ultralytics 8.0.81 single-line docstring updates (#2061)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

ultralytics/tracker/utils/gmc.py

@@ -11,6 +11,7 @@ from ultralytics.yolo.utils import LOGGER
 class GMC:
 
     def __init__(self, method='sparseOptFlow', downscale=2, verbose=None):
+        """Initialize a video tracker with specified parameters."""
         super().__init__()
 
         self.method = method
@@ -69,6 +70,7 @@ class GMC:
         self.initializedFirstFrame = False
 
     def apply(self, raw_frame, detections=None):
+        """Apply object detection on a raw frame using specified method."""
         if self.method in ['orb', 'sift']:
             return self.applyFeatures(raw_frame, detections)
         elif self.method == 'ecc':
@@ -303,6 +305,7 @@ class GMC:
         return H
 
     def applyFile(self, raw_frame, detections=None):
+        """Return the homography matrix based on the GCPs in the next line of the input GMC file."""
         line = self.gmcFile.readline()
         tokens = line.split('\t')
         H = np.eye(2, 3, dtype=np.float_)

ultralytics/tracker/utils/kalman_filter.py

@@ -27,6 +27,7 @@ class KalmanFilterXYAH:
     """
 
     def __init__(self):
+        """Initialize Kalman filter model matrices with motion and observation uncertainty weights."""
         ndim, dt = 4, 1.
 
         # Create Kalman filter model matrices.
@@ -253,6 +254,7 @@ class KalmanFilterXYWH:
     """
 
     def __init__(self):
+        """Initialize Kalman filter model matrices with motion and observation uncertainties."""
         ndim, dt = 4, 1.
 
         # Create Kalman filter model matrices.

ultralytics/tracker/utils/matching.py

@@ -18,6 +18,7 @@ except (ImportError, AssertionError, AttributeError):
 
 
 def merge_matches(m1, m2, shape):
+    """Merge two sets of matches and return matched and unmatched indices."""
     O, P, Q = shape
     m1 = np.asarray(m1)
     m2 = np.asarray(m2)
@@ -35,6 +36,7 @@ def merge_matches(m1, m2, shape):
 
 
 def _indices_to_matches(cost_matrix, indices, thresh):
+    """_indices_to_matches: Return matched and unmatched indices given a cost matrix, indices, and a threshold."""
     matched_cost = cost_matrix[tuple(zip(*indices))]
     matched_mask = (matched_cost <= thresh)
 
@@ -144,6 +146,7 @@ def embedding_distance(tracks, detections, metric='cosine'):
 
 
 def gate_cost_matrix(kf, cost_matrix, tracks, detections, only_position=False):
+    """Apply gating to the cost matrix based on predicted tracks and detected objects."""
     if cost_matrix.size == 0:
         return cost_matrix
     gating_dim = 2 if only_position else 4
@@ -156,6 +159,7 @@ def gate_cost_matrix(kf, cost_matrix, tracks, detections, only_position=False):
 
 
 def fuse_motion(kf, cost_matrix, tracks, detections, only_position=False, lambda_=0.98):
+    """Fuse motion between tracks and detections with gating and Kalman filtering."""
     if cost_matrix.size == 0:
         return cost_matrix
     gating_dim = 2 if only_position else 4
@@ -169,6 +173,7 @@ def fuse_motion(kf, cost_matrix, tracks, detections, only_position=False, lambda
 
 
 def fuse_iou(cost_matrix, tracks, detections):
+    """Fuses ReID and IoU similarity matrices to yield a cost matrix for object tracking."""
     if cost_matrix.size == 0:
         return cost_matrix
     reid_sim = 1 - cost_matrix
@@ -181,6 +186,7 @@ def fuse_iou(cost_matrix, tracks, detections):
 
 
 def fuse_score(cost_matrix, detections):
+    """Fuses cost matrix with detection scores to produce a single similarity matrix."""
     if cost_matrix.size == 0:
         return cost_matrix
     iou_sim = 1 - cost_matrix