Update PaddleClas and PaddleSeg doc

examples/vision/classification/paddleclas/cpp/README.md

@@ -1,76 +1,75 @@
-# YOLOv7 C++部署示例
+# PaddleClas C++部署示例
 
-本目录下提供`infer.cc`快速完成YOLOv7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PaddleClas系列模型在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/quick_start/requirements.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/compile/prebuilt_libraries.md)
 
-以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
+以Linux上ResNet50_vd推理为例，在本目录执行如下命令即可完成编译测试
 
 ```
+#下载SDK，编译模型examples代码（SDK中包含了examples代码）
+wget https://bj.bcebos.com/paddlehub/fastdeploy/libs/0.2.0/fastdeploy-linux-x64-gpu-0.2.0.tgz
+tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz
+cd fastdeploy-linux-x64-gpu-0.2.0/examples/vision/classification/paddleclas/cpp
 mkdir build
 cd build
-wget https://xxx.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../fastdeploy-linux-x64-gpu-0.2.0 
 make -j
 
-#下载官方转换好的yolov7模型文件和测试图片
-wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
-wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000087038.jpg
+# 下载ResNet50_vd模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/ResNet50_vd_infer.tgz
+tar -xvf ResNet50_vd_infer.tgz
+wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
 
 
 # CPU推理
-./infer_demo yolov7.onnx 000000087038.jpg 0
+./infer_demo ResNet50_vd_infer ILSVRC2012_val_00000010.jpeg 0
 # GPU推理
-./infer_demo yolov7.onnx 000000087038.jpg 1
+./infer_demo ResNet50_vd_infer ILSVRC2012_val_00000010.jpeg 1
 # GPU上TensorRT推理
-./infer_demo yolov7.onnx 000000087038.jpg 2
+./infer_demo ResNet50_vd_infer ILSVRC2012_val_00000010.jpeg 2
 ```
 
-## YOLOv7 C++接口
+## PaddleClas C++接口
 
-### YOLOv7类
+### PaddleClas类
 
 ```
-fastdeploy::vision::detection::YOLOv7(
+fastdeploy::vision::classification::PaddleClasModel(
         const string& model_file,
-        const string& params_file = "",
+        const string& params_file,
+        const string& config_file,
         const RuntimeOption& runtime_option = RuntimeOption(),
-        const Frontend& model_format = Frontend::ONNX)
+        const Frontend& model_format = Frontend::PADDLE)
 ```
 
-YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式。
+PaddleClas模型加载和初始化，其中model_file, params_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/PaddleClas/blob/release/2.4/docs/zh_CN/inference_deployment/export_model.md#2-%E5%88%86%E7%B1%BB%E6%A8%A1%E5%9E%8B%E5%AF%BC%E5%87%BA)
 
 **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时，此参数传入空字符串即可
+> * **params_file**(str): 参数文件路径
+> * **config_file**(str): 推理部署配置文件
 > * **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格式
+> * **model_format**(Frontend): 模型格式，默认为Paddle格式
 
 #### Predict函数
 
 > ```
-> YOLOv7::Predict(cv::Mat* im, DetectionResult* result,
->                 float conf_threshold = 0.25,
->                 float nms_iou_threshold = 0.5)
+> PaddleClasModel::Predict(cv::Mat* im, ClassifyResult* result, int topk = 1)
 > ```
 > 
 > 模型预测接口，输入图像直接输出检测结果。
 > 
 > **参数**
 > 
 > > * **im**: 输入图像，注意需为HWC，BGR格式
-> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
-> > * **conf_threshold**: 检测框置信度过滤阈值
-> > * **nms_iou_threshold**: NMS处理过程中iou阈值
+> > * **result**: 分类结果，包括label_id，以及相应的置信度, ClassifyResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
+> > * **topk**(int):返回预测概率最高的topk个分类结果，默认为1
 
-### 类成员变量
-
-> > * **size**(vector<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[640, 640]
 
 - [模型介绍](../../)
 - [Python部署](../python)

examples/vision/classification/paddleclas/cpp/infer.cc

@@ -13,80 +13,95 @@
 // limitations under the License.
 
