apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Doc] Add default values for public variables for external models (#441)

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

* add default values for public variables in comments

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
2022-10-27 10:01:56 +08:00
committed by GitHub
parent 583f16afc1
commit b7e06b8c50
39 changed files with 114 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
fastdeploy/vision/classification/contrib/resnet.h
View File

@@ -50,12 +50,16 @@ class FASTDEPLOY_DECL ResNet : public FastDeployModel {
*/ */
virtual bool Predict(cv::Mat* im, ClassifyResult* result, int topk = 1); virtual bool Predict(cv::Mat* im, ClassifyResult* result, int topk = 1);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {224, 224}
*/ */
std::vector<int> size; std::vector<int> size;
/// Mean parameters for normalize, size should be the the same as channels /*! @brief
Mean parameters for normalize, size should be the the same as channels, default mean_vals = {0.485f, 0.456f, 0.406f}
*/
std::vector<float> mean_vals; std::vector<float> mean_vals;
/// Std parameters for normalize, size should be the the same as channels /*! @brief
Std parameters for normalize, size should be the the same as channels, default std_vals = {0.229f, 0.224f, 0.225f}
*/
std::vector<float> std_vals; std::vector<float> std_vals;

2
fastdeploy/vision/detection/contrib/nanodet_plus.h
View File

@@ -54,7 +54,7 @@ class FASTDEPLOY_DECL NanoDetPlus : public FastDeployModel {
float nms_iou_threshold = 0.5f); float nms_iou_threshold = 0.5f);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of input size (width, height), e.g (320, 320) Argument for image preprocessing step, tuple of input size (width, height), default (320, 320)
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels

2
fastdeploy/vision/detection/contrib/scaledyolov4.h
View File

@@ -51,7 +51,7 @@ class FASTDEPLOY_DECL ScaledYOLOv4 : public FastDeployModel {
float nms_iou_threshold = 0.5); float nms_iou_threshold = 0.5);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640}
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels

4
fastdeploy/vision/detection/contrib/yolor.h
View File

@@ -39,7 +39,7 @@ class FASTDEPLOY_DECL YOLOR : public FastDeployModel {
virtual std::string ModelName() const { return "YOLOR"; } virtual std::string ModelName() const { return "YOLOR"; }
/** \brief Predict the detection result for an input image /** \brief Predict the detection result for an input image
* *
* \param[in] im The input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format * \param[in] im The input image data, comes from cv::imread()
* \param[in] result The output detection result will be writen to this structure * \param[in] result The output detection result will be writen to this structure
* \param[in] conf_threshold confidence threashold for postprocessing, default is 0.25 * \param[in] conf_threshold confidence threashold for postprocessing, default is 0.25
* \param[in] nms_iou_threshold iou threashold for NMS, default is 0.5 * \param[in] nms_iou_threshold iou threashold for NMS, default is 0.5
@@ -50,7 +50,7 @@ class FASTDEPLOY_DECL YOLOR : public FastDeployModel {
float nms_iou_threshold = 0.5); float nms_iou_threshold = 0.5);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640}
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels

6
fastdeploy/vision/detection/contrib/yolov5.h
View File

@@ -78,7 +78,7 @@ class FASTDEPLOY_DECL YOLOv5 : public FastDeployModel {
float max_wh = 7680.0); float max_wh = 7680.0);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640}
*/ */
std::vector<int> size_; std::vector<int> size_;
// padding value, size should be the same as channels // padding value, size should be the same as channels
@@ -96,7 +96,9 @@ class FASTDEPLOY_DECL YOLOv5 : public FastDeployModel {
int stride_; int stride_;
// for offseting the boxes by classes when using NMS // for offseting the boxes by classes when using NMS
float max_wh_; float max_wh_;
/// for different strategies to get boxes when postprocessing /*! @brief
Argument for image preprocessing step, for different strategies to get boxes when postprocessing, default true
*/
bool multi_label_; bool multi_label_;
private: private:

4
fastdeploy/vision/detection/contrib/yolov5lite.h
View File

@@ -54,7 +54,7 @@ class FASTDEPLOY_DECL YOLOv5Lite : public FastDeployModel {
void UseCudaPreprocessing(int max_img_size = 3840 * 2160); void UseCudaPreprocessing(int max_img_size = 3840 * 2160);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, size = {640, 640}
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels
@@ -84,7 +84,7 @@ class FASTDEPLOY_DECL YOLOv5Lite : public FastDeployModel {
decode module. Please set it 'true' manually if the model file decode module. Please set it 'true' manually if the model file
was exported with decode module. was exported with decode module.
false : ONNX files without decode module. false : ONNX files without decode module.
true : ONNX file with decode module. true : ONNX file with decode module. default false.
*/ */
bool is_decode_exported; bool is_decode_exported;

2
fastdeploy/vision/detection/contrib/yolov6.h
View File

@@ -57,7 +57,7 @@ class FASTDEPLOY_DECL YOLOv6 : public FastDeployModel {
void UseCudaPreprocessing(int max_img_size = 3840 * 2160); void UseCudaPreprocessing(int max_img_size = 3840 * 2160);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640};
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels

2
fastdeploy/vision/detection/contrib/yolov7.h
View File

@@ -54,7 +54,7 @@ class FASTDEPLOY_DECL YOLOv7 : public FastDeployModel {
void UseCudaPreprocessing(int max_img_size = 3840 * 2160); void UseCudaPreprocessing(int max_img_size = 3840 * 2160);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640}
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels

2
fastdeploy/vision/detection/contrib/yolov7end2end_ort.h
View File

@@ -48,7 +48,7 @@ class FASTDEPLOY_DECL YOLOv7End2EndORT : public FastDeployModel {
float conf_threshold = 0.25); float conf_threshold = 0.25);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640}
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels

2
fastdeploy/vision/detection/contrib/yolov7end2end_trt.h
View File

@@ -53,7 +53,7 @@ class FASTDEPLOY_DECL YOLOv7End2EndTRT : public FastDeployModel {
void UseCudaPreprocessing(int max_img_size = 3840 * 2160); void UseCudaPreprocessing(int max_img_size = 3840 * 2160);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640}
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels

4
fastdeploy/vision/detection/contrib/yolox.h
View File

@@ -52,7 +52,7 @@ class FASTDEPLOY_DECL YOLOX : public FastDeployModel {
float nms_iou_threshold = 0.5); float nms_iou_threshold = 0.5);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640}
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels
@@ -61,7 +61,7 @@ class FASTDEPLOY_DECL YOLOX : public FastDeployModel {
whether the model_file was exported with decode module. The official whether the model_file was exported with decode module. The official
YOLOX/tools/export_onnx.py script will export ONNX file without YOLOX/tools/export_onnx.py script will export ONNX file without
decode module. Please set it 'true' manually if the model file decode module. Please set it 'true' manually if the model file
was exported with decode module. was exported with decode module. default false.
*/ */
bool is_decode_exported; bool is_decode_exported;
// downsample strides for YOLOX to generate anchors, // downsample strides for YOLOX to generate anchors,

2
fastdeploy/vision/facedet/contrib/retinaface.h
View File

@@ -65,7 +65,7 @@ class FASTDEPLOY_DECL RetinaFace : public FastDeployModel {
*/ */
std::vector<int> downsample_strides; std::vector<int> downsample_strides;
/*! @brief /*! @brief
Argument for image postprocessing step, min sizes, width and height for each anchor Argument for image postprocessing step, min sizes, width and height for each anchor, default min_sizes = {{16, 32}, {64, 128}, {256, 512}}
*/ */
std::vector<std::vector<int>> min_sizes; std::vector<std::vector<int>> min_sizes;
/*! @brief /*! @brief

8
fastdeploy/vision/facedet/contrib/scrfd.h
View File

@@ -77,14 +77,16 @@ class FASTDEPLOY_DECL SCRFD : public FastDeployModel {
*/ */
int landmarks_per_face; int landmarks_per_face;
/*! @brief /*! @brief
Argument for image postprocessing step, the outputs of onnx file with key points features or not Argument for image postprocessing step, the outputs of onnx file with key points features or not, default true
*/ */
bool use_kps; bool use_kps;
/*! @brief /*! @brief
Argument for image postprocessing step, the upperbond number of boxes processed by nms Argument for image postprocessing step, the upperbond number of boxes processed by nms, default 30000
*/ */
int max_nms; int max_nms;
/// Argument for image postprocessing step, anchor number of each stride /*! @brief
Argument for image postprocessing step, anchor number of each stride, default 2
*/
unsigned int num_anchors; unsigned int num_anchors;
private: private:

