mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 09:07:10 +08:00
Modify docs for PP-Matting, change VisMattingAlpha to VisMatting, fix Squeeze function. (#354)
* 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 * modify PPMatting to PP-Matting, fix squeeze, modify VisMattingAlpha to VisMatting 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
@@ -204,8 +204,8 @@ int main(int argc, char* argv[]) {
|
||||
| <font size=2> Face Recognition | <font size=2> [insightface/PartialFC](./examples/vision/faceid/insightface) | <font size=2> [Python](./examples/vision/faceid/insightface/python)/[C++](./examples/vision/faceid/insightface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
|
||||
| <font size=2> Face Recognition | <font size=2> [insightface/VPL](./examples/vision/faceid/insightface) | <font size=2> [Python](./examples/vision/faceid/insightface/python)/[C++](./examples/vision/faceid/insightface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
|
||||
| <font size=2> Matting | <font size=2> [ZHKKKe/MODNet](./examples/vision/matting/modnet) | <font size=2> [Python](./examples/vision/matting/modnet/python)/[C++](./examples/vision/matting/modnet/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/PPMatting](./examples/vision/matting/ppmatting) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/PPHumanMatting](./examples/vision/matting/modnet) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/PP-Matting](./examples/vision/matting/ppmatting) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/PP-HumanMatting](./examples/vision/matting/modnet) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/ModNet](./examples/vision/matting/modnet) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Information Extraction | <font size=2> [PaddleNLP/UIE](./examples/text/uie) | <font size=2> [Python](./examples/text/uie/python)/[C++](./examples/text/uie/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
|
||||
|
||||
@@ -218,8 +218,8 @@ Notes:
|
||||
| <font size=2> Face Recognition | <font size=2> [insightface/PartialFC](./examples/vision/faceid/insightface) | <font size=2> [Python](./examples/vision/faceid/insightface/python)/[C++](./examples/vision/faceid/insightface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
|
||||
| <font size=2> Face Recognition | <font size=2> [insightface/VPL](./examples/vision/faceid/insightface) | <font size=2> [Python](./examples/vision/faceid/insightface/python)/[C++](./examples/vision/faceid/insightface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
|
||||
| <font size=2> Matting | <font size=2> [ZHKKKe/MODNet](./examples/vision/matting/modnet) | <font size=2> [Python](./examples/vision/matting/modnet/python)/[C++](./examples/vision/matting/modnet/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/PPMatting](./examples/vision/matting/ppmatting) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/PPHumanMatting](./examples/vision/matting/modnet) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/PP-Matting](./examples/vision/matting/ppmatting) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/PP-HumanMatting](./examples/vision/matting/modnet) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Matting | <font size=2> [PaddleSeg/ModNet](./examples/vision/matting/modnet) | <font size=2> [Python](./examples/vision/matting/ppmatting/python)/[C++](./examples/vision/matting/ppmatting/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
| <font size=2> Information Extraction | <font size=2> [PaddleNLP/UIE](./examples/text/uie) | <font size=2> [Python](./examples/text/uie/python)/[C++](./examples/text/uie/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅|
|
||||
|
||||
|
||||
@@ -5,6 +5,6 @@ FastDeploy目前支持如下抠图模型部署
