Parser's parameters renaming.

depthai_nodes/ml/parsers/keypoints.py

@@ -17,7 +17,7 @@ class KeypointParser(dai.node.ThreadedHostNode):
         Parser sends the processed network results to this output in a form of DepthAI message. It is a linking point from which the processed network results are retrieved.
     scale_factor : float
         Scale factor to divide the keypoints by.
-    num_keypoints : int
+    n_keypoints : int
         Number of keypoints the model detects.
 
     Output Message/s
@@ -38,21 +38,21 @@ class KeypointParser(dai.node.ThreadedHostNode):
     def __init__(
         self,
         scale_factor=1,
-        num_keypoints=None,
+        n_keypoints=None,
     ):
         """Initializes KeypointParser node.
 
         @param scale_factor: Scale factor to divide the keypoints by.
         @type scale_factor: float
-        @param num_keypoints: Number of keypoints.
-        @type num_keypoints: int
+        @param n_keypoints: Number of keypoints.
+        @type n_keypoints: int
         """
         dai.node.ThreadedHostNode.__init__(self)
         self.input = dai.Node.Input(self)
         self.out = dai.Node.Output(self)
 
         self.scale_factor = scale_factor
-        self.num_keypoints = num_keypoints
+        self.n_keypoints = n_keypoints
 
     def setScaleFactor(self, scale_factor):
         """Sets the scale factor to divide the keypoints by.
@@ -62,16 +62,16 @@ def setScaleFactor(self, scale_factor):
         """
         self.scale_factor = scale_factor
 
-    def setNumKeypoints(self, num_keypoints):
+    def setNumKeypoints(self, n_keypoints):
         """Sets the number of keypoints.
 
-        @param num_keypoints: Number of keypoints.
-        @type num_keypoints: int
+        @param n_keypoints: Number of keypoints.
+        @type n_keypoints: int
         """
-        self.num_keypoints = num_keypoints
+        self.n_keypoints = n_keypoints
 
     def run(self):
-        if self.num_keypoints is None:
+        if self.n_keypoints is None:
             raise ValueError("Number of keypoints must be specified!")
 
         while self.isRunning():
@@ -90,14 +90,14 @@ def run(self):
             keypoints = output.getTensor(output_layer_names[0], dequantize=True).astype(
                 np.float32
             )
-            num_coords = int(np.prod(keypoints.shape) / self.num_keypoints)
+            num_coords = int(np.prod(keypoints.shape) / self.n_keypoints)
 
             if num_coords not in [2, 3]:
                 raise ValueError(
                     f"Expected 2 or 3 coordinates per keypoint, got {num_coords}."
                 )
 
-            keypoints = keypoints.reshape(self.num_keypoints, num_coords)
+            keypoints = keypoints.reshape(self.n_keypoints, num_coords)
 
             keypoints /= self.scale_factor
 

depthai_nodes/ml/parsers/mediapipe_palm_detection.py

@@ -17,11 +17,11 @@ class MPPalmDetectionParser(dai.node.ThreadedHostNode):
         Node's input. It is a linking point to which the Neural Network's output is linked. It accepts the output of the Neural Network node.
     out : Node.Output
         Parser sends the processed network results to this output in a form of DepthAI message. It is a linking point from which the processed network results are retrieved.Parser sends the processed network results to this output in form of messages. It is a linking point from which the processed network results are retrieved.
-    score_threshold : float
+    conf_threshold : float
         Confidence score threshold for detected hands.
-    nms_threshold : float
+    iou_threshold : float
         Non-maximum suppression threshold.
-    top_k : int
+    max_det : int
         Maximum number of detections to keep.
 
     Output Message/s
@@ -36,47 +36,47 @@ class MPPalmDetectionParser(dai.node.ThreadedHostNode):
     https://ai.google.dev/edge/mediapipe/solutions/vision/hand_landmarker
     """
 
-    def __init__(self, score_threshold=0.5, nms_threshold=0.5, top_k=100):
+    def __init__(self, conf_threshold=0.5, iou_threshold=0.5, max_det=100):
         """Initializes the MPPalmDetectionParser node.
 
-        @param score_threshold: Confidence score threshold for detected hands.
-        @type score_threshold: float
-        @param nms_threshold: Non-maximum suppression threshold.
-        @type nms_threshold: float
-        @param top_k: Maximum number of detections to keep.
-        @type top_k: int
+        @param conf_threshold: Confidence score threshold for detected hands.
+        @type conf_threshold: float
+        @param iou_threshold: Non-maximum suppression threshold.
+        @type iou_threshold: float
+        @param max_det: Maximum number of detections to keep.
+        @type max_det: int
         """
         dai.node.ThreadedHostNode.__init__(self)
         self.input = dai.Node.Input(self)
         self.out = dai.Node.Output(self)
 
-        self.score_threshold = score_threshold
-        self.nms_threshold = nms_threshold
-        self.top_k = top_k
+        self.conf_threshold = conf_threshold
+        self.iou_threshold = iou_threshold
+        self.max_det = max_det
 
     def setConfidenceThreshold(self, threshold):
         """Sets the confidence score threshold for detected hands.
 
         @param threshold: Confidence score threshold for detected hands.
         @type threshold: float
         """
-        self.score_threshold = threshold
+        self.conf_threshold = threshold
 
-    def setNMSThreshold(self, threshold):
+    def setIOUThreshold(self, threshold):
         """Sets the non-maximum suppression threshold.
 
         @param threshold: Non-maximum suppression threshold.
         @type threshold: float
         """
-        self.nms_threshold = threshold
+        self.iou_threshold = threshold
 
-    def setTopK(self, top_k):
+    def setMaxDetections(self, max_det):
         """Sets the maximum number of detections to keep.
 
-        @param top_k: Maximum number of detections to keep.
-        @type top_k: int
+        @param max_det: Maximum number of detections to keep.
+        @type max_det: int
         """
-        self.top_k = top_k
+        self.max_det = max_det
 
     def run(self):
         while self.isRunning():
@@ -97,7 +97,7 @@ def run(self):
             )
 
             decoded_bboxes = generate_anchors_and_decode(
-                bboxes=bboxes, scores=scores, threshold=self.score_threshold, scale=192
+                bboxes=bboxes, scores=scores, threshold=self.conf_threshold, scale=192
             )
 
             bboxes = []
@@ -116,9 +116,9 @@ def run(self):
             indices = cv2.dnn.NMSBoxes(
                 bboxes,
                 scores,
-                self.score_threshold,
-                self.nms_threshold,
-                top_k=self.top_k,
+                self.conf_threshold,
+                self.iou_threshold,
+                top_k=self.max_det,
             )
             bboxes = np.array(bboxes)[indices]
             scores = np.array(scores)[indices]

depthai_nodes/ml/parsers/scrfd.py

@@ -14,11 +14,11 @@ class SCRFDParser(dai.node.ThreadedHostNode):
         Node's input. It is a linking point to which the Neural Network's output is linked. It accepts the output of the Neural Network node.
     out : Node.Output
         Parser sends the processed network results to this output in a form of DepthAI message. It is a linking point from which the processed network results are retrieved.
-    score_threshold : float
+    conf_threshold : float
         Confidence score threshold for detected faces.
-    nms_threshold : float
+    iou_threshold : float
         Non-maximum suppression threshold.
-    top_k : int
+    max_det : int
         Maximum number of detections to keep.
     feat_stride_fpn : tuple
         Tuple of the feature strides.
@@ -36,21 +36,21 @@ class SCRFDParser(dai.node.ThreadedHostNode):
 
     def __init__(
         self,
-        score_threshold=0.5,
-        nms_threshold=0.5,
-        top_k=100,
+        conf_threshold=0.5,
+        iou_threshold=0.5,
+        max_det=100,
         input_size=(640, 640),
         feat_stride_fpn=(8, 16, 32),
         num_anchors=2,
     ):
         """Initializes the SCRFDParser node.
 
-        @param score_threshold: Confidence score threshold for detected faces.
-        @type score_threshold: float
-        @param nms_threshold: Non-maximum suppression threshold.
-        @type nms_threshold: float
-        @param top_k: Maximum number of detections to keep.
-        @type top_k: int
+        @param conf_threshold: Confidence score threshold for detected faces.
+        @type conf_threshold: float
+        @param iou_threshold: Non-maximum suppression threshold.
+        @type iou_threshold: float
+        @param max_det: Maximum number of detections to keep.
+        @type max_det: int
         @param feat_stride_fpn: List of the feature strides.
         @type feat_stride_fpn: tuple
         @param num_anchors: Number of anchors.
@@ -62,9 +62,9 @@ def __init__(
         self.input = dai.Node.Input(self)
         self.out = dai.Node.Output(self)
 
-        self.score_threshold = score_threshold
-        self.nms_threshold = nms_threshold
-        self.top_k = top_k
+        self.conf_threshold = conf_threshold
+        self.iou_threshold = iou_threshold
+        self.max_det = max_det
 
         self.feat_stride_fpn = feat_stride_fpn
         self.num_anchors = num_anchors
@@ -76,23 +76,23 @@ def setConfidenceThreshold(self, threshold):
         @param threshold: Confidence score threshold for detected faces.
         @type threshold: float
         """
-        self.score_threshold = threshold
+        self.conf_threshold = threshold
 
-    def setNMSThreshold(self, threshold):
+    def setIOUThreshold(self, threshold):
         """Sets the non-maximum suppression threshold.
 
         @param threshold: Non-maximum suppression threshold.
         @type threshold: float
         """
-        self.nms_threshold = threshold
+        self.iou_threshold = threshold
 
-    def setTopK(self, top_k):
+    def setMaxDetections(self, max_det):
         """Sets the maximum number of detections to keep.
 
-        @param top_k: Maximum number of detections to keep.
-        @type top_k: int
+        @param max_det: Maximum number of detections to keep.
+        @type max_det: int
         """
-        self.top_k = top_k
+        self.max_det = max_det
 
     def setFeatStrideFPN(self, feat_stride_fpn):
         """Sets the feature stride of the FPN.
@@ -173,8 +173,8 @@ def run(self):
                 feat_stride_fpn=self.feat_stride_fpn,
                 input_size=self.input_size,
                 num_anchors=self.num_anchors,
-                score_threshold=self.score_threshold,
-                nms_threshold=self.nms_threshold,
+                score_threshold=self.conf_threshold,
+                nms_threshold=self.iou_threshold,
             )
             detection_msg = create_detection_message(
                 bboxes, scores, None, keypoints.tolist()

depthai_nodes/ml/parsers/yunet.py

@@ -17,11 +17,11 @@ class YuNetParser(dai.node.ThreadedHostNode):
         Node's input. It is a linking point to which the Neural Network's output is linked. It accepts the output of the Neural Network node.
     out : Node.Output
         Parser sends the processed network results to this output in a form of DepthAI message. It is a linking point from which the processed network results are retrieved.
-    score_threshold : float
+    conf_threshold : float
         Confidence score threshold for detected faces.
-    nms_threshold : float
+    iou_threshold : float
         Non-maximum suppression threshold.
-    top_k : int
+    max_det : int
         Maximum number of detections to keep.
 
     Output Message/s
@@ -33,50 +33,50 @@ class YuNetParser(dai.node.ThreadedHostNode):
 
     def __init__(
         self,
-        score_threshold=0.6,
-        nms_threshold=0.3,
-        top_k=5000,
+        conf_threshold=0.6,
+        iou_threshold=0.3,
+        max_det=5000,
     ):
         """Initializes the YuNetParser node.
 
-        @param score_threshold: Confidence score threshold for detected faces.
-        @type score_threshold: float
-        @param nms_threshold: Non-maximum suppression threshold.
-        @type nms_threshold: float
-        @param top_k: Maximum number of detections to keep.
-        @type top_k: int
+        @param conf_threshold: Confidence score threshold for detected faces.
+        @type conf_threshold: float
+        @param iou_threshold: Non-maximum suppression threshold.
+        @type iou_threshold: float
+        @param max_det: Maximum number of detections to keep.
+        @type max_det: int
         """
         dai.node.ThreadedHostNode.__init__(self)
         self.input = dai.Node.Input(self)
         self.out = dai.Node.Output(self)
 
-        self.score_threshold = score_threshold
-        self.nms_threshold = nms_threshold
-        self.top_k = top_k
+        self.conf_threshold = conf_threshold
+        self.iou_threshold = iou_threshold
+        self.max_det = max_det
 
     def setConfidenceThreshold(self, threshold):
         """Sets the confidence score threshold for detected faces.
 
         @param threshold: Confidence score threshold for detected faces.
         @type threshold: float
         """
-        self.score_threshold = threshold
+        self.conf_threshold = threshold
 
-    def setNMSThreshold(self, threshold):
+    def setIOUThreshold(self, threshold):
         """Sets the non-maximum suppression threshold.
 
         @param threshold: Non-maximum suppression threshold.
         @type threshold: float
         """
-        self.nms_threshold = threshold
+        self.iou_threshold = threshold
 
-    def setTopK(self, top_k):
+    def setMaxDetections(self, max_det):
         """Sets the maximum number of detections to keep.
 
-        @param top_k: Maximum number of detections to keep.
-        @type top_k: int
+        @param max_det: Maximum number of detections to keep.
+        @type max_det: int
         """
-        self.top_k = top_k
+        self.max_det = max_det
 
     def run(self):
         while self.isRunning():
@@ -113,7 +113,7 @@ def run(self):
                 detections += decode_detections(
                     input_size,
                     stride,
-                    self.score_threshold,
+                    self.conf_threshold,
                     cls,
                     obj,
                     bbox,
@@ -126,9 +126,9 @@ def run(self):
             indices = cv2.dnn.NMSBoxes(
                 detection_boxes,
                 detection_scores,
-                self.score_threshold,
-                self.nms_threshold,
-                top_k=self.top_k,
+                self.conf_threshold,
+                self.iou_threshold,
+                top_k=self.max_det,
             )
             detections = np.array(detections)[indices]