mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-06-07 17:44:04 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #20080 from pauljurczak:patch-3

Browse Source 
* Update dnn.hpp

getPerfProfile is not supported by the CUDA backend, see https://github.com/opencv/opencv/issues/20077

* dnn.hpp: fix doxygen formatting
This commit is contained in:
Paul Jurczak 2021-06-02 13:15:52 -06:00 committed by GitHub
parent 7d91dfe339
commit ff60abb575
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
modules/dnn/include/opencv2/dnn/dnn.hpp
View File

@ -712,9 +712,11 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
CV_WRAP void enableFusion(bool fusion); CV_WRAP void enableFusion(bool fusion);
/** @brief Returns overall time for inference and timings (in ticks) for layers. /** @brief Returns overall time for inference and timings (in ticks) for layers.
*
* Indexes in returned vector correspond to layers ids. Some layers can be fused with others, * Indexes in returned vector correspond to layers ids. Some layers can be fused with others,
* in this case zero ticks count will be return for that skipped layers. * in this case zero ticks count will be return for that skipped layers. Supported by DNN_BACKEND_OPENCV on DNN_TARGET_CPU only.
* @param timings vector for tick timings for all layers. *
* @param[out] timings vector for tick timings for all layers.
* @return overall ticks for model inference. * @return overall ticks for model inference.
*/ */
CV_WRAP int64 getPerfProfile(CV_OUT std::vector<double>& timings); CV_WRAP int64 getPerfProfile(CV_OUT std::vector<double>& timings);