|
||||
| 模型 | 说明 | 模型格式 | 版本 |
|
||||
| :--- | :--- | :------- | :--- |
|
||||
| [ZHKKKe/MODNet](./modnet) | MODNet 系列模型 | ONNX | [CommitID:28165a4](https://github.com/ZHKKKe/MODNet/commit/28165a4) |
|
||||
| [PaddleSeg/PPMatting](./ppmatting) | PPMatting 系列模型 | Paddle | [Release/2.6](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting) |
|
||||
| [PaddleSeg/PPHumanMatting](./ppmatting) | PPHumanMatting 系列模型 | Paddle | [Release/2.6](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting) |
|
||||
| [PaddleSeg/PP-Matting](./ppmatting) | PP-Matting 系列模型 | Paddle | [Release/2.6](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting) |
|
||||
| [PaddleSeg/PP-HumanMatting](./ppmatting) | PP-HumanMatting 系列模型 | Paddle | [Release/2.6](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting) |
|
||||
| [PaddleSeg/ModNet](./ppmatting) | ModNet 系列模型 | Paddle | [Release/2.6](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting) |
|
||||
|
||||
@@ -32,7 +32,7 @@ void CpuInfer(const std::string& model_file, const std::string& image_file,
|
||||
return;
|
||||
}
|
||||
|
||||
auto vis_im = fastdeploy::vision::Visualize::VisMattingAlpha(im_bak, res);
|
||||
auto vis_im = fastdeploy::vision::VisMatting(im_bak, res);
|
||||
auto vis_im_with_bg =
|
||||
fastdeploy::vision::Visualize::SwapBackgroundMatting(im_bak, bg, res);
|
||||
cv::imwrite("visualized_result.jpg", vis_im_with_bg);
|
||||
@@ -63,7 +63,7 @@ void GpuInfer(const std::string& model_file, const std::string& image_file,
|
||||
return;
|
||||
}
|
||||
|
||||
auto vis_im = fastdeploy::vision::Visualize::VisMattingAlpha(im_bak, res);
|
||||
auto vis_im = fastdeploy::vision::VisMatting(im_bak, res);
|
||||
auto vis_im_with_bg =
|
||||
fastdeploy::vision::Visualize::SwapBackgroundMatting(im_bak, bg, res);
|
||||
cv::imwrite("visualized_result.jpg", vis_im_with_bg);
|
||||
@@ -95,7 +95,7 @@ void TrtInfer(const std::string& model_file, const std::string& image_file,
|
||||
return;
|
||||
}
|
||||
|
||||
auto vis_im = fastdeploy::vision::Visualize::VisMattingAlpha(im_bak, res);
|
||||
auto vis_im = fastdeploy::vision::VisMatting(im_bak, res);
|
||||
auto vis_im_with_bg =
|
||||
fastdeploy::vision::Visualize::SwapBackgroundMatting(im_bak, bg, res);
|
||||
cv::imwrite("visualized_result.jpg", vis_im_with_bg);
|
||||
|
||||
@@ -1,38 +1,38 @@
|
||||
# PPMatting模型部署
|
||||
# PP-Matting模型部署
|
||||
|
||||
## 模型版本说明
|
||||
|
||||
- [PPMatting Release/2.6](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
- [PP-Matting Release/2.6](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
|
||||
## 支持模型列表
|
||||
|
||||
目前FastDeploy支持如下模型的部署
|
||||
|
||||
- [PPMatting系列模型](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
- [PPHumanMatting系列模型](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
- [PP-Matting系列模型](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
- [PP-HumanMatting系列模型](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
- [ModNet系列模型](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
|
||||
|
||||
## 导出部署模型
|
||||
|
||||
在部署前，需要先将PPMatting导出成部署模型，导出步骤参考文档[导出模型](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)(Tips:导出PPMatting系列模型和PPHumanMatting系列模型需要设置导出脚本的`--input_shape`参数)
|
||||
在部署前，需要先将PP-Matting导出成部署模型，导出步骤参考文档[导出模型](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)(Tips:导出PP-Matting系列模型和PP-HumanMatting系列模型需要设置导出脚本的`--input_shape`参数)
|
||||
|
||||
|
||||
## 下载预训练模型
|
||||
|
||||
为了方便开发者的测试，下面提供了PPMatting导出的各系列模型，开发者可直接下载使用。
|
||||
为了方便开发者的测试，下面提供了PP-Matting导出的各系列模型，开发者可直接下载使用。
|
||||
|
||||
其中精度指标来源于PPMatting中对各模型的介绍(未提供精度数据)，详情各参考PPMatting中的说明。
|
||||
其中精度指标来源于PP-Matting中对各模型的介绍(未提供精度数据)，详情各参考PP-Matting中的说明。
|
||||
|
||||
|
||||
| 模型 | 参数大小 | 精度 | 备注 |
|
||||
