potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-31 00:03:03 +04:00
Code Packages Releases Wiki Activity

Merge pull request #24092 from Aser-Abdelfatah:GSoC_Support_GatherElements_ONNX

Browse Source 
GSoC Add ONNX Support for GatherElements #24092

Merge with: https://github.com/opencv/opencv_extra/pull/1082
Adds support to the ONNX operator GatherElements [operator docs](https://github.com/onnx/onnx/blob/main/docs/Operators.md#GatherElements)
Added tests to opencv_extra at pull request https://github.com/opencv/opencv_extra/pull/1082

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
This commit is contained in:
Aser Atawya
2023-10-18 00:41:47 -07:00
committed by GitHub
parent 014e8485b5
commit 240b245105
8 changed files with 303 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/include/opencv2/dnn/all_layers.hpp
+16
View File
@@ -343,6 +343,22 @@ CV__DNN_INLINE_NS_BEGIN
static Ptr<GatherLayer> create(const LayerParams& params);
};
/** @brief GatherElements layer
* GatherElements takes two inputs data and indices of the same rank r >= 1 and an optional attribute axis and works such that:
* output[i][j][k] = data[index[i][j][k]][j][k] if axis = 0 and r = 3
* output[i][j][k] = data[i][index[i][j][k]][k] if axis = 1 and r = 3
* output[i][j][k] = data[i][j][index[i][j][k]] if axis = 2 and r = 3
*
* Gather, on the other hand, takes a data tensor of rank r >= 1, and indices tensor of rank q, and works such that:
* it gathers the enteries along axis dimension of the input data indexed by indices and concatenates them in an output tensor of rank q + (r - 1)
* e.g. If axis = 0, let k = indices[i_{0}, ..., i_{q-1}] then output[i_{0}, ..., i_{q-1}, j_{0}, ..., j_{r-2}] = input[k , j_{0}, ..., j_{r-2}]:
**/
class CV_EXPORTS GatherElementsLayer : public Layer
{
public:
static Ptr<GatherElementsLayer> create(const LayerParams& params);
};
class CV_EXPORTS PoolingLayer : public Layer
{
public: