Merge remote-tracking branch 'origin/docstrings2' into docstrings2

models/experimental.py

@@ -11,8 +11,11 @@
 
 class Sum(nn.Module):
     """Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070."""
+
     def __init__(self, n, weight=False):
-        """Initializes a module to sum outputs of layers with number of inputs `n` and optional weighting, supporting 2+ inputs."""
+        """Initializes a module to sum outputs of layers with number of inputs `n` and optional weighting, supporting 2+
+        inputs.
+        """
         super().__init__()
         self.weight = weight  # apply weights boolean
         self.iter = range(n - 1)  # iter object
@@ -34,8 +37,11 @@ def forward(self, x):
 
 class MixConv2d(nn.Module):
     """Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595."""
+
     def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
-        """Initializes MixConv2d with mixed depth-wise convolutional layers, taking input and output channels (c1, c2), kernel sizes (k), stride (s), and channel distribution strategy (equal_ch)."""
+        """Initializes MixConv2d with mixed depth-wise convolutional layers, taking input and output channels (c1, c2),
+        kernel sizes (k), stride (s), and channel distribution strategy (equal_ch).
+        """
         super().__init__()
         n = len(k)  # number of convolutions
         if equal_ch:  # equal c_ per group

models/yolo.py

@@ -308,7 +308,11 @@ def _clip_augmented(self, y):
         return y
 
     def _initialize_biases(self, cf=None):
-        """Initializes biases for YOLOv5's Detect() module, optionally using class frequencies (cf). For details see https://arxiv.org/abs/1708.02002 section 3.3."""
+        """
+        Initializes biases for YOLOv5's Detect() module, optionally using class frequencies (cf).
+
+        For details see https://arxiv.org/abs/1708.02002 section 3.3.
+        """
         # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
         m = self.model[-1]  # Detect() module
         for mi, s in zip(m.m, m.stride):  # from
@@ -333,7 +337,9 @@ def __init__(self, cfg="yolov5s-seg.yaml", ch=3, nc=None, anchors=None):
 class ClassificationModel(BaseModel):
     # YOLOv5 classification model
     def __init__(self, cfg=None, model=None, nc=1000, cutoff=10):
-        """Initializes YOLOv5 model with config file `cfg`, input channels `ch`, number of classes `nc`, and `cuttoff` index."""
+        """Initializes YOLOv5 model with config file `cfg`, input channels `ch`, number of classes `nc`, and `cuttoff`
+        index.
+        """
         super().__init__()
         self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg)
 

segment/train.py

@@ -96,7 +96,11 @@
 
 
 def train(hyp, opt, device, callbacks):
-    """Trains the YOLOv5 model on a dataset, managing hyperparameters, model optimization, logging, and validation. `hyp` is path/to/hyp.yaml or hyp dictionary."""
+    """
+    Trains the YOLOv5 model on a dataset, managing hyperparameters, model optimization, logging, and validation.
+
+    `hyp` is path/to/hyp.yaml or hyp dictionary.
+    """
     (
         save_dir,
         epochs,

train.py

@@ -101,7 +101,12 @@
 
 
 def train(hyp, opt, device, callbacks):
-    """Trains YOLOv5 model with given hyperparameters, options, and device, managing datasets, model architecture, loss computation, and optimizer steps. `hyp` argument is path/to/hyp.yaml or hyp dictionary."""
+    """
+    Trains YOLOv5 model with given hyperparameters, options, and device, managing datasets, model architecture, loss
+    computation, and optimizer steps.
+
+    `hyp` argument is path/to/hyp.yaml or hyp dictionary.
+    """
     save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze = (
         Path(opt.save_dir),
         opt.epochs,

utils/activations.py

@@ -60,6 +60,7 @@ def forward(self, x):
 
 class FReLU(nn.Module):
     """FReLU activation https://arxiv.org/abs/2007.11824."""
+
     def __init__(self, c1, k=3):  # ch_in, kernel
         """Initializes FReLU activation with channel `c1` and kernel size `k`."""
         super().__init__()