|:---------------------------------------------------------------- |:----- |:----- | :------ |
|
||||
| [PPMatting-512](https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-512.tgz) | 106MB | - |
|
||||
| [PPMatting-1024](https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-1024.tgz) | 106MB | - |
|
||||
| [PPHumanMatting](https://bj.bcebos.com/paddlehub/fastdeploy/PPHumanMatting.tgz) | 247MB | - |
|
||||
| [Modnet_ResNet50_vd](https://bj.bcebos.com/paddlehub/fastdeploy/PPModnet_ResNet50_vd.tgz) | 355MB | - |
|
||||
| [Modnet_MobileNetV2](https://bj.bcebos.com/paddlehub/fastdeploy/PPModnet_MobileNetV2.tgz) | 28MB | - |
|
||||
| [Modnet_HRNet_w18](https://bj.bcebos.com/paddlehub/fastdeploy/PPModnet_HRNet_w18.tgz) | 51MB | - |
|
||||
| [PP-Matting-512](https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-512.tgz) | 106MB | - |
|
||||
| [PP-Matting-1024](https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-1024.tgz) | 106MB | - |
|
||||
| [PP-HumanMatting](https://bj.bcebos.com/paddlehub/fastdeploy/PPHumanMatting.tgz) | 247MB | - |
|
||||
| [Modnet-ResNet50_vd](https://bj.bcebos.com/paddlehub/fastdeploy/PPModnet_ResNet50_vd.tgz) | 355MB | - |
|
||||
| [Modnet-MobileNetV2](https://bj.bcebos.com/paddlehub/fastdeploy/PPModnet_MobileNetV2.tgz) | 28MB | - |
|
||||
| [Modnet-HRNet_w18](https://bj.bcebos.com/paddlehub/fastdeploy/PPModnet_HRNet_w18.tgz) | 51MB | - |
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
# PPMatting C++部署示例
|
||||
# PP-Matting C++部署示例
|
||||
|
||||
本目录下提供`infer.cc`快速完成PPMatting在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
|
||||
本目录下提供`infer.cc`快速完成PP-Matting在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/environment.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/quick_start)
|
||||
|
||||
以Linux上 PPMatting 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在[Fastdeploy C++预编译库](../../../../../docs/quick_start/CPP_prebuilt_libraries.md)下载CPU推理库）
|
||||
以Linux上 PP-Matting 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在[Fastdeploy C++预编译库](../../../../../docs/quick_start/CPP_prebuilt_libraries.md)下载CPU推理库）
|
||||
|
||||
```bash
|
||||
#下载SDK，编译模型examples代码（SDK中包含了examples代码）
|
||||
@@ -18,7 +18,7 @@ mkdir build && cd build
|
||||
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.1
|
||||
make -j
|
||||
|
||||
# 下载PPMatting模型文件和测试图片
|
||||
# 下载PP-Matting模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-512.tgz
|
||||
tar -xvf PP-Matting-512.tgz
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_input.jpg
|
||||
@@ -44,7 +44,7 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg
|
||||
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/compile/how_to_use_sdk_on_windows.md)
|
||||
|
||||
## PPMatting C++接口
|
||||
## PP-Matting C++接口
|
||||
|
||||
### PPMatting类
|
||||
|
||||
@@ -57,7 +57,7 @@ fastdeploy::vision::matting::PPMatting(
|
||||
const ModelFormat& model_format = ModelFormat::PADDLE)
|
||||
```
|
||||
|
||||
PPMatting模型加载和初始化，其中model_file为导出的Paddle模型格式。
|
||||
PP-Matting模型加载和初始化，其中model_file为导出的Paddle模型格式。
|
||||
|
||||
**参数**
|
||||
|
||||
|
||||
@@ -41,7 +41,7 @@ void CpuInfer(const std::string& model_dir, const std::string& image_file,
|
||||
std::cerr << "Failed to predict." << std::endl;
|
||||
return;
|
||||
}
|
||||
auto vis_im = fastdeploy::vision::Visualize::VisMattingAlpha(im_bak, res);
|
||||
auto vis_im = fastdeploy::vision::VisMatting(im_bak, res);
|
||||
auto vis_im_with_bg =
|
||||
fastdeploy::vision::Visualize::SwapBackgroundMatting(im_bak, bg, res);
|
||||
cv::imwrite("visualized_result.jpg", vis_im_with_bg);
|
||||
@@ -75,7 +75,7 @@ void GpuInfer(const std::string& model_dir, const std::string& image_file,
|
||||
std::cerr << "Failed to predict." << std::endl;
|
