[Model] Add YOLOv5-seg (#988)

* add onnx_ort_runtime demo * rm in requirements * support batch eval * fixed MattingResults bug * move assignment for DetectionResult * integrated x2paddle * add model convert readme * update readme * re-lint * add processor api * Add MattingResult Free * change valid_cpu_backends order * add ppocr benchmark * mv bs from 64 to 32 * fixed quantize.md * fixed quantize bugs * Add Monitor for benchmark * update mem monitor * Set trt_max_batch_size default 1 * fixed ocr benchmark bug * support yolov5 in serving * Fixed yolov5 serving * Fixed postprocess * update yolov5 to 7.0 * add poros runtime demos * update readme * Support poros abi=1 * rm useless note * deal with comments * support pp_trt for ppseg * fixed symlink problem * Add is_mini_pad and stride for yolov5 * Add yolo series for paddle format * fixed bugs * fixed bug * support yolov5seg * fixed bug * refactor yolov5seg * fixed bug * mv Mask int32 to uint8 * add yolov5seg example * rm log info * fixed code style * add yolov5seg example in python * fixed dtype bug * update note * deal with comments * get sorted index * add yolov5seg test case * Add GPL-3.0 License * add round func * deal with comments * deal with commens Co-authored-by: Jason <jiangjiajun@baidu.com>
2025-10-12 20:11:20 +08:00 · 2023-01-11 15:36:32 +08:00
parent 60e6a12b93
commit aa6931bee9
28 changed files with 1607 additions and 33 deletions
--- a/fastdeploy/vision/detection/contrib/yolov5seg/yolov5seg_pybind.cc
+++ b/fastdeploy/vision/detection/contrib/yolov5seg/yolov5seg_pybind.cc
@@ -0,0 +1,90 @@
+// Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+#include "fastdeploy/pybind/main.h"
+
+namespace fastdeploy {
+void BindYOLOv5Seg(pybind11::module& m) {
+  pybind11::class_<vision::detection::YOLOv5SegPreprocessor>(
+      m, "YOLOv5SegPreprocessor")
+      .def(pybind11::init<>())
+      .def("run", [](vision::detection::YOLOv5SegPreprocessor& self, std::vector<pybind11::array>& im_list) {
+        std::vector<vision::FDMat> images;
+        for (size_t i = 0; i < im_list.size(); ++i) {
+          images.push_back(vision::WrapMat(PyArrayToCvMat(im_list[i])));
+        }
+        std::vector<FDTensor> outputs;
+        std::vector<std::map<std::string, std::array<float, 2>>> ims_info;
+        if (!self.Run(&images, &outputs, &ims_info)) {
+          throw std::runtime_error("Failed to preprocess the input data in PaddleClasPreprocessor.");
+        }
+        for (size_t i = 0; i < outputs.size(); ++i) {
+          outputs[i].StopSharing();
+        }
+        return make_pair(outputs, ims_info);
+      })
+      .def_property("size", &vision::detection::YOLOv5SegPreprocessor::GetSize, &vision::detection::YOLOv5SegPreprocessor::SetSize)
+      .def_property("padding_value", &vision::detection::YOLOv5SegPreprocessor::GetPaddingValue, &vision::detection::YOLOv5SegPreprocessor::SetPaddingValue)
+      .def_property("is_scale_up", &vision::detection::YOLOv5SegPreprocessor::GetScaleUp, &vision::detection::YOLOv5SegPreprocessor::SetScaleUp)
+      .def_property("is_mini_pad", &vision::detection::YOLOv5SegPreprocessor::GetMiniPad, &vision::detection::YOLOv5SegPreprocessor::SetMiniPad)
+      .def_property("stride", &vision::detection::YOLOv5SegPreprocessor::GetStride, &vision::detection::YOLOv5SegPreprocessor::SetStride);
+
+  pybind11::class_<vision::detection::YOLOv5SegPostprocessor>(
+      m, "YOLOv5SegPostprocessor")
+      .def(pybind11::init<>())
+      .def("run", [](vision::detection::YOLOv5SegPostprocessor& self, std::vector<FDTensor>& inputs,
+                     const std::vector<std::map<std::string, std::array<float, 2>>>& ims_info) {
+        std::vector<vision::DetectionResult> results;
+        if (!self.Run(inputs, &results, ims_info)) {
+          throw std::runtime_error("Failed to postprocess the runtime result in YOLOv5SegPostprocessor.");
+        }
+        return results;
+      })
+      .def("run", [](vision::detection::YOLOv5SegPostprocessor& self, std::vector<pybind11::array>& input_array,
+                     const std::vector<std::map<std::string, std::array<float, 2>>>& ims_info) {
+        std::vector<vision::DetectionResult> results;
+        std::vector<FDTensor> inputs;
+        PyArrayToTensorList(input_array, &inputs, /*share_buffer=*/true);
+        if (!self.Run(inputs, &results, ims_info)) {
+          throw std::runtime_error("Failed to postprocess the runtime result in YOLOv5SegPostprocessor.");
+        }
+        return results;
+      })
+      .def_property("conf_threshold", &vision::detection::YOLOv5SegPostprocessor::GetConfThreshold, &vision::detection::YOLOv5SegPostprocessor::SetConfThreshold)
+      .def_property("nms_threshold", &vision::detection::YOLOv5SegPostprocessor::GetNMSThreshold, &vision::detection::YOLOv5SegPostprocessor::SetNMSThreshold)
+      .def_property("multi_label", &vision::detection::YOLOv5SegPostprocessor::GetMultiLabel, &vision::detection::YOLOv5SegPostprocessor::SetMultiLabel);
+
+  pybind11::class_<vision::detection::YOLOv5Seg, FastDeployModel>(m, "YOLOv5Seg")
+      .def(pybind11::init<std::string, std::string, RuntimeOption,
+                          ModelFormat>())
+      .def("predict",
+           [](vision::detection::YOLOv5Seg& self, pybind11::array& data) {
+             auto mat = PyArrayToCvMat(data);
+             vision::DetectionResult res;
+             self.Predict(mat, &res);
+             return res;
+           })
+      .def("batch_predict", [](vision::detection::YOLOv5Seg& self, std::vector<pybind11::array>& data) {
+        std::vector<cv::Mat> images;
+        for (size_t i = 0; i < data.size(); ++i) {
+          images.push_back(PyArrayToCvMat(data[i]));
+        }
+        std::vector<vision::DetectionResult> results;
+        self.BatchPredict(images, &results);
+        return results;
+      })
+      .def_property_readonly("preprocessor", &vision::detection::YOLOv5Seg::GetPreprocessor)
+      .def_property_readonly("postprocessor", &vision::detection::YOLOv5Seg::GetPostprocessor);
+}
+}  // namespace fastdeploy