potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-31 08:13:04 +04:00
Code Packages Releases Wiki Activity

Merge pull request #23528 from WanliZhong:issue23278

Browse Source 
DNN/CUDA: make 'abcd op 1b11' broadcast eltwise operator support cuda
This commit is contained in:
Alexander Smorkalov
2023-04-24 19:31:55 +03:00
committed by GitHub
parent aa57833ad5 e4360294c5
commit e3e1f704a4
2 changed files with 20 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/src/layers/nary_eltwise_layers.cpp
+8 -3
View File
@@ -673,12 +673,17 @@ public:
{
auto context = reinterpret_cast<csl::CSLContext*>(context_);
auto input_wrapper = inputs[0].dynamicCast<CUDABackendWrapper>();
auto input_0_shape = inputs[0].dynamicCast<CUDABackendWrapper>()->getShape();
for (int i = 1; i < inputs.size(); i++)
{
auto from_wrapper = inputs[i].dynamicCast<CUDABackendWrapper>();
if (input_wrapper->getShape() != from_wrapper->getShape())
auto input_i_shape = inputs[i].dynamicCast<CUDABackendWrapper>()->getShape();
if (input_0_shape.size() != input_i_shape.size())
return Ptr<BackendNode>();
// check if the shape can be supported by `eltwise_ops.cu`, or return the default BackendNode
for (int j = 0; j < input_0_shape.size(); j++)
if (input_0_shape[j] != input_i_shape[j] &&
input_0_shape[j] != 1 && input_i_shape[j] != 1)
return Ptr<BackendNode>();
}
cuda4dnn::EltwiseOpType op_ = cuda4dnn::EltwiseOpType::SUM;