dgenerate-ultralytics-headless 8.3.196__py3-none-any.whl → 8.3.248__py3-none-any.whl

ultralytics/models/yolo/classify/val.py

@@ -6,20 +6,20 @@ from pathlib import Path
 from typing import Any
 
 import torch
+import torch.distributed as dist
 
 from ultralytics.data import ClassificationDataset, build_dataloader
 from ultralytics.engine.validator import BaseValidator
-from ultralytics.utils import LOGGER
+from ultralytics.utils import LOGGER, RANK
 from ultralytics.utils.metrics import ClassifyMetrics, ConfusionMatrix
 from ultralytics.utils.plotting import plot_images
 
 
 class ClassificationValidator(BaseValidator):
-    """
-    A class extending the BaseValidator class for validation based on a classification model.
+    """A class extending the BaseValidator class for validation based on a classification model.
 
-    This validator handles the validation process for classification models, including metrics calculation,
-    confusion matrix generation, and visualization of results.
+    This validator handles the validation process for classification models, including metrics calculation, confusion
+    matrix generation, and visualization of results.
 
     Attributes:
         targets (list[torch.Tensor]): Ground truth class labels.
@@ -54,20 +54,13 @@ class ClassificationValidator(BaseValidator):
     """
 
     def __init__(self, dataloader=None, save_dir=None, args=None, _callbacks=None) -> None:
-        """
-        Initialize ClassificationValidator with dataloader, save directory, and other parameters.
+        """Initialize ClassificationValidator with dataloader, save directory, and other parameters.
 
         Args:
-            dataloader (torch.utils.data.DataLoader, optional): Dataloader to use for validation.
+            dataloader (torch.utils.data.DataLoader, optional): DataLoader to use for validation.
             save_dir (str | Path, optional): Directory to save results.
             args (dict, optional): Arguments containing model and validation configuration.
             _callbacks (list, optional): List of callback functions to be called during validation.
-
-        Examples:
-            >>> from ultralytics.models.yolo.classify import ClassificationValidator
-            >>> args = dict(model="yolo11n-cls.pt", data="imagenet10")
-            >>> validator = ClassificationValidator(args=args)
-            >>> validator()
         """
         super().__init__(dataloader, save_dir, args, _callbacks)
         self.targets = None
@@ -89,14 +82,13 @@ class ClassificationValidator(BaseValidator):
 
     def preprocess(self, batch: dict[str, Any]) -> dict[str, Any]:
         """Preprocess input batch by moving data to device and converting to appropriate dtype."""
-        batch["img"] = batch["img"].to(self.device, non_blocking=True)
+        batch["img"] = batch["img"].to(self.device, non_blocking=self.device.type == "cuda")
         batch["img"] = batch["img"].half() if self.args.half else batch["img"].float()
-        batch["cls"] = batch["cls"].to(self.device, non_blocking=True)
+        batch["cls"] = batch["cls"].to(self.device, non_blocking=self.device.type == "cuda")
         return batch
 
     def update_metrics(self, preds: torch.Tensor, batch: dict[str, Any]) -> None:
-        """
-        Update running metrics with model predictions and batch targets.
+        """Update running metrics with model predictions and batch targets.
 
         Args:
             preds (torch.Tensor): Model predictions, typically logits or probabilities for each class.
@@ -111,12 +103,7 @@ class ClassificationValidator(BaseValidator):
         self.targets.append(batch["cls"].type(torch.int32).cpu())
 
     def finalize_metrics(self) -> None:
-        """
-        Finalize metrics including confusion matrix and processing speed.
-
-        Notes:
-            This method processes the accumulated predictions and targets to generate the confusion matrix,
-            optionally plots it, and updates the metrics object with speed information.
+        """Finalize metrics including confusion matrix and processing speed.
 
         Examples:
             >>> validator = ClassificationValidator()
@@ -124,6 +111,10 @@ class ClassificationValidator(BaseValidator):
             >>> validator.targets = [torch.tensor([0])]  # Ground truth class
             >>> validator.finalize_metrics()
             >>> print(validator.metrics.confusion_matrix)  # Access the confusion matrix
+
+        Notes:
+            This method processes the accumulated predictions and targets to generate the confusion matrix,
+            optionally plots it, and updates the metrics object with speed information.
         """
         self.confusion_matrix.process_cls_preds(self.pred, self.targets)
         if self.args.plots:
@@ -142,13 +133,25 @@ class ClassificationValidator(BaseValidator):
         self.metrics.process(self.targets, self.pred)
         return self.metrics.results_dict
 
+    def gather_stats(self) -> None:
+        """Gather stats from all GPUs."""
+        if RANK == 0:
+            gathered_preds = [None] * dist.get_world_size()
+            gathered_targets = [None] * dist.get_world_size()
+            dist.gather_object(self.pred, gathered_preds, dst=0)
+            dist.gather_object(self.targets, gathered_targets, dst=0)
+            self.pred = [pred for rank in gathered_preds for pred in rank]
+            self.targets = [targets for rank in gathered_targets for targets in rank]
+        elif RANK > 0:
+            dist.gather_object(self.pred, None, dst=0)
+            dist.gather_object(self.targets, None, dst=0)
+
     def build_dataset(self, img_path: str) -> ClassificationDataset:
         """Create a ClassificationDataset instance for validation."""
         return ClassificationDataset(root=img_path, args=self.args, augment=False, prefix=self.args.split)
 
     def get_dataloader(self, dataset_path: Path | str, batch_size: int) -> torch.utils.data.DataLoader:
-        """
-        Build and return a data loader for classification validation.
+        """Build and return a data loader for classification validation.
 
         Args:
             dataset_path (str | Path): Path to the dataset directory.
@@ -166,8 +169,7 @@ class ClassificationValidator(BaseValidator):
         LOGGER.info(pf % ("all", self.metrics.top1, self.metrics.top5))
 
     def plot_val_samples(self, batch: dict[str, Any], ni: int) -> None:
-        """
-        Plot validation image samples with their ground truth labels.
+        """Plot validation image samples with their ground truth labels.
 
         Args:
             batch (dict[str, Any]): Dictionary containing batch data with 'img' (images) and 'cls' (class labels).
@@ -178,7 +180,7 @@ class ClassificationValidator(BaseValidator):
             >>> batch = {"img": torch.rand(16, 3, 224, 224), "cls": torch.randint(0, 10, (16,))}
             >>> validator.plot_val_samples(batch, 0)
         """
-        batch["batch_idx"] = torch.arange(len(batch["img"]))  # add batch index for plotting
+        batch["batch_idx"] = torch.arange(batch["img"].shape[0])  # add batch index for plotting
         plot_images(
             labels=batch,
             fname=self.save_dir / f"val_batch{ni}_labels.jpg",
@@ -187,8 +189,7 @@ class ClassificationValidator(BaseValidator):
         )
 
     def plot_predictions(self, batch: dict[str, Any], preds: torch.Tensor, ni: int) -> None:
-        """
-        Plot images with their predicted class labels and save the visualization.
+        """Plot images with their predicted class labels and save the visualization.
 
         Args:
             batch (dict[str, Any]): Batch data containing images and other information.
@@ -203,8 +204,9 @@ class ClassificationValidator(BaseValidator):
         """
         batched_preds = dict(
             img=batch["img"],
-            batch_idx=torch.arange(len(batch["img"])),
+            batch_idx=torch.arange(batch["img"].shape[0]),
             cls=torch.argmax(preds, dim=1),
+            conf=torch.amax(preds, dim=1),
         )
         plot_images(
             batched_preds,

ultralytics/models/yolo/detect/predict.py

@@ -6,8 +6,7 @@ from ultralytics.utils import nms, ops
 
 
 class DetectionPredictor(BasePredictor):
-    """
-    A class extending the BasePredictor class for prediction based on a detection model.
+    """A class extending the BasePredictor class for prediction based on a detection model.
 
     This predictor specializes in object detection tasks, processing model outputs into meaningful detection results
     with bounding boxes and class predictions.
@@ -32,8 +31,7 @@ class DetectionPredictor(BasePredictor):
     """
 
     def postprocess(self, preds, img, orig_imgs, **kwargs):
-        """
-        Post-process predictions and return a list of Results objects.
+        """Post-process predictions and return a list of Results objects.
 
         This method applies non-maximum suppression to raw model predictions and prepares them for visualization and
         further analysis.
@@ -67,7 +65,7 @@ class DetectionPredictor(BasePredictor):
         )
 
         if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
-            orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
+            orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)[..., ::-1]
 
         if save_feats:
             obj_feats = self.get_obj_feats(self._feats, preds[1])
@@ -81,7 +79,8 @@ class DetectionPredictor(BasePredictor):
 
         return results
 
-    def get_obj_feats(self, feat_maps, idxs):
+    @staticmethod
+    def get_obj_feats(feat_maps, idxs):
         """Extract object features from the feature maps."""
         import torch
 
@@ -89,11 +88,10 @@ class DetectionPredictor(BasePredictor):
         obj_feats = torch.cat(
             [x.permute(0, 2, 3, 1).reshape(x.shape[0], -1, s, x.shape[1] // s).mean(dim=-1) for x in feat_maps], dim=1
         )  # mean reduce all vectors to same length
-        return [feats[idx] if len(idx) else [] for feats, idx in zip(obj_feats, idxs)]  # for each img in batch
+        return [feats[idx] if idx.shape[0] else [] for feats, idx in zip(obj_feats, idxs)]  # for each img in batch
 
     def construct_results(self, preds, img, orig_imgs):
-        """
-        Construct a list of Results objects from model predictions.
+        """Construct a list of Results objects from model predictions.
 
         Args:
             preds (list[torch.Tensor]): List of predicted bounding boxes and scores for each image.
@@ -109,8 +107,7 @@ class DetectionPredictor(BasePredictor):
         ]
 
     def construct_result(self, pred, img, orig_img, img_path):
-        """
-        Construct a single Results object from one image prediction.
+        """Construct a single Results object from one image prediction.
 
         Args:
             pred (torch.Tensor): Predicted boxes and scores with shape (N, 6) where N is the number of detections.

ultralytics/models/yolo/detect/train.py

@@ -17,16 +17,15 @@ from ultralytics.models import yolo
 from ultralytics.nn.tasks import DetectionModel
 from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
 from ultralytics.utils.patches import override_configs
-from ultralytics.utils.plotting import plot_images, plot_labels, plot_results
+from ultralytics.utils.plotting import plot_images, plot_labels
 from ultralytics.utils.torch_utils import torch_distributed_zero_first, unwrap_model
 
 
 class DetectionTrainer(BaseTrainer):
-    """
-    A class extending the BaseTrainer class for training based on a detection model.
+    """A class extending the BaseTrainer class for training based on a detection model.
 
-    This trainer specializes in object detection tasks, handling the specific requirements for training YOLO models
-    for object detection including dataset building, data loading, preprocessing, and model configuration.
+    This trainer specializes in object detection tasks, handling the specific requirements for training YOLO models for
+    object detection including dataset building, data loading, preprocessing, and model configuration.
 
     Attributes:
         model (DetectionModel): The YOLO detection model being trained.
@@ -43,7 +42,6 @@ class DetectionTrainer(BaseTrainer):
         label_loss_items: Return a loss dictionary with labeled training loss items.
         progress_string: Return a formatted string of training progress.
         plot_training_samples: Plot training samples with their annotations.
-        plot_metrics: Plot metrics from a CSV file.
         plot_training_labels: Create a labeled training plot of the YOLO model.
         auto_batch: Calculate optimal batch size based on model memory requirements.
 
@@ -55,8 +53,7 @@ class DetectionTrainer(BaseTrainer):
     """
 
     def __init__(self, cfg=DEFAULT_CFG, overrides: dict[str, Any] | None = None, _callbacks=None):
-        """
-        Initialize a DetectionTrainer object for training YOLO object detection model training.
+        """Initialize a DetectionTrainer object for training YOLO object detection models.
 
         Args:
             cfg (dict, optional): Default configuration dictionary containing training parameters.
@@ -64,11 +61,9 @@ class DetectionTrainer(BaseTrainer):
             _callbacks (list, optional): List of callback functions to be executed during training.
         """
         super().__init__(cfg, overrides, _callbacks)
-        self.dynamic_tensors = ["batch_idx", "cls", "bboxes"]
 
     def build_dataset(self, img_path: str, mode: str = "train", batch: int | None = None):
-        """
-        Build YOLO Dataset for training or validation.
+        """Build YOLO Dataset for training or validation.
 
         Args:
             img_path (str): Path to the folder containing images.
@@ -82,8 +77,7 @@ class DetectionTrainer(BaseTrainer):
         return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == "val", stride=gs)
 
     def get_dataloader(self, dataset_path: str, batch_size: int = 16, rank: int = 0, mode: str = "train"):
-        """
-        Construct and return dataloader for the specified mode.
+        """Construct and return dataloader for the specified mode.
 
         Args:
             dataset_path (str): Path to the dataset.
@@ -111,8 +105,7 @@ class DetectionTrainer(BaseTrainer):
         )
 
     def preprocess_batch(self, batch: dict) -> dict:
-        """
-        Preprocess a batch of images by scaling and converting to float.
+        """Preprocess a batch of images by scaling and converting to float.
 
         Args:
             batch (dict): Dictionary containing batch data with 'img' tensor.
@@ -122,7 +115,7 @@ class DetectionTrainer(BaseTrainer):
         """
         for k, v in batch.items():
             if isinstance(v, torch.Tensor):
-                batch[k] = v.to(self.device, non_blocking=True)
+                batch[k] = v.to(self.device, non_blocking=self.device.type == "cuda")
         batch["img"] = batch["img"].float() / 255
         if self.args.multi_scale:
             imgs = batch["img"]
@@ -138,10 +131,6 @@ class DetectionTrainer(BaseTrainer):
                 ]  # new shape (stretched to gs-multiple)
                 imgs = nn.functional.interpolate(imgs, size=ns, mode="bilinear", align_corners=False)
             batch["img"] = imgs
-
-        if self.args.compile:
-            for k in self.dynamic_tensors:
-                torch._dynamo.maybe_mark_dynamic(batch[k], 0)
         return batch
 
     def set_model_attributes(self):
@@ -156,8 +145,7 @@ class DetectionTrainer(BaseTrainer):
         # TODO: self.model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc
 
     def get_model(self, cfg: str | None = None, weights: str | None = None, verbose: bool = True):
-        """
-        Return a YOLO detection model.
+        """Return a YOLO detection model.
 
         Args:
             cfg (str, optional): Path to model configuration file.
@@ -180,8 +168,7 @@ class DetectionTrainer(BaseTrainer):
         )
 
     def label_loss_items(self, loss_items: list[float] | None = None, prefix: str = "train"):
-        """
-        Return a loss dict with labeled training loss items tensor.
+        """Return a loss dict with labeled training loss items tensor.
 
         Args:
             loss_items (list[float], optional): List of loss values.
@@ -208,8 +195,7 @@ class DetectionTrainer(BaseTrainer):
         )
 
     def plot_training_samples(self, batch: dict[str, Any], ni: int) -> None:
-        """
-        Plot training samples with their annotations.
+        """Plot training samples with their annotations.
 
         Args:
             batch (dict[str, Any]): Dictionary containing batch data.
@@ -222,10 +208,6 @@ class DetectionTrainer(BaseTrainer):
             on_plot=self.on_plot,
         )
 
-    def plot_metrics(self):
-        """Plot metrics from a CSV file."""
-        plot_results(file=self.csv, on_plot=self.on_plot)  # save results.png
-
     def plot_training_labels(self):
         """Create a labeled training plot of the YOLO model."""
         boxes = np.concatenate([lb["bboxes"] for lb in self.train_loader.dataset.labels], 0)
@@ -233,8 +215,7 @@ class DetectionTrainer(BaseTrainer):
         plot_labels(boxes, cls.squeeze(), names=self.data["names"], save_dir=self.save_dir, on_plot=self.on_plot)
 
     def auto_batch(self):
-        """
-        Get optimal batch size by calculating memory occupation of model.
+        """Get optimal batch size by calculating memory occupation of model.
 
         Returns:
             (int): Optimal batch size.