utils/augmentations.py

@@ -311,7 +311,12 @@ def mixup(im, labels, im2, labels2):
 
 
 def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16):
-    """Filters bounding box candidates by minimum width-height threshold `wh_thr` (pixels), aspect ratio threshold `ar_thr`, and area ratio threshold `area_thr`.  box1(4,n) is before augmentation, box2(4,n) is after augmentation."""
+    """
+    Filters bounding box candidates by minimum width-height threshold `wh_thr` (pixels), aspect ratio threshold
+    `ar_thr`, and area ratio threshold `area_thr`.
+
+    box1(4,n) is before augmentation, box2(4,n) is after augmentation.
+    """
     w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
     w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
     ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps))  # aspect ratio
@@ -381,7 +386,11 @@ def __init__(self, size=(640, 640), auto=False, stride=32):
         self.stride = stride  # used with auto
 
     def __call__(self, im):
-        """Resizes and pads input image `im` (HWC format) to specified dimensions, maintaining aspect ratio. im = np.array HWC"""
+        """
+        Resizes and pads input image `im` (HWC format) to specified dimensions, maintaining aspect ratio.
+
+        im = np.array HWC
+        """
         imh, imw = im.shape[:2]
         r = min(self.h / imh, self.w / imw)  # ratio of new/old
         h, w = round(imh * r), round(imw * r)  # resized image
@@ -400,7 +409,11 @@ def __init__(self, size=640):
         self.h, self.w = (size, size) if isinstance(size, int) else size
 
     def __call__(self, im):
-        """Applies center crop to the input image and resizes it to a specified size, maintaining aspect ratio. im = np.array HWC"""
+        """
+        Applies center crop to the input image and resizes it to a specified size, maintaining aspect ratio.
+
+        im = np.array HWC
+        """
         imh, imw = im.shape[:2]
         m = min(imh, imw)  # min dimension
         top, left = (imh - m) // 2, (imw - m) // 2
@@ -415,7 +428,12 @@ def __init__(self, half=False):
         self.half = half
 
     def __call__(self, im):
-        """Converts BGR np.array image from HWC to RGB CHW format, and normalizes to [0, 1], with support for FP16 if `half=True`. im = np.array HWC in BGR order"""
+        """
+        Converts BGR np.array image from HWC to RGB CHW format, and normalizes to [0, 1], with support for FP16 if
+        `half=True`.
+
+        im = np.array HWC in BGR order
+        """
         im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1])  # HWC to CHW -> BGR to RGB -> contiguous
         im = torch.from_numpy(im)  # to torch
         im = im.half() if self.half else im.float()  # uint8 to fp16/32

utils/dataloaders.py

@@ -1061,7 +1061,12 @@ def flatten_recursive(path=DATASETS_DIR / "coco128"):
 
 
 def extract_boxes(path=DATASETS_DIR / "coco128"):
-    """Converts a detection dataset to a classification dataset, creating a directory for each class and extracting bounding boxes. Example: from utils.dataloaders import *; extract_boxes()"""
+    """
+    Converts a detection dataset to a classification dataset, creating a directory for each class and extracting
+    bounding boxes.
+
+    Example: from utils.dataloaders import *; extract_boxes()
+    """
     path = Path(path)  # images dir
     shutil.rmtree(path / "classification") if (path / "classification").is_dir() else None  # remove existing
     files = list(path.rglob("*.*"))

utils/torch_utils.py

@@ -325,7 +325,9 @@ def model_info(model, verbose=False, imgsz=640):
 
 
 def scale_img(img, ratio=1.0, same_shape=False, gs=32):  # img(16,3,256,416)
-    """Scales an image tensor `img` of shape (bs,3,y,x) by `ratio`, optionally maintaining the original shape, padded to multiples of `gs`."""
+    """Scales an image tensor `img` of shape (bs,3,y,x) by `ratio`, optionally maintaining the original shape, padded to
+    multiples of `gs`.
+    """
     if ratio == 1.0:
         return img
     h, w = img.shape[2:]