apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-07 01:22:59 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Doc] API docs for Visualize module (#770)

Browse Source 
* first commit for yolov7

* pybind for yolov7

* CPP README.md

* CPP README.md

* modified yolov7.cc

* README.md

* python file modify

* delete license in fastdeploy/

* repush the conflict part

* README.md modified

* README.md modified

* file path modified

* file path modified

* file path modified

* file path modified

* file path modified

* README modified

* README modified

* move some helpers to private

* add examples for yolov7

* api.md modified

* api.md modified

* api.md modified

* YOLOv7

* yolov7 release link

* yolov7 release link

* yolov7 release link

* copyright

* change some helpers to private

* change variables to const and fix documents.

* gitignore

* Transfer some funtions to private member of class

* Transfer some funtions to private member of class

* Merge from develop (#9)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

* first commit for yolor

* for merge

* Develop (#11)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

* Yolor (#16)

* Develop (#11) (#12)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

* Develop (#13)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* Develop (#14)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>
Co-authored-by: Jason <928090362@qq.com>

* add is_dynamic for YOLO series (#22)

* modify ppmatting backend and docs

* modify ppmatting docs

* fix the PPMatting size problem

* fix LimitShort's log

* retrigger ci

* modify PPMatting docs

* modify the way  for dealing with  LimitShort

* add python comments for external models

* modify resnet c++ comments

* modify C++ comments for external models

* modify python comments and add result class comments

* fix comments compile error

* modify result.h comments

* comments for vis

* python API

* python API

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>
Co-authored-by: Jason <928090362@qq.com>
This commit is contained in:
ziqi-jin
2022-12-01 20:46:35 +08:00
committed by GitHub
parent 4fd333f7f0
commit e811e9e239
4 changed files with 193 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
fastdeploy/vision/visualize/visualize.h
View File

@@ -20,9 +20,11 @@
#include "fastdeploy/vision/tracking/pptracking/model.h"
namespace fastdeploy {
/** \brief All C++ FastDeploy Vision Models APIs are defined inside this namespace
*
*/
namespace vision {
// This class will deprecated, please not use it
class FASTDEPLOY_DECL Visualize {
public:
static int num_classes_;
@@ -52,35 +54,108 @@ class FASTDEPLOY_DECL Visualize {
std::vector<int> GenerateColorMap(int num_classes = 1000);
cv::Mat RemoveSmallConnectedArea(const cv::Mat& alpha_pred, float threshold);
/** \brief Show the visualized results for detection models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \param[in] score_threshold threshold for result scores, the bounding box will not be shown if the score is less than score_threshold
* \param[in] line_size line size for bounding boxes
* \param[in] font_size font size for text
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisDetection(const cv::Mat& im,
const DetectionResult& result,
float score_threshold = 0.0,
int line_size = 1, float font_size = 0.5f);
/** \brief Show the visualized results with custom labels for detection models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \param[in] labels the visualized result will show the bounding box contain class label
* \param[in] score_threshold threshold for result scores, the bounding box will not be shown if the score is less than score_threshold
* \param[in] line_size line size for bounding boxes
* \param[in] font_size font size for text
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisDetection(const cv::Mat& im,
const DetectionResult& result,
const std::vector<std::string>& labels,
float score_threshold = 0.0,
int line_size = 1, float font_size = 0.5f);
/** \brief Show the visualized results for classification models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \param[in] top_k the length of return values, e.g., if topk==2, the result will include the 2 most possible class label for input image.
* \param[in] score_threshold threshold for top_k scores, the class will not be shown if the score is less than score_threshold
* \param[in] font_size font size
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisClassification(
const cv::Mat& im, const ClassifyResult& result, int top_k = 5,
float score_threshold = 0.0f, float font_size = 0.5f);
/** \brief Show the visualized results with custom labels for classification models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \param[in] labels custom labels for user, the visualized result will show the corresponding custom labels
* \param[in] top_k the length of return values, e.g., if topk==2, the result will include the 2 most possible class label for input image.
* \param[in] score_threshold threshold for top_k scores, the class will not be shown if the score is less than score_threshold
* \param[in] font_size font size
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisClassification(
const cv::Mat& im, const ClassifyResult& result,
const std::vector<std::string>& labels, int top_k = 5,
float score_threshold = 0.0f, float font_size = 0.5f);
/** \brief Show the visualized results for face detection models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \param[in] line_size line size for bounding boxes
* \param[in] font_size font size for text
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisFaceDetection(const cv::Mat& im,
const FaceDetectionResult& result,
int line_size = 1,
float font_size = 0.5f);
/** \brief Show the visualized results for face alignment models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \param[in] line_size line size for circle point
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisFaceAlignment(const cv::Mat& im,
const FaceAlignmentResult& result,
int line_size = 1);
/** \brief Show the visualized results for segmentation models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \param[in] weight transparent weight of visualized result image
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisSegmentation(const cv::Mat& im,
const SegmentationResult& result,
float weight = 0.5);
/** \brief Show the visualized results for matting models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \param[in] remove_small_connected_area if remove_small_connected_area==true, the visualized result will not include the small connected areas
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisMatting(const cv::Mat& im,
const MattingResult& result,
bool remove_small_connected_area = false);
/** \brief Show the visualized results for Ocr models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] result the result produced by model
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisOcr(const cv::Mat& im, const OCRResult& ocr_result);
FASTDEPLOY_DECL cv::Mat VisMOT(const cv::Mat& img, const MOTResult& results,
@@ -93,6 +168,13 @@ FASTDEPLOY_DECL cv::Mat SwapBackground(const cv::Mat& im,
const cv::Mat& background,
const SegmentationResult& result,
int background_label);
/** \brief Show the visualized results for key point detection models
*
* \param[in] im the input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
* \param[in] results the result produced by model
* \param[in] conf_threshold threshold for result scores, the result will not be shown if the score is less than conf_threshold
* \return cv::Mat type stores the visualized results
*/
FASTDEPLOY_DECL cv::Mat VisKeypointDetection(const cv::Mat& im,
const KeyPointDetectionResult& results,
float conf_threshold = 0.5f);