4.x
Merge pull request #17363 from YashasSamaga:cuda4dnn-eltwise-fusion2
Merge pull request #24080 from dkurt:dnn_cuda_layers
Merge pull request #14827 from YashasSamaga:cuda4dnn-csl-low
Merge pull request #17534 from YashasSamaga:cuda4dnn-remove-unused-funcs
add DetectionOutputOp
dnn: fix various dnn related typos
Merge pull request #17200 from YashasSamaga:cuda4dnn-general-opt1
fix compile-time errors, disable unsupported tests
Merge pull request #25630 from fengyuentau:nary-multi-thread
Merge pull request #16658 from YashasSamaga:cuda4dnn-refactor-activations
perfor fp conversions on GPU
Merge pull request #20933 from shubham-shahh:master
Merge pull request #16218 from JulienMaille:cuda-dnn-for-older-gpus
Merge pull request #24765 from fengyuentau:mod_operator
Merge pull request #19058 from sl-sergei:cuda_1d
Merge pull request #24610 from jimmylaw21:dnn-onnx-add-group-norm-layer
backport YOLOv4x-mish new_coords CUDA implementation
add half pixel centers and align corners param
FIX: disable dnn cuda input_shortcut on _half for CC<5.3