4
fastdeploy/vision/facedet/contrib/yolov5face.h
View File

@@ -51,7 +51,7 @@ class FASTDEPLOY_DECL YOLOv5Face : public FastDeployModel {
float nms_iou_threshold = 0.5); float nms_iou_threshold = 0.5);
/*! @brief /*! @brief
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default size = {640, 640}
*/ */
std::vector<int> size; std::vector<int> size;
// padding value, size should be the same as channels // padding value, size should be the same as channels
@@ -72,7 +72,7 @@ class FASTDEPLOY_DECL YOLOv5Face : public FastDeployModel {
/*! @brief /*! @brief
Argument for image postprocessing step, setup the number of landmarks for per face (if have), default 5 in Argument for image postprocessing step, setup the number of landmarks for per face (if have), default 5 in
official yolov5face note that, the outupt tensor's shape must be: official yolov5face note that, the outupt tensor's shape must be:
(1,n,4+1+2*landmarks_per_face+1=box+obj+landmarks+cls) (1,n,4+1+2*landmarks_per_face+1=box+obj+landmarks+cls), default 5
*/ */
int landmarks_per_face; int landmarks_per_face;

8
fastdeploy/vision/faceid/contrib/insightface_rec.h
View File

@@ -44,9 +44,13 @@ class FASTDEPLOY_DECL InsightFaceRecognitionModel : public FastDeployModel {
Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default (112, 112) Argument for image preprocessing step, tuple of (width, height), decide the target size after resize, default (112, 112)
*/ */
std::vector<int> size; std::vector<int> size;
/// Argument for image preprocessing step, alpha values for normalization /*! @brief
Argument for image preprocessing step, alpha values for normalization, default alpha = {1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f};
*/
std::vector<float> alpha; std::vector<float> alpha;
/// Argument for image preprocessing step, beta values for normalization /*! @brief
Argument for image preprocessing step, beta values for normalization, default beta = {-1.f, -1.f, -1.f}
*/
std::vector<float> beta; std::vector<float> beta;
/*! @brief /*! @brief
Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true. Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true.

4
fastdeploy/vision/matting/contrib/modnet.h
View File

@@ -44,11 +44,11 @@ class FASTDEPLOY_DECL MODNet : public FastDeployModel {
*/ */
std::vector<int> size; std::vector<int> size;
/*! @brief /*! @brief
Argument for image preprocessing step, parameters for normalization, size should be the the same as channels Argument for image preprocessing step, parameters for normalization, size should be the the same as channels, default alpha = {1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f}
*/ */
std::vector<float> alpha; std::vector<float> alpha;
/*! @brief /*! @brief
Argument for image preprocessing step, parameters for normalization, size should be the the same as channels Argument for image preprocessing step, parameters for normalization, size should be the the same as channels, default beta = {-1.f, -1.f, -1.f}
*/ */
std::vector<float> beta; std::vector<float> beta;
/*! @brief /*! @brief

6
python/fastdeploy/vision/classification/contrib/resnet.py
View File

@@ -56,21 +56,21 @@ class ResNet(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Returns the preprocess image size Returns the preprocess image size, default size = [224, 224];
""" """
return self._model.size return self._model.size
@property @property
def mean_vals(self): def mean_vals(self):
""" """
Returns the mean value of normlization Returns the mean value of normlization, default mean_vals = [0.485f, 0.456f, 0.406f];
""" """
return self._model.mean_vals return self._model.mean_vals
@property @property
def std_vals(self): def std_vals(self):
""" """
Returns the std value of normlization Returns the std value of normlization, default std_vals = [0.229f, 0.224f, 0.225f];
""" """
return self._model.std_vals return self._model.std_vals

