layers)
12{
13 cache = std::make_shared<PointRendererCache>();
14}
15
16std::pair<std::vector<torch::Tensor>, std::vector<torch::Tensor>> PointRenderModuleImpl::forward(
17 NeuralScene& scene, const std::vector<NeuralTrainData>& batch, CUDA::CudaTimerSystem* timer_system)

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected