[Doc] Add Python comments for external models

docs/api_docs/python/face_detection.md

@@ -0,0 +1,34 @@
+# Face Detection API
+
+## fastdeploy.vision.facedet.RetinaFace
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.facedet.RetinaFace
+    :members:
+    :inherited-members:
+```
+
+
+## fastdeploy.vision.facedet.SCRFD
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.facedet.SCRFD
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.facedet.UltraFace
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.facedet.UltraFace
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.facedet.YOLOv5Face
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.facedet.YOLOv5Face
+    :members:
+    :inherited-members:
+```

docs/api_docs/python/face_recognition.md

@@ -0,0 +1,41 @@
+# Face Recognition API
+
+## fastdeploy.vision.faceid.AdaFace
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.faceid.AdaFace
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.faceid.CosFace
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.faceid.CosFace
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.faceid.ArcFace
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.faceid.ArcFace
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.faceid.PartialFC
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.faceid.PartialFC
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.faceid.VPL
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.faceid.VPL
+    :members:
+    :inherited-members:
+```

docs/api_docs/python/index.rst

@@ -18,4 +18,6 @@ FastDeploy
     image_classification.md
     keypoint_detection.md
     matting.md
+    face_recognition.md
+    face_detection.md
     vision_results_en.md

docs/api_docs/python/matting.md

@@ -1,3 +1,17 @@
 # Matting API
 
-comming soon...
+## fastdeploy.vision.matting.MODNet
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.matting.MODNet
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.matting.PPMatting
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.matting.PPMatting
+    :members:
+    :inherited-members:
+```

docs/api_docs/python/object_detection.md

@@ -63,3 +63,93 @@
     :members:
     :inherited-members:
 ```
+
+## fastdeploy.vision.detection.NanoDetPlus
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.NanoDetPlus
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.detection.ScaledYOLOv4
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.ScaledYOLOv4
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.detection.YOLOR
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOR
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.detection.YOLOv5
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOv5
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.detection.YOLOv5Lite
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOv5Lite
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.detection.YOLOv6
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOv6
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.detection.YOLOv7
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOv7
+    :members:
+    :inherited-members:
+```
+
+
+## fastdeploy.vision.detection.YOLOR
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOR
+    :members:
+    :inherited-members:
+```
+
+
+## fastdeploy.vision.detection.YOLOv7End2EndORT
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOv7End2EndORT
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.detection.YOLOv7End2EndTRT
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOv7End2EndTRT
+    :members:
+    :inherited-members:
+```
+
+## fastdeploy.vision.detection.YOLOX
+
+```{eval-rst}
+.. autoclass:: fastdeploy.vision.detection.YOLOX
+    :members:
+    :inherited-members:
+```

fastdeploy/vision/classification/contrib/resnet.h

@@ -25,7 +25,7 @@ namespace vision {
  *
  */
 namespace classification {
-/*! @brief ResNet series model
+/*! @brief Torchvision ResNet series model
  */
 class FASTDEPLOY_DECL ResNet : public FastDeployModel {
  public:
@@ -44,17 +44,18 @@ class FASTDEPLOY_DECL ResNet : public FastDeployModel {
   virtual std::string ModelName() const { return "ResNet"; }
    /** \brief Predict for the input "im", the result will be saved in "result".
    *
-   * \param[in] im Input image for inference.
+   * \param[in] im The input image data, comes from cv::imread(), is a 3-D array with layout HWC, BGR format
    * \param[in] result Saving the inference result.
    * \param[in] topk The length of return values, e.g., if topk==2, the result will include the 2 most possible class label for input image.
    */
   virtual bool Predict(cv::Mat* im, ClassifyResult* result, int topk = 1);
-
-  /// Tuple of (width, height)
+  /*! @brief
+  Argument for image preprocessing step, tuple of (width, height), decide the target size after resize
+  */
   std::vector<int> size;
-  /// Mean parameters for normalize
+  /// Mean parameters for normalize, size should be the the same as channels
   std::vector<float> mean_vals;
-  /// Std parameters for normalize
+  /// Std parameters for normalize, size should be the the same as channels
   std::vector<float> std_vals;
 
 

fastdeploy/vision/common/result.h

@@ -154,88 +154,117 @@ struct FASTDEPLOY_DECL OCRResult : public BaseResult {
   std::string Str();
 };
 
+/*! @brief Face detection result structure for all the face detection models
+ */
 struct FASTDEPLOY_DECL FaceDetectionResult : public BaseResult {
-  // box: xmin, ymin, xmax, ymax
+  /** \brief All the detected object boxes for an input image, the size of `boxes` is the number of detected objects, and the element of `boxes` is a array of 4 float values, means [xmin, ymin, xmax, ymax]
+   */
   std::vector<std::array<float, 4>> boxes;
-  // landmark: x, y, landmarks may empty if the
-  // model don't detect face with landmarks.
-  // Note, one face might have multiple landmarks,
-  // such as 5/19/21/68/98/..., etc.
+  /** \brief
+   * If the model detect face with landmarks, every detected object box correspoing to a landmark, which is a array of 2 float values, means location [x,y]
+  */
   std::vector<std::array<float, 2>> landmarks;
+  /** \brief
+   * Indicates the confidence of all targets detected from a single image, and the number of elements is consistent with boxes.size()
+   */
   std::vector<float> scores;
   ResultType type = ResultType::FACE_DETECTION;
-  // set landmarks_per_face manually in your post processes.
+  /** \brief
+   * `landmarks_per_face` indicates the number of face landmarks for each detected face
+   * if the model's output contains face landmarks (such as YOLOv5Face, SCRFD, ...)
+  */
   int landmarks_per_face;
 
   FaceDetectionResult() { landmarks_per_face = 0; }
   FaceDetectionResult(const FaceDetectionResult& res);
-
+  /// Clear detection result
   void Clear();
 
   void Reserve(int size);
 
   void Resize(int size);
-
+  /// Debug function, convert the result to string to print
   std::string Str();
 };
 
+/*! @brief Segmentation result structure for all the segmentation models
+ */
 struct FASTDEPLOY_DECL SegmentationResult : public BaseResult {
-  // mask
+  /** \brief
+   * `label_map` stores the pixel-level category labels for input image. the number of pixels is equal to label_map.size()
+  */
   std::vector<uint8_t> label_map;
+  /** \brief
+   * `score_map` stores the probability of the predicted label for each pixel of input image.
+  */
   std::vector<float> score_map;
+  /// The output shape, means [H, W]
   std::vector<int64_t> shape;
   bool contain_score_map = false;
 
   ResultType type = ResultType::SEGMENTATION;
-
+  /// Clear detection result
   void Clear();
 
   void Reserve(int size);
 
   void Resize(int size);
-
+  /// Debug function, convert the result to string to print
   std::string Str();
 };
 
+/*! @brief Face recognition result structure for all the Face recognition models
+ */
 struct FASTDEPLOY_DECL FaceRecognitionResult : public BaseResult {
-  // face embedding vector with 128/256/512 ... dim
+  /** \brief The feature embedding that represents the final extraction of the face recognition model can be used to calculate the feature similarity between faces.
+   */
   std::vector<float> embedding;
 
   ResultType type = ResultType::FACE_RECOGNITION;
 
   FaceRecognitionResult() {}
   FaceRecognitionResult(const FaceRecognitionResult& res);
-
+  /// Clear detection result
   void Clear();
 
   void Reserve(int size);
 
   void Resize(int size);
-
+  /// Debug function, convert the result to string to print
   std::string Str();
 };
 
+/*! @brief Matting result structure for all the Matting models
+ */
 struct FASTDEPLOY_DECL MattingResult : public BaseResult {
-  // alpha matte and fgr (predicted foreground: HWC/BGR float32)
+  /** \brief
+  `alpha` is a one-dimensional vector, which is the predicted alpha transparency value. The range of values is [0., 1.], and the length is hxw. h, w are the height and width of the input image
+  */
   std::vector<float> alpha;       // h x w
+  /** \brief
+  If the model can predict foreground, `foreground` save the predicted foreground image, the shape is [hight,width,channel] generally.
+  */
   std::vector<float> foreground;  // h x w x c (c=3 default)
-  // height, width, channel for foreground and alpha
-  // must be (h,w,c) and setup before Reserve and Resize
-  // c is only for foreground if contain_foreground is true.
+  /** \brief
+   * The shape of output result, when contain_foreground == false, shape only contains (h, w), when contain_foreground == true, shape contains (h, w, c), and c is generally 3
+   */
   std::vector<int64_t> shape;
+  /** \brief
+  If the model can predict alpha matte and foreground, contain_foreground = true, default false
+  */
   bool contain_foreground = false;
 
   ResultType type = ResultType::MATTING;
 
   MattingResult() {}
   MattingResult(const MattingResult& res);
-
+  /// Clear detection result
   void Clear();
 
   void Reserve(int size);
 
   void Resize(int size);
-
+  /// Debug function, convert the result to string to print
   std::string Str();
 };