2
python/fastdeploy/vision/classification/contrib/yolov5cls.py
View File

@@ -52,7 +52,7 @@ class YOLOv5Cls(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Returns the preprocess image size Returns the preprocess image size, default is (224, 224)
""" """
return self._model.size return self._model.size

2
python/fastdeploy/vision/detection/contrib/nanodet_plus.py
View File

@@ -56,7 +56,7 @@ class NanoDetPlus(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (320, 320)
""" """
return self._model.size return self._model.size

3
python/fastdeploy/vision/detection/contrib/scaled_yolov4.py
View File

@@ -56,7 +56,8 @@ class ScaledYOLOv4(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size

2
python/fastdeploy/vision/detection/contrib/yolor.py
View File

@@ -56,7 +56,7 @@ class YOLOR(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size

5
python/fastdeploy/vision/detection/contrib/yolov5.py
View File

@@ -81,7 +81,7 @@ class YOLOv5(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size
@@ -117,6 +117,9 @@ class YOLOv5(FastDeployModel):
@property @property
def multi_label(self): def multi_label(self):
"""
Argument for image preprocessing step, for different strategies to get boxes when postprocessing, default True
"""
return self._model.multi_label return self._model.multi_label
@size.setter @size.setter

5
python/fastdeploy/vision/detection/contrib/yolov5lite.py
View File

@@ -56,7 +56,7 @@ class YOLOv5Lite(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size
@@ -96,7 +96,8 @@ class YOLOv5Lite(FastDeployModel):
whether the model_file was exported with decode module. whether the model_file was exported with decode module.
The official YOLOv5Lite/export.py script will export ONNX file without decode module. The official YOLOv5Lite/export.py script will export ONNX file without decode module.
Please set it 'true' manually if the model file was exported with decode module. Please set it 'true' manually if the model file was exported with decode module.
false : ONNX files without decode module. true : ONNX file with decode module. False : ONNX files without decode module. True : ONNX file with decode module.
default False
""" """
return self._model.is_decode_exported return self._model.is_decode_exported

2
python/fastdeploy/vision/detection/contrib/yolov6.py
View File

@@ -56,7 +56,7 @@ class YOLOv6(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size

2
python/fastdeploy/vision/detection/contrib/yolov7.py
View File

@@ -56,7 +56,7 @@ class YOLOv7(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size

2
python/fastdeploy/vision/detection/contrib/yolov7end2end_ort.py
View File

@@ -54,7 +54,7 @@ class YOLOv7End2EndORT(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size

2
python/fastdeploy/vision/detection/contrib/yolov7end2end_trt.py
View File

@@ -54,7 +54,7 @@ class YOLOv7End2EndTRT(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size

3
python/fastdeploy/vision/detection/contrib/yolox.py
View File

@@ -56,7 +56,7 @@ class YOLOX(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640, 640]
""" """
return self._model.size return self._model.size
@@ -71,6 +71,7 @@ class YOLOX(FastDeployModel):
whether the model_file was exported with decode module. whether the model_file was exported with decode module.
The official YOLOX/tools/export_onnx.py script will export ONNX file without decode module. The official YOLOX/tools/export_onnx.py script will export ONNX file without decode module.
Please set it 'true' manually if the model file was exported with decode module. Please set it 'true' manually if the model file was exported with decode module.
Defalut False.
""" """
return self._model.is_decode_exported return self._model.is_decode_exported

4
python/fastdeploy/vision/facedet/contrib/retinaface.py
View File

@@ -56,7 +56,7 @@ class RetinaFace(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (640, 640)
""" """
return self._model.size return self._model.size
@@ -77,7 +77,7 @@ class RetinaFace(FastDeployModel):
@property @property
def min_sizes(self): def min_sizes(self):
""" """
Argument for image postprocessing step, min sizes, width and height for each anchor Argument for image postprocessing step, min sizes, width and height for each anchor, default min_sizes = [[16, 32], [64, 128], [256, 512]]
""" """
return self._model.min_sizes return self._model.min_sizes