 #include "fastdeploy/vision.h"
+#ifdef WIN32
+const char sep = '\\';
+#else
+const char sep = '/';
+#endif
 
-void CpuInfer(const std::string& model_file, const std::string& image_file) {
-  auto model = fastdeploy::vision::detection::YOLOv7(model_file);
+void CpuInfer(const std::string& model_dir, const std::string& image_file) {
+  auto model_file = model_dir + sep + "inference.pdmodel";
+  auto params_file = model_dir + sep + "inference.pdiparams";
+  auto config_file = model_dir + sep + "inference_cls.yaml";
+
+  auto option = fastdeploy::RuntimeOption();
+  option.UseCpu();
+  auto model = fastdeploy::vision::classification::PaddleClasModel(
+      model_file, params_file, config_file, option);
   if (!model.Initialized()) {
     std::cerr << "Failed to initialize." << std::endl;
     return;
   }
 
   auto im = cv::imread(image_file);
-  auto im_bak = im.clone();
 
-  fastdeploy::vision::DetectionResult res;
+  fastdeploy::vision::ClassifyResult res;
   if (!model.Predict(&im, &res)) {
     std::cerr << "Failed to predict." << std::endl;
     return;
   }
 
-  auto vis_im = fastdeploy::vision::Visualize::VisDetection(im_bak, res);
-  cv::imwrite("vis_result.jpg", vis_im);
-  std::cout << "Visualized result saved in ./vis_result.jpg" << std::endl;
+  // print res
+  std::cout << res.Str() << std::endl;
 }
 
-void GpuInfer(const std::string& model_file, const std::string& image_file) {
+void GpuInfer(const std::string& model_dir, const std::string& image_file) {
+  auto model_file = model_dir + sep + "inference.pdmodel";
+  auto params_file = model_dir + sep + "inference.pdiparams";
+  auto config_file = model_dir + sep + "inference_cls.yaml";
   auto option = fastdeploy::RuntimeOption();
   option.UseGpu();
-  auto model = fastdeploy::vision::detection::YOLOv7(model_file, "", option);
+  auto model = fastdeploy::vision::classification::PaddleClasModel(
+      model_file, params_file, config_file, option);
   if (!model.Initialized()) {
     std::cerr << "Failed to initialize." << std::endl;
     return;
   }
 
   auto im = cv::imread(image_file);
-  auto im_bak = im.clone();
 
-  fastdeploy::vision::DetectionResult res;
+  fastdeploy::vision::ClassifyResult res;
   if (!model.Predict(&im, &res)) {
     std::cerr << "Failed to predict." << std::endl;
     return;
   }
 
-  auto vis_im = fastdeploy::vision::Visualize::VisDetection(im_bak, res);
-  cv::imwrite("vis_result.jpg", vis_im);
-  std::cout << "Visualized result saved in ./vis_result.jpg" << std::endl;
+  // print res
+  std::cout << res.Str() << std::endl;
 }
 
-void TrtInfer(const std::string& model_file, const std::string& image_file) {
+void TrtInfer(const std::string& model_dir, const std::string& image_file) {
+  auto model_file = model_dir + sep + "inference.pdmodel";
+  auto params_file = model_dir + sep + "inference.pdiparams";
+  auto config_file = model_dir + sep + "inference_cls.yaml";
   auto option = fastdeploy::RuntimeOption();
   option.UseGpu();
   option.UseTrtBackend();
-  option.SetTrtInputShape("images", {1, 3, 640, 640});
-  auto model = fastdeploy::vision::detection::YOLOv7(model_file, "", option);
+  option.SetTrtInputShape("inputs", {1, 3, 224, 224}, {1, 3, 224, 224},
+                          {1, 3, 224, 224});
+  auto model = fastdeploy::vision::classification::PaddleClasModel(
+      model_file, params_file, config_file, option);
   if (!model.Initialized()) {
     std::cerr << "Failed to initialize." << std::endl;
     return;
   }
 
   auto im = cv::imread(image_file);
-  auto im_bak = im.clone();
 
-  fastdeploy::vision::DetectionResult res;
+  fastdeploy::vision::ClassifyResult res;
   if (!model.Predict(&im, &res)) {
     std::cerr << "Failed to predict." << std::endl;
     return;
   }
 
-  auto vis_im = fastdeploy::vision::Visualize::VisDetection(im_bak, res);
-  cv::imwrite("vis_result.jpg", vis_im);
-  std::cout << "Visualized result saved in ./vis_result.jpg" << std::endl;
+  // print res
+  std::cout << res.Str() << std::endl;
 }
 
 int main(int argc, char* argv[]) {
   if (argc < 4) {
     std::cout << "Usage: infer_demo path/to/model path/to/image run_option, "
-                 "e.g ./infer_model ./yolov7.onnx ./test.jpeg 0"
+                 "e.g ./infer_demo ./ResNet50_vd ./test.jpeg 0"
               << std::endl;
     std::cout << "The data type of run_option is int, 0: run with cpu; 1: run "
                  "with gpu; 2: run with gpu and use tensorrt backend."

examples/vision/classification/paddleclas/python/README.md

@@ -61,7 +61,7 @@ PaddleClas模型加载和初始化，其中model_file, params_file为训练模
 > **参数**
 > 
 > > * **input_image**(np.ndarray): 输入数据，注意需为HWC，BGR格式
-> > * **topk**(int):返回预测概率最高的topk个分类结果
+> > * **topk**(int):返回预测概率最高的topk个分类结果，默认为1
 
 > **返回**
 >