Merge remote-tracking branch 'origin/docstrings' into docstrings

utils/loggers/comet/hpo.py

@@ -25,7 +25,9 @@
 
 
 def get_args(known=False):
-    """Parses command-line arguments for YOLOv5 training, supporting configuration of weights, data paths, hyperparameters, and more."""
+    """Parses command-line arguments for YOLOv5 training, supporting configuration of weights, data paths,
+    hyperparameters, and more.
+    """
     parser = argparse.ArgumentParser()
     parser.add_argument("--weights", type=str, default=ROOT / "yolov5s.pt", help="initial weights path")
     parser.add_argument("--cfg", type=str, default="", help="model.yaml path")

utils/loss.py

@@ -16,13 +16,17 @@ def smooth_BCE(eps=0.1):  # https://github.com/ultralytics/yolov3/issues/238#iss
 class BCEBlurWithLogitsLoss(nn.Module):
     # BCEwithLogitLoss() with reduced missing label effects.
     def __init__(self, alpha=0.05):
-        """Initializes a modified BCEWithLogitsLoss with reduced missing label effects, taking optional alpha smoothing parameter."""
+        """Initializes a modified BCEWithLogitsLoss with reduced missing label effects, taking optional alpha smoothing
+        parameter.
+        """
         super().__init__()
         self.loss_fcn = nn.BCEWithLogitsLoss(reduction="none")  # must be nn.BCEWithLogitsLoss()
         self.alpha = alpha
 
     def forward(self, pred, true):
-        """Computes modified BCE loss for YOLOv5 with reduced missing label effects, taking pred and true tensors, returns mean loss."""
+        """Computes modified BCE loss for YOLOv5 with reduced missing label effects, taking pred and true tensors,
+        returns mean loss.
+        """
         loss = self.loss_fcn(pred, true)
         pred = torch.sigmoid(pred)  # prob from logits
         dx = pred - true  # reduce only missing label effects
@@ -35,7 +39,9 @@ def forward(self, pred, true):
 class FocalLoss(nn.Module):
     # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
     def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
-        """Initializes FocalLoss with specified loss function, gamma, and alpha values; modifies loss reduction to 'none'."""
+        """Initializes FocalLoss with specified loss function, gamma, and alpha values; modifies loss reduction to
+        'none'.
+        """
         super().__init__()
         self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
         self.gamma = gamma
@@ -76,7 +82,9 @@ def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
         self.loss_fcn.reduction = "none"  # required to apply FL to each element
 
     def forward(self, pred, true):
-        """Computes the focal loss between `pred` and `true` using BCEWithLogitsLoss, adjusting for imbalance with `gamma` and `alpha`."""
+        """Computes the focal loss between `pred` and `true` using BCEWithLogitsLoss, adjusting for imbalance with
+        `gamma` and `alpha`.
+        """
         loss = self.loss_fcn(pred, true)
 
         pred_prob = torch.sigmoid(pred)  # prob from logits
@@ -180,7 +188,9 @@ def __call__(self, p, targets):  # predictions, targets
         return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach()
 
     def build_targets(self, p, targets):
-        """Prepares model targets from input targets (image,class,x,y,w,h) for loss computation, returning class, box, indices, and anchors."""
+        """Prepares model targets from input targets (image,class,x,y,w,h) for loss computation, returning class, box,
+        indices, and anchors.
+        """
         na, nt = self.na, targets.shape[0]  # number of anchors, targets
         tcls, tbox, indices, anch = [], [], [], []
         gain = torch.ones(7, device=self.device)  # normalized to gridspace gain

utils/segment/general.py

@@ -144,7 +144,9 @@ def masks_iou(mask1, mask2, eps=1e-7):
 
 
 def masks2segments(masks, strategy="largest"):
-    """Converts binary (n,160,160) masks to polygon segments with options for concatenation or selecting the largest segment."""
+    """Converts binary (n,160,160) masks to polygon segments with options for concatenation or selecting the largest
+    segment.
+    """
     segments = []
     for x in masks.int().cpu().numpy().astype("uint8"):
         c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]

utils/segment/loss.py

@@ -12,7 +12,9 @@
 class ComputeLoss:
     # Compute losses
     def __init__(self, model, autobalance=False, overlap=False):
-        """Initializes the compute loss function for YOLOv5 models with options for autobalancing and overlap handling."""
+        """Initializes the compute loss function for YOLOv5 models with options for autobalancing and overlap
+        handling.
+        """
         self.sort_obj_iou = False
         self.overlap = overlap
         device = next(model.parameters()).device  # get model device
@@ -116,7 +118,9 @@ def single_mask_loss(self, gt_mask, pred, proto, xyxy, area):
         return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).mean()
 
     def build_targets(self, p, targets):
-        """Prepares YOLOv5 targets for loss computation; inputs targets (image, class, x, y, w, h), output target classes/boxes."""
+        """Prepares YOLOv5 targets for loss computation; inputs targets (image, class, x, y, w, h), output target
+        classes/boxes.
+        """
         na, nt = self.na, targets.shape[0]  # number of anchors, targets
         tcls, tbox, indices, anch, tidxs, xywhn = [], [], [], [], [], []
         gain = torch.ones(8, device=self.device)  # normalized to gridspace gain

utils/segment/metrics.py

@@ -171,7 +171,9 @@ def class_result(self, i):
         return self.metric_box.class_result(i) + self.metric_mask.class_result(i)
 
     def get_maps(self, nc):
-        """Calculates and returns the sum of mean average precisions (mAPs) for both box and mask metrics for `nc` classes."""
+        """Calculates and returns the sum of mean average precisions (mAPs) for both box and mask metrics for `nc`
+        classes.
+        """
         return self.metric_box.get_maps(nc) + self.metric_mask.get_maps(nc)
 
     @property