20
python/fastdeploy/vision/facedet/contrib/scrfd.py
View File

@@ -56,7 +56,7 @@ class SCRFD(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (640, 640)
""" """
return self._model.size return self._model.size
@@ -87,22 +87,40 @@ class SCRFD(FastDeployModel):
@property @property
def downsample_strides(self): def downsample_strides(self):
"""
Argument for image postprocessing step,
downsample strides (namely, steps) for SCRFD to generate anchors,
will take (8,16,32) as default values
"""
return self._model.downsample_strides return self._model.downsample_strides
@property @property
def landmarks_per_face(self): def landmarks_per_face(self):
"""
Argument for image postprocessing step, landmarks_per_face, default 5 in SCRFD
"""
return self._model.landmarks_per_face return self._model.landmarks_per_face
@property @property
def use_kps(self): def use_kps(self):
"""
Argument for image postprocessing step,
the outputs of onnx file with key points features or not, default true
"""
return self._model.use_kps return self._model.use_kps
@property @property
def max_nms(self): def max_nms(self):
"""
Argument for image postprocessing step, the upperbond number of boxes processed by nms, default 30000
"""
return self._model.max_nms return self._model.max_nms
@property @property
def num_anchors(self): def num_anchors(self):
"""
Argument for image postprocessing step, anchor number of each stride, default 2
"""
return self._model.num_anchors return self._model.num_anchors
@size.setter @size.setter

2
python/fastdeploy/vision/facedet/contrib/ultraface.py
View File

@@ -56,7 +56,7 @@ class UltraFace(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (320, 240)
""" """
return self._model.size return self._model.size

2
python/fastdeploy/vision/facedet/contrib/yolov5face.py
View File

@@ -56,7 +56,7 @@ class YOLOv5Face(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [640,640]
""" """
return self._model.size return self._model.size

11
python/fastdeploy/vision/faceid/contrib/adaface.py
View File

@@ -52,35 +52,36 @@ class AdaFace(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (112, 112)
""" """
return self._model.size return self._model.size
@property @property
def alpha(self): def alpha(self):
""" """
Argument for image preprocessing step, alpha value for normalization Argument for image preprocessing step, alpha value for normalization, default alpha = [1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f]
""" """
return self._model.alpha return self._model.alpha
@property @property
def beta(self): def beta(self):
""" """
Argument for image preprocessing step, beta value for normalization Argument for image preprocessing step, beta values for normalization, default beta = {-1.f, -1.f, -1.f}
""" """
return self._model.beta return self._model.beta
@property @property
def swap_rb(self): def swap_rb(self):
""" """
Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true. Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default True.
""" """
return self._model.swap_rb return self._model.swap_rb
@property @property
def l2_normalize(self): def l2_normalize(self):
""" """
Argument for image preprocessing step, whether to apply l2 normalize to embedding values, default; Argument for image preprocessing step, whether to apply l2 normalize to embedding values, default False;
""" """
return self._model.l2_normalize return self._model.l2_normalize

10
python/fastdeploy/vision/faceid/contrib/arcface.py
View File

@@ -54,35 +54,35 @@ class ArcFace(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (112, 112)
""" """
return self._model.size return self._model.size
@property @property
def alpha(self): def alpha(self):
""" """
Argument for image preprocessing step, alpha value for normalization Argument for image preprocessing step, alpha value for normalization, default alpha = [1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f]
""" """
return self._model.alpha return self._model.alpha
@property @property
def beta(self): def beta(self):
""" """
Argument for image preprocessing step, beta value for normalization Argument for image preprocessing step, beta values for normalization, default beta = {-1.f, -1.f, -1.f}
""" """
return self._model.beta return self._model.beta
@property @property
def swap_rb(self): def swap_rb(self):
""" """
Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true. Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default True.
""" """
return self._model.swap_rb return self._model.swap_rb
@property @property
def l2_normalize(self): def l2_normalize(self):
""" """
Argument for image preprocessing step, whether to apply l2 normalize to embedding values, default; Argument for image preprocessing step, whether to apply l2 normalize to embedding values, default False;
""" """
return self._model.l2_normalize return self._model.l2_normalize

