ultralytics 8.1.44 add IS_RASPBERRYPI and constants refactor (#9827)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>

ultralytics/models/rtdetr/val.py

@@ -125,7 +125,7 @@ class RTDETRValidator(DetectionValidator):
             bbox = ops.xywh2xyxy(bbox)  # target boxes
             bbox[..., [0, 2]] *= ori_shape[1]  # native-space pred
             bbox[..., [1, 3]] *= ori_shape[0]  # native-space pred
-        return dict(cls=cls, bbox=bbox, ori_shape=ori_shape, imgsz=imgsz, ratio_pad=ratio_pad)
+        return {"cls": cls, "bbox": bbox, "ori_shape": ori_shape, "imgsz": imgsz, "ratio_pad": ratio_pad}
 
     def _prepare_pred(self, pred, pbatch):
         """Prepares and returns a batch with transformed bounding boxes and class labels."""

ultralytics/models/sam/modules/tiny_encoder.py

@@ -584,9 +584,9 @@ class TinyViT(nn.Module):
             img_size (int, optional): The input image size. Defaults to 224.
             in_chans (int, optional): Number of input channels. Defaults to 3.
             num_classes (int, optional): Number of classification classes. Defaults to 1000.
-            embed_dims (List[int], optional): List of embedding dimensions for each layer. Defaults to [96, 192, 384, 768].
+            embed_dims (List[int], optional): List of embedding dimensions per layer. Defaults to [96, 192, 384, 768].
             depths (List[int], optional): List of depths for each layer. Defaults to [2, 2, 6, 2].
-            num_heads (List[int], optional): List of number of attention heads for each layer. Defaults to [3, 6, 12, 24].
+            num_heads (List[int], optional): List of number of attention heads per layer. Defaults to [3, 6, 12, 24].
             window_sizes (List[int], optional): List of window sizes for each layer. Defaults to [7, 7, 14, 7].
             mlp_ratio (float, optional): Ratio of MLP hidden dimension to embedding dimension. Defaults to 4.
             drop_rate (float, optional): Dropout rate. Defaults to 0.

ultralytics/models/sam/modules/transformer.py

@@ -222,7 +222,7 @@ class Attention(nn.Module):
             downsample_rate (int, optional): The factor by which the internal dimensions are downsampled. Defaults to 1.
 
         Raises:
-            AssertionError: If 'num_heads' does not evenly divide the internal dimension (embedding_dim / downsample_rate).
+            AssertionError: If 'num_heads' does not evenly divide the internal dim (embedding_dim / downsample_rate).
         """
         super().__init__()
         self.embedding_dim = embedding_dim

ultralytics/models/sam/predict.py

@@ -127,10 +127,10 @@ class Predictor(BasePredictor):
         Args:
             im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
             bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
-            points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates.
-            labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background.
-            masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256.
-            multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False.
+            points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixels.
+            labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 = foreground, 0 = background.
+            masks (np.ndarray, optional): Low-resolution masks from previous predictions shape (N,H,W). For SAM H=W=256.
+            multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts.
 
         Returns:
             (tuple): Contains the following three elements.
@@ -156,10 +156,10 @@ class Predictor(BasePredictor):
         Args:
             im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
             bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
-            points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates.
-            labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background.
-            masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256.
-            multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False.
+            points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixels.
+            labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 = foreground, 0 = background.
+            masks (np.ndarray, optional): Low-resolution masks from previous predictions shape (N,H,W). For SAM H=W=256.
+            multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts.
 
