Add model SCRFD support by ziqi-jin · Pull Request #68 · PaddlePaddle/FastDeploy

ziqi-jin · 2022-08-03T08:35:47Z

Face detection model SCRFD
supply the decoding process when the exported ONNX file includes face key points or not
add is_dynamic support for all yolo series

DefTruth · 2022-08-03T11:03:44Z

+}
+
+void SCRFD::GeneratePoints() {
+  if (center_points_is_update_ && !is_dynamic_input_) return;


这里也改成统一的风格吧

if (center_points_is_update_ && !is_dynamic_input_) { return; }

DefTruth · 2022-08-03T11:04:53Z

+        float* landmarks_ptr =
+            static_cast<float*>(infer_result.at(f + 2 * fmc).Data());
+        // landmarks
+        const float* kps_offsets = landmarks_ptr + i * 10;


这句也应该是用landmarks_per_face * 2来计算地址

const float* kps_offsets = landmarks_ptr + i * 10; // 改成 const float* kps_offsets = landmarks_ptr + i *(landmarks_per_face * 2);

DefTruth · 2022-08-03T11:07:28Z

+  bool center_points_is_update_;
+
+  // feature map count
+  unsigned int fmc;


fmc 和 center_points都是私有的，都加一下下划线吧

…he count for nms

* 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 (PaddlePaddle#9) * Fix compile problem in different python version (PaddlePaddle#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 (PaddlePaddle#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (PaddlePaddle#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 (PaddlePaddle#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 (PaddlePaddle#11) * Fix compile problem in different python version (PaddlePaddle#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 (PaddlePaddle#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (PaddlePaddle#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 (PaddlePaddle#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 (PaddlePaddle#16) * Develop (PaddlePaddle#11) (PaddlePaddle#12) * Fix compile problem in different python version (PaddlePaddle#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 (PaddlePaddle#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (PaddlePaddle#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 (PaddlePaddle#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 (PaddlePaddle#13) * Fix compile problem in different python version (PaddlePaddle#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 (PaddlePaddle#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (PaddlePaddle#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 (PaddlePaddle#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 (PaddlePaddle#14) * Fix compile problem in different python version (PaddlePaddle#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 (PaddlePaddle#22) * add ppdet/ppyoloe * Add demo code and documents * add convert processor to vision (PaddlePaddle#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 (PaddlePaddle#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 (PaddlePaddle#22) * first commit for scrfd * bind file * documents for scrfd * documents for scrfd * documents for scrfd * documents for scrfd * modified for the pr comments * modified for the PR comments * fix second PR comments * delete the member fmc_, create fmc in the Postprocess function, fix the count for nms 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>

ziqi-jin added 30 commits July 13, 2022 13:55

first commit for yolov7

1684b05

pybind for yolov7

71c00d9

CPP README.md

21ab2f9

CPP README.md

d63e862

modified yolov7.cc

7b3b0e2

README.md

d039e80

python file modify

a34a815

merge test

eb010a8

delete license in fastdeploy/

39f64f2

repush the conflict part

d071b37

README.md modified

d5026ca

README.md modified

fb376ad

file path modified

4b8737c

file path modified

ce922a0

file path modified

6e00b82

file path modified

8c359fb

file path modified

906c730

README modified

80c1223

README modified

6072757

move some helpers to private

2c6e6a4

add examples for yolov7

48136f0

api.md modified

6feca92

api.md modified

ae70d4f

api.md modified

f591b85

YOLOv7

f0def41

yolov7 release link

15b9160

yolov7 release link

4706e8c

yolov7 release link

dc83584

copyright

086debd

change some helpers to private

4f980b9

ziqi-jin and others added 16 commits July 22, 2022 10:00

Merge branch 'PaddlePaddle:develop' into develop

c996117

Merge branch 'PaddlePaddle:develop' into develop

0aefe32

Merge branch 'PaddlePaddle:develop' into develop

2330414

Merge branch 'PaddlePaddle:develop' into develop

4660161

Merge branch 'PaddlePaddle:develop' into develop

033c18e

Merge branch 'PaddlePaddle:develop' into develop

6c94d65

Merge branch 'PaddlePaddle:develop' into develop

85fb256

add is_dynamic for YOLO series (#22)

90ca4cb

Merge branch 'PaddlePaddle:develop' into develop

f6a4ed2

Merge branch 'PaddlePaddle:develop' into develop

3682091

first commit for scrfd

200b5a0

bind file

ab7a81c

documents for scrfd

e4b6f3e

documents for scrfd

f77073d

documents for scrfd

2426e8a

documents for scrfd

656a89a

DefTruth requested changes Aug 3, 2022

View reviewed changes

ziqi-jin added 2 commits August 3, 2022 10:37

modified for the pr comments

722c67f

modified for the PR comments

9630a7d

ziqi-jin requested a review from DefTruth August 3, 2022 10:58

DefTruth requested changes Aug 3, 2022

View reviewed changes

fix second PR comments

4a6caed

DefTruth requested changes Aug 3, 2022

View reviewed changes

Comment thread csrcs/fastdeploy/vision/deepinsight/scrfd.cc Outdated

Comment thread csrcs/fastdeploy/vision/deepinsight/scrfd.cc Outdated

delete the member fmc_, create fmc in the Postprocess function, fix t…

25d36a5

…he count for nms

ziqi-jin requested a review from DefTruth August 3, 2022 12:15

DefTruth approved these changes Aug 3, 2022

View reviewed changes

jiangjiajun merged commit bd0482f into PaddlePaddle:develop Aug 4, 2022

ziqi-jin deleted the scrfdpr branch August 10, 2022 06:21

chriswack mentioned this pull request Oct 17, 2022

OpenCV(4.3.0) Error: Assertion failed (inv_scale_x > 0) in resize #385

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add model SCRFD support #68

Add model SCRFD support #68
jiangjiajun merged 63 commits into
PaddlePaddle:developfrom
ziqi-jin:scrfdpr

ziqi-jin commented Aug 3, 2022 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

DefTruth Aug 3, 2022

Uh oh!

DefTruth Aug 3, 2022

Uh oh!

ziqi-jin Aug 3, 2022

Uh oh!

DefTruth Aug 3, 2022

Uh oh!

ziqi-jin Aug 3, 2022

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

ziqi-jin commented Aug 3, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

DefTruth Aug 3, 2022

Choose a reason for hiding this comment

Uh oh!

DefTruth Aug 3, 2022

Choose a reason for hiding this comment

Uh oh!

ziqi-jin Aug 3, 2022

Choose a reason for hiding this comment

Uh oh!

DefTruth Aug 3, 2022

Choose a reason for hiding this comment

Uh oh!

ziqi-jin Aug 3, 2022

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

ziqi-jin commented Aug 3, 2022 •

edited

Loading