8
python/fastdeploy/vision/faceid/contrib/cosface.py
View File

@@ -53,28 +53,28 @@ class CosFace(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (112, 112)
""" """
return self._model.size return self._model.size
@property @property
def alpha(self): def alpha(self):
""" """
Argument for image preprocessing step, alpha value for normalization Argument for image preprocessing step, alpha value for normalization, default alpha = [1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f]
""" """
return self._model.alpha return self._model.alpha
@property @property
def beta(self): def beta(self):
""" """
Argument for image preprocessing step, beta value for normalization Argument for image preprocessing step, beta values for normalization, default beta = {-1.f, -1.f, -1.f}
""" """
return self._model.beta return self._model.beta
@property @property
def swap_rb(self): def swap_rb(self):
""" """
Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true. Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default True.
""" """
return self._model.swap_rb return self._model.swap_rb

8
python/fastdeploy/vision/faceid/contrib/insightface_rec.py
View File

@@ -53,28 +53,28 @@ class InsightFaceRecognitionModel(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (112, 112)
""" """
return self._model.size return self._model.size
@property @property
def alpha(self): def alpha(self):
""" """
Argument for image preprocessing step, alpha value for normalization Argument for image preprocessing step, alpha value for normalization, default alpha = [1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f]
""" """
return self._model.alpha return self._model.alpha
@property @property
def beta(self): def beta(self):
""" """
Argument for image preprocessing step, beta value for normalization Argument for image preprocessing step, beta values for normalization, default beta = {-1.f, -1.f, -1.f}
""" """
return self._model.beta return self._model.beta
@property @property
def swap_rb(self): def swap_rb(self):
""" """
Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true. Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default True.
""" """
return self._model.swap_rb return self._model.swap_rb

8
python/fastdeploy/vision/faceid/contrib/partial_fc.py
View File

@@ -53,28 +53,28 @@ class PartialFC(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (112, 112)
""" """
return self._model.size return self._model.size
@property @property
def alpha(self): def alpha(self):
""" """
Argument for image preprocessing step, alpha value for normalization Argument for image preprocessing step, alpha value for normalization, default alpha = [1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f]
""" """
return self._model.alpha return self._model.alpha
@property @property
def beta(self): def beta(self):
""" """
Argument for image preprocessing step, beta value for normalization Argument for image preprocessing step, beta values for normalization, default beta = {-1.f, -1.f, -1.f}
""" """
return self._model.beta return self._model.beta
@property @property
def swap_rb(self): def swap_rb(self):
""" """
Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true. Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default True.
""" """
return self._model.swap_rb return self._model.swap_rb

8
python/fastdeploy/vision/faceid/contrib/vpl.py
View File

@@ -53,28 +53,28 @@ class VPL(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default (112, 112)
""" """
return self._model.size return self._model.size
@property @property
def alpha(self): def alpha(self):
""" """
Argument for image preprocessing step, alpha value for normalization Argument for image preprocessing step, alpha value for normalization, default alpha = [1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f]
""" """
return self._model.alpha return self._model.alpha
@property @property
def beta(self): def beta(self):
""" """
Argument for image preprocessing step, beta value for normalization Argument for image preprocessing step, beta values for normalization, default beta = {-1.f, -1.f, -1.f}
""" """
return self._model.beta return self._model.beta
@property @property
def swap_rb(self): def swap_rb(self):
""" """
Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true. Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default True.
""" """
return self._model.swap_rb return self._model.swap_rb

8
python/fastdeploy/vision/matting/contrib/modnet.py
View File

@@ -53,28 +53,28 @@ class MODNet(FastDeployModel):
@property @property
def size(self): def size(self):
""" """
Argument for image preprocessing step, the preprocess image size, tuple of (width, height) Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [256,256]
""" """
return self._model.size return self._model.size
@property @property
def alpha(self): def alpha(self):
""" """
Argument for image preprocessing step, alpha value for normalization Argument for image preprocessing step, alpha value for normalization, default alpha = {1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f}
""" """
return self._model.alpha return self._model.alpha
@property @property
def beta(self): def beta(self):
""" """
Argument for image preprocessing step, beta value for normalization Argument for image preprocessing step, beta value for normalization, default beta = {-1.f, -1.f, -1.f}
""" """
return self._model.beta return self._model.beta
@property @property
def swap_rb(self): def swap_rb(self):
""" """
Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default true. Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default True.
""" """
return self._model.swap_rb return self._model.swap_rb