[Other] Improve some PPOCR API comments. (#875)

* Fix links in readme

* Fix links in readme

* Update PPOCRv2/v3 examples

* Update auto compression configs

* Add neww quantization  support for paddleclas model

* Update quantized Yolov6s model download link

* Improve PPOCR comments

fastdeploy/vision/ocr/ppocr/classifier.h

@@ -43,11 +43,21 @@ class FASTDEPLOY_DECL Classifier : public FastDeployModel {
              const ModelFormat& model_format = ModelFormat::PADDLE);
   /// Get model's name
   std::string ModelName() const { return "ppocr/ocr_cls"; }
-  virtual bool Predict(const cv::Mat& img, int32_t* cls_label, float* cls_score);
+
+  /** \brief Predict the input image and get OCR classification model cls_result.
+   *
+   * \param[in] img The input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format.
+   * \param[in] cls_label The label result of cls model will be written in to this param.
+   * \param[in] cls_score The score result of cls model will be written in to this param.
+   * \return true if the prediction is successed, otherwise false.
+   */
+  virtual bool Predict(const cv::Mat& img,
+                      int32_t* cls_label, float* cls_score);
   /** \brief BatchPredict the input image and get OCR classification model cls_result.
    *
    * \param[in] images The list of input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format.
-   * \param[in] cls_results The output of OCR classification model cls_result will be writen to this structure.
+   * \param[in] cls_labels The label results of cls model will be written in to this vector.
+   * \param[in] cls_scores The score results of cls model will be written in to this vector.
    * \return true if the prediction is successed, otherwise false.
    */
   virtual bool BatchPredict(const std::vector<cv::Mat>& images,

fastdeploy/vision/ocr/ppocr/cls_postprocessor.h

@@ -28,8 +28,8 @@ class FASTDEPLOY_DECL ClassifierPostprocessor {
   /** \brief Process the result of runtime and fill to ClassifyResult structure
    *
    * \param[in] tensors The inference result from runtime
-   * \param[in] cls_labels The output result of classification
+   * \param[in] cls_labels The output label results of classification model
-   * \param[in] cls_scores The output result of classification
+   * \param[in] cls_scores The output score results of classification model
    * \return true if the postprocess successed, otherwise false
    */
   bool Run(const std::vector<FDTensor>& tensors,

fastdeploy/vision/ocr/ppocr/cls_preprocessor.h

@@ -26,8 +26,8 @@ class FASTDEPLOY_DECL ClassifierPreprocessor {
  public:
   /** \brief Process the input image and prepare input tensors for runtime
    *
-   * \param[in] images The input image data list, all the elements are returned by cv::imread()
+   * \param[in] images The input data list, all the elements are FDMat
-   * \param[in] outputs The output tensors which will feed in runtime
+   * \param[in] outputs The output tensors which will be fed into runtime
    * \return true if the preprocess successed, otherwise false
    */
   bool Run(std::vector<FDMat>* images, std::vector<FDTensor>* outputs);

fastdeploy/vision/ocr/ppocr/det_preprocessor.h

@@ -26,7 +26,7 @@ class FASTDEPLOY_DECL DBDetectorPreprocessor {
  public:
   /** \brief Process the input image and prepare input tensors for runtime
    *
-   * \param[in] images The input image data list, all the elements are returned by cv::imread()
+   * \param[in] images The input data list, all the elements are FDMat
    * \param[in] outputs The output tensors which will feed in runtime
    * \param[in] batch_det_img_info_ptr The output of preprocess
    * \return true if the preprocess successed, otherwise false

fastdeploy/vision/ocr/ppocr/rec_postprocessor.h

@@ -35,8 +35,8 @@ class FASTDEPLOY_DECL RecognizerPostprocessor {
   /** \brief Process the result of runtime and fill to RecognizerResult
    *
    * \param[in] tensors The inference result from runtime
-   * \param[in] texts The output result of recognizer
+   * \param[in] texts The output text results of recognizer
-   * \param[in] rec_scores The output result of recognizer
+   * \param[in] rec_scores The output score results of recognizer
    * \return true if the postprocess successed, otherwise false
    */
   bool Run(const std::vector<FDTensor>& tensors,

fastdeploy/vision/ocr/ppocr/rec_preprocessor.h

@@ -26,8 +26,8 @@ class FASTDEPLOY_DECL RecognizerPreprocessor {
  public:
   /** \brief Process the input image and prepare input tensors for runtime
    *
-   * \param[in] images The input image data list, all the elements are returned by cv::imread()
+   * \param[in] images The input data list, all the elements are FDMat
-   * \param[in] outputs The output tensors which will feed in runtime
+   * \param[in] outputs The output tensors which will be fed into runtime
    * \return true if the preprocess successed, otherwise false
    */
   bool Run(std::vector<FDMat>* images, std::vector<FDTensor>* outputs);

fastdeploy/vision/ocr/ppocr/recognizer.h

@@ -45,11 +45,19 @@ class FASTDEPLOY_DECL Recognizer : public FastDeployModel {
              const ModelFormat& model_format = ModelFormat::PADDLE);
   /// Get model's name
   std::string ModelName() const { return "ppocr/ocr_rec"; }
+  /** \brief Predict the input image and get OCR recognition model result.
+   *
+   * \param[in] img The input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format.
+   * \param[in] text The text result of rec model will be written into this parameter.
+   * \param[in] rec_score The sccore result of rec model will be written into this parameter.
+   * \return true if the prediction is successed, otherwise false.
+   */
   virtual bool Predict(const cv::Mat& img, std::string* text, float* rec_score);
   /** \brief BatchPredict the input image and get OCR recognition model result.
    *
    * \param[in] images The list of input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format.
-   * \param[in] rec_results The output of OCR recognition model result will be writen to this structure.
+   * \param[in] texts The list of text results of rec model will be written into this vector.
+   * \param[in] rec_scores The list of sccore result of rec model will be written into this vector.
    * \return true if the prediction is successed, otherwise false.
    */
   virtual bool BatchPredict(const std::vector<cv::Mat>& images,