potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 07:13:02 +04:00
Code Packages Releases Wiki Activity

Merge pull request #24231 from fengyuentau:halide_cleanup_5.x

Browse Source 
dnn: cleanup of halide backend for 5.x #24231

Merge with https://github.com/opencv/opencv_extra/pull/1092.

### 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:
Yuantao Feng
2023-10-13 08:53:18 -05:00
committed by GitHub
parent 0976765c62
commit d789cb459c
59 changed files with 226 additions and 2610 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/include/opencv2/dnn/dnn.hpp
+12 -63
View File
@@ -71,9 +71,8 @@ CV__DNN_INLINE_NS_BEGIN
{
//! DNN_BACKEND_DEFAULT equals to OPENCV_DNN_BACKEND_DEFAULT, which can be defined using CMake or a configuration parameter
DNN_BACKEND_DEFAULT = 0,
DNN_BACKEND_HALIDE,
DNN_BACKEND_INFERENCE_ENGINE, //!< Intel OpenVINO computational backend
//!< @note Tutorial how to build OpenCV with OpenVINO: @ref tutorial_dnn_openvino
DNN_BACKEND_INFERENCE_ENGINE = 2, //!< Intel OpenVINO computational backend
//!< @note Tutorial how to build OpenCV with OpenVINO: @ref tutorial_dnn_openvino
DNN_BACKEND_OPENCV,
DNN_BACKEND_VKCOM,
DNN_BACKEND_CUDA,
@@ -314,18 +313,6 @@ CV__DNN_INLINE_NS_BEGIN
*/
virtual bool supportBackend(int backendId); // FIXIT const
/**
* @brief Returns Halide backend node.
* @param[in] inputs Input Halide buffers.
* @see BackendNode, BackendWrapper
*
* Input buffers should be exactly the same that will be used in forward invocations.
* Despite we can use Halide::ImageParam based on input shape only,
* it helps prevent some memory management issues (if something wrong,
* Halide tests will be failed).
*/
virtual Ptr<BackendNode> initHalide(const std::vector<Ptr<BackendWrapper> > &inputs);
virtual Ptr<BackendNode> initNgraph(const std::vector<Ptr<BackendWrapper> > &inputs, const std::vector<Ptr<BackendNode> >& nodes);
virtual Ptr<BackendNode> initVkCom(const std::vector<Ptr<BackendWrapper> > &inputs, std::vector<Ptr<BackendWrapper> > &outputs);
@@ -369,33 +356,6 @@ CV__DNN_INLINE_NS_BEGIN
const std::vector<Ptr<BackendWrapper> > &outputs,
const std::vector<Ptr<BackendNode> >& nodes);
/**
* @brief Automatic Halide scheduling based on layer hyper-parameters.
* @param[in] node Backend node with Halide functions.
* @param[in] inputs Blobs that will be used in forward invocations.
* @param[in] outputs Blobs that will be used in forward invocations.
* @param[in] targetId Target identifier
* @see BackendNode, Target
*
* Layer don't use own Halide::Func members because we can have applied
* layers fusing. In this way the fused function should be scheduled.
*/
virtual void applyHalideScheduler(Ptr<BackendNode>& node,
const std::vector<Mat*> &inputs,
const std::vector<Mat> &outputs,
int targetId) const;
/**
* @brief Implement layers fusing.
* @param[in] node Backend node of bottom layer.
* @see BackendNode
*
* Actual for graph-based backends. If layer attached successfully,
* returns non-empty cv::Ptr to node of the same backend.
* Fuse only over the last function.
*/
virtual Ptr<BackendNode> tryAttach(const Ptr<BackendNode>& node);
/**
* @brief Tries to attach to the layer the subsequent activation layer, i.e. do the layer fusion in a partial case.
* @param[in] layer The subsequent activation layer.
@@ -671,17 +631,6 @@ CV__DNN_INLINE_NS_BEGIN
*/
CV_WRAP void getOutputDetails(CV_OUT std::vector<float>& scales, CV_OUT std::vector<int>& zeropoints) const;
/**
* @brief Compile Halide layers.
* @param[in] scheduler Path to YAML file with scheduling directives.
* @see setPreferableBackend
*
* Schedule layers that support Halide backend. Then compile them for
* specific target. For layers that not represented in scheduling file
* or if no manual scheduling used at all, automatic scheduling will be applied.
*/
CV_WRAP void setHalideScheduler(const String& scheduler);
/**
* @brief Ask network to use specific computation backend where it supported.
* @param[in] backendId backend identifier.
@@ -695,16 +644,16 @@ CV__DNN_INLINE_NS_BEGIN
* @see Target
*
* List of supported combinations backend / target:
* | | DNN_BACKEND_OPENCV | DNN_BACKEND_INFERENCE_ENGINE | DNN_BACKEND_HALIDE | DNN_BACKEND_CUDA |
* |------------------------|--------------------|------------------------------|--------------------|-------------------|
* | DNN_TARGET_CPU | + | + | + | |
* | DNN_TARGET_OPENCL | + | + | + | |
* | DNN_TARGET_OPENCL_FP16 | + | + | | |
* | DNN_TARGET_MYRIAD | | + | | |
* | DNN_TARGET_FPGA | | + | | |
* | DNN_TARGET_CUDA | | | | + |
* | DNN_TARGET_CUDA_FP16 | | | | + |
* | DNN_TARGET_HDDL | | + | | |
* | | DNN_BACKEND_OPENCV | DNN_BACKEND_INFERENCE_ENGINE | DNN_BACKEND_CUDA |
* |------------------------|--------------------|------------------------------|-------------------|
* | DNN_TARGET_CPU | + | + | |
* | DNN_TARGET_OPENCL | + | + | |
* | DNN_TARGET_OPENCL_FP16 | + | + | |
* | DNN_TARGET_MYRIAD | | + | |
* | DNN_TARGET_FPGA | | + | |
* | DNN_TARGET_CUDA | | | + |
* | DNN_TARGET_CUDA_FP16 | | | + |
* | DNN_TARGET_HDDL | | + | |
*/
CV_WRAP void setPreferableTarget(int targetId);