         Returns:
             (tuple): Contains the following three elements.
@@ -230,7 +230,7 @@ class Predictor(BasePredictor):
             im (torch.Tensor): Input tensor representing the preprocessed image with dimensions (N, C, H, W).
             crop_n_layers (int): Specifies the number of layers for additional mask predictions on image crops.
                                  Each layer produces 2**i_layer number of image crops.
-            crop_overlap_ratio (float): Determines the extent of overlap between crops. Scaled down in subsequent layers.
+            crop_overlap_ratio (float): Determines the overlap between crops. Scaled down in subsequent layers.
             crop_downscale_factor (int): Scaling factor for the number of sampled points-per-side in each layer.
             point_grids (list[np.ndarray], optional): Custom grids for point sampling normalized to [0,1].
                                                       Used in the nth crop layer.
@@ -240,7 +240,7 @@ class Predictor(BasePredictor):
             conf_thres (float): Confidence threshold [0,1] for filtering based on the model's mask quality prediction.
             stability_score_thresh (float): Stability threshold [0,1] for mask filtering based on mask stability.
             stability_score_offset (float): Offset value for calculating stability score.
-            crop_nms_thresh (float): IoU cutoff for Non-Maximum Suppression (NMS) to remove duplicate masks between crops.
+            crop_nms_thresh (float): IoU cutoff for NMS to remove duplicate masks between crops.
 
         Returns:
             (tuple): A tuple containing segmented masks, confidence scores, and bounding boxes.
@@ -351,8 +351,8 @@ class Predictor(BasePredictor):
         """
         Post-processes SAM's inference outputs to generate object detection masks and bounding boxes.
 
-        The method scales masks and boxes to the original image size and applies a threshold to the mask predictions. The
-        SAM model uses advanced architecture and promptable segmentation tasks to achieve real-time performance.
+        The method scales masks and boxes to the original image size and applies a threshold to the mask predictions.
+        The SAM model uses advanced architecture and promptable segmentation tasks to achieve real-time performance.
 
         Args:
             preds (tuple): The output from SAM model inference, containing masks, scores, and optional bounding boxes.

ultralytics/models/yolo/detect/val.py

@@ -106,7 +106,7 @@ class DetectionValidator(BaseValidator):
         if len(cls):
             bbox = ops.xywh2xyxy(bbox) * torch.tensor(imgsz, device=self.device)[[1, 0, 1, 0]]  # target boxes
             ops.scale_boxes(imgsz, bbox, ori_shape, ratio_pad=ratio_pad)  # native-space labels
-        return dict(cls=cls, bbox=bbox, ori_shape=ori_shape, imgsz=imgsz, ratio_pad=ratio_pad)
+        return {"cls": cls, "bbox": bbox, "ori_shape": ori_shape, "imgsz": imgsz, "ratio_pad": ratio_pad}
 
     def _prepare_pred(self, pred, pbatch):
         """Prepares a batch of images and annotations for validation."""

ultralytics/models/yolo/model.py

@@ -5,7 +5,7 @@ from pathlib import Path
 from ultralytics.engine.model import Model
 from ultralytics.models import yolo
 from ultralytics.nn.tasks import ClassificationModel, DetectionModel, OBBModel, PoseModel, SegmentationModel, WorldModel
-from ultralytics.utils import yaml_load, ROOT
+from ultralytics.utils import ROOT, yaml_load
 
 
 class YOLO(Model):

ultralytics/models/yolo/obb/val.py

@@ -78,7 +78,7 @@ class OBBValidator(DetectionValidator):
         if len(cls):
             bbox[..., :4].mul_(torch.tensor(imgsz, device=self.device)[[1, 0, 1, 0]])  # target boxes
             ops.scale_boxes(imgsz, bbox, ori_shape, ratio_pad=ratio_pad, xywh=True)  # native-space labels
-        return dict(cls=cls, bbox=bbox, ori_shape=ori_shape, imgsz=imgsz, ratio_pad=ratio_pad)
+        return {"cls": cls, "bbox": bbox, "ori_shape": ori_shape, "imgsz": imgsz, "ratio_pad": ratio_pad}
 
     def _prepare_pred(self, pred, pbatch):
         """Prepares and returns a batch for OBB validation with scaled and padded bounding boxes."""

ultralytics/models/yolo/world/train_world.py

@@ -1,8 +1,8 @@
-from ultralytics.data import build_yolo_dataset, build_grounding, YOLOConcatDataset
+from ultralytics.data import YOLOConcatDataset, build_grounding, build_yolo_dataset
 from ultralytics.data.utils import check_det_dataset
 from ultralytics.models.yolo.world import WorldTrainer
-from ultralytics.utils.torch_utils import de_parallel
 from ultralytics.utils import DEFAULT_CFG
+from ultralytics.utils.torch_utils import de_parallel
 
 
 class WorldTrainerFromScratch(WorldTrainer):