||||
return;
|
||||
}
|
||||
auto vis_im = fastdeploy::vision::Visualize::VisMattingAlpha(im_bak, res);
|
||||
auto vis_im = fastdeploy::vision::VisMatting(im_bak, res);
|
||||
auto vis_im_with_bg =
|
||||
fastdeploy::vision::Visualize::SwapBackgroundMatting(im_bak, bg, res);
|
||||
cv::imwrite("visualized_result.jpg", vis_im_with_bg);
|
||||
@@ -110,7 +110,7 @@ void TrtInfer(const std::string& model_dir, const std::string& image_file,
|
||||
std::cerr << "Failed to predict." << std::endl;
|
||||
return;
|
||||
}
|
||||
auto vis_im = fastdeploy::vision::Visualize::VisMattingAlpha(im_bak, res);
|
||||
auto vis_im = fastdeploy::vision::VisMatting(im_bak, res);
|
||||
auto vis_im_with_bg =
|
||||
fastdeploy::vision::Visualize::SwapBackgroundMatting(im_bak, bg, res);
|
||||
cv::imwrite("visualized_result.jpg", vis_im_with_bg);
|
||||
|
||||
@@ -1,18 +1,18 @@
|
||||
# PPMatting Python部署示例
|
||||
# PP-Matting Python部署示例
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/environment.md)
|
||||
- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/quick_start)
|
||||
|
||||
本目录下提供`infer.py`快速完成PPMatting在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
|
||||
本目录下提供`infer.py`快速完成PP-Matting在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
|
||||
|
||||
```bash
|
||||
#下载部署示例代码
|
||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||
cd FastDeploy/examples/vision/matting/ppmatting/python
|
||||
|
||||
# 下载PPmatting模型文件和测试图片
|
||||
# 下载PP-Matting模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-512.tgz
|
||||
tar -xvf PP-Matting-512.tgz
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_input.jpg
|
||||
@@ -32,13 +32,13 @@ python infer.py --model PP-Matting-512 --image matting_input.jpg --bg matting_bg
|
||||
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852116-cf91445b-3a67-45d9-a675-c69fe77c383a.jpg">
|
||||
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852554-6960659f-4fd7-4506-b33b-54e1a9dd89bf.jpg">
|
||||
</div>
|
||||
## PPMatting Python接口
|
||||
## PP-Matting Python接口
|
||||
|
||||
```python
|
||||
fd.vision.matting.PPMatting(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
|
||||
```
|
||||
|
||||
PPMatting模型加载和初始化，其中model_file, params_file以及config_file为训练模型导出的Paddle inference文件，具体请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
PP-Matting模型加载和初始化，其中model_file, params_file以及config_file为训练模型导出的Paddle inference文件，具体请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/Matting)
|
||||
|
||||
**参数**
|
||||
|
||||
@@ -72,7 +72,7 @@ PPMatting模型加载和初始化，其中model_file, params_file以及config_fi
|
||||
|
||||
## 其它文档
|
||||
|
||||
- [PPMatting 模型介绍](..)
|
||||
- [PPMatting C++部署](../cpp)
|
||||
- [PP-Matting 模型介绍](..)
|
||||
- [PP-Matting C++部署](../cpp)
|
||||
- [模型预测结果说明](../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../docs/runtime/how_to_change_backend.md)
|
||||
|
||||
@@ -59,7 +59,7 @@ bg = cv2.imread(args.bg)
|
||||
result = model.predict(im.copy())
|
||||
print(result)
|
||||
# 可视化结果
|
||||
vis_im = fd.vision.vis_matting_alpha(im, result)
|
||||
vis_im = fd.vision.vis_matting(im, result)
|
||||
vis_im_with_bg = fd.vision.swap_background_matting(im, bg, result)
|
||||
cv2.imwrite("visualized_result_fg.jpg", vis_im)
|
||||
cv2.imwrite("visualized_result_replaced_bg.jpg", vis_im_with_bg)
|
||||
|
||||
@@ -89,6 +89,8 @@ void FDTensor::Squeeze(int64_t axis) {
|
||||
size_t ndim = shape.size();
|
||||
FDASSERT(axis >= 0 && axis < ndim,
|
||||
"The allowed 'axis' must be in range of (0, %lu)!", ndim);
|
||||
FDASSERT(shape[axis]==1,
|
||||
"The No.%ld dimension of shape should be 1, but it is %ld!", (long)axis, (long)shape[axis]);
|
||||
shape.erase(shape.begin() + axis);
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user