mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 16:48:03 +08:00

* 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) * first commit test photo * yolov7 doc * yolov7 doc * yolov7 doc * yolov7 doc * add yolov5 docs * modify yolov5 doc * first commit for retinaface * first commit for retinaface * firt commit for ultraface * firt commit for ultraface * firt commit for yolov5face * firt commit for modnet and arcface * firt commit for modnet and arcface * first commit for partial_fc * first commit for partial_fc * first commit for yolox * first commit for yolov6 * first commit for nano_det * first commit for scrfd * first commit for scrfd * first commit for retinaface * first commit for ultraface * first commit for yolov5face * first commit for yolox yolov6 nano * rm jpg * first commit for modnet and modify nano * yolor scaledyolov4 v5lite * first commit for insightface * first commit for insightface * first commit for insightface * docs * docs * docs * docs * docs * add print for detect and modify docs * docs * docs * docs * docs test for insightface * docs test for insightface again * docs test for insightface * modify all wrong expressions in docs * modify all wrong expressions in docs * modify all wrong expressions in docs * modify all wrong expressions in docs * modify docs expressions * fix expression of detection part * fix expression of detection part * fix expression of detection part 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>
InsightFace Python部署示例
本目录下提供infer_xxx.py快速完成InsighFace模型包括ArcFace\CosFace\VPL\Partial_FC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
-
- 软硬件环境满足要求,参考FastDeploy环境要求
-
- FastDeploy Python whl包安装,参考FastDeploy Python安装
以ArcFace为例子, 提供infer_arcface.py
快速完成ArcFace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
#下载ArcFace模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_arcface_r100.onnx
wget https://bj.bcebos.com/paddlehub/test_samples/test_lite_focal_arcface_0.JPG
wget https://bj.bcebos.com/paddlehub/test_samples/test_lite_focal_arcface_1.JPG
wget https://bj.bcebos.com/paddlehub/test_samples/test_lite_focal_arcface_2.JPG
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vison/faceid/insightface/python/
# CPU推理
python infer_arcface.py --model ms1mv3_arcface_r100.onnx --face test_lite_focal_arcface_0.JPG --face_positive test_lite_focal_arcface_1.JPG --face_negative test_lite_focal_arcface_2.JPG --device cpu
# GPU推理
python infer_arcface.py --model ms1mv3_arcface_r100.onnx --face test_lite_focal_arcface_0.JPG --face_positive test_lite_focal_arcface_1.JPG --face_negative test_lite_focal_arcface_2.JPG --device gpu
# GPU上使用TensorRT推理
python infer_arcface.py --model ms1mv3_arcface_r100.onnx --face test_lite_focal_arcface_0.JPG --face_positive test_lite_focal_arcface_1.JPG --face_negative test_lite_focal_arcface_2.JPG --device gpu --use_trt True
运行完成可视化结果如下图所示
Prediction Done!
--- [Face 0]:FaceRecognitionResult: [Dim(512), Min(-2.309220), Max(2.372197), Mean(0.016987)]
--- [Face 1]:FaceRecognitionResult: [Dim(512), Min(-2.288258), Max(1.995104), Mean(-0.003400)]
--- [Face 2]:FaceRecognitionResult: [Dim(512), Min(-3.243411), Max(3.875866), Mean(-0.030682)]
Detect Done! Cosine 01: 0.814385, Cosine 02:-0.059388
InsightFace Python接口
fastdeploy.vision.faceid.ArcFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
fastdeploy.vision.faceid.CosFace(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
fastdeploy.vision.faceid.PartialFC(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
fastdeploy.vision.faceid.VPL(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
ArcFace模型加载和初始化,其中model_file为导出的ONNX模型格式
参数
- model_file(str): 模型文件路径
- params_file(str): 参数文件路径,当模型格式为ONNX格式时,此参数无需设定
- runtime_option(RuntimeOption): 后端推理配置,默认为None,即采用默认配置
- model_format(Frontend): 模型格式,默认为ONNX
predict函数
ArcFace.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
模型预测结口,输入图像直接输出检测结果。
参数
- image_data(np.ndarray): 输入数据,注意需为HWC,BGR格式
- conf_threshold(float): 检测框置信度过滤阈值
- nms_iou_threshold(float): NMS处理过程中iou阈值
返回
返回
fastdeploy.vision.FaceRecognitionResult
结构体,结构体说明参考文档视觉模型预测结果
类成员属性
预处理参数
用户可按照自己的实际需求,修改下列预处理参数,从而影响最终的推理和部署效果
- size(list[int]): 通过此参数修改预处理过程中resize的大小,包含两个整型元素,表示[width, height], 默认值为[112, 112]
- alpha(list[float]): 预处理归一化的alpha值,计算公式为
x'=x*alpha+beta
,alpha默认为[1. / 127.5, 1.f / 127.5, 1. / 127.5]- beta(list[float]): 预处理归一化的beta值,计算公式为
x'=x*alpha+beta
,beta默认为[-1.f, -1.f, -1.f]- swap_rb(bool): 预处理是否将BGR转换成RGB,默认True
- l2_normalize(bool): 输出人脸向量之前是否执行l2归一化,默认False