-
Notifications
You must be signed in to change notification settings - Fork 728
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[ORT][TRT] support FaceFusion #445
Conversation
typedef _ONNXYOLOFaceNet YOLOV8Face; | ||
typedef _ONNXFace_Swap InSwapper; | ||
typedef _ONNXFace_Restoration GFPGAN; | ||
typedef _ONNXFace_68Landmarks Face_68Landmarks; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这几个新增了类都属于FaceFusion系列,建议改成FaceFusion68Landmarks, FaceFusionRecognizer, FaceFusionSwap, FaceFusionRestoration, FaceFusionPipeline的风格。本仓库class名称采用驼峰法风格,不采用下划线。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
preprocessed_mat.convertTo(preprocessed_mat,CV_32FC3,1.0 / 255.f); | ||
preprocessed_mat.convertTo(preprocessed_mat,CV_32FC3,1.0 / 1.f,0); | ||
|
||
std::vector<float> model_martix = face_utils::load_npy("/home/facefusion-onnxrun/python/model_matrix.npy"); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这里写了某个绝对路径,是否要修改?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
我现在在测试大佬 我准备做完多线程的之后 再一次性全部修复 先不 merge
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
好的
…switch of TensorRT
…CUDA version of NMS implementation.
This pull request introduces new features and updates to the face recognition and manipulation functionalities in the project. It includes the addition of several new face-related models and their corresponding test files, as well as updates to the CMake configuration for these new models.
New Features:
face_68landmarks
(lite/ort/cv/face_68landmarks.h
,lite/ort/cv/face_68landmarks.cpp
) [1] [2]face_recognizer
(lite/ort/cv/face_recognizer.h
,lite/ort/cv/face_recognizer.cpp
)face_restoration
(lite/ort/cv/face_restoration.h
,lite/ort/cv/face_restoration.cpp
)face_swap
(lite/ort/cv/face_swap.h
,lite/ort/cv/face_swap.cpp
)face_fusion_pipeline
(lite/ort/cv/face_fusion_pipeline.h
,lite/ort/cv/face_fusion_pipeline.cpp
) [1] [2]Updates to CMake Configuration:
OpenCV_LIBS
variable to includeopencv_calib3d
incmake/opencv.cmake
.examples/lite/CMakeLists.txt
.Test Files:
test_lite_face_68landmarks.cpp
test_lite_face_recognizer.cpp
test_lite_face_restoration.cpp
test_lite_face_swap.cpp
test_lite_facefusion_pipeline.cpp
Header File Updates:
lite/models.h
to include the new face-related models and their typedefs. [1] [2] [3] [4]