ultralytics 8.3.11__py3-none-any.whl → 8.3.13__py3-none-any.whl

tests/test_cli.py

@@ -97,9 +97,12 @@ def test_mobilesam():
     # Source
     source = ASSETS / "zidane.jpg"
 
-    # Predict a segment based on a point prompt
+    # Predict a segment based on a 1D point prompt and 1D labels.
     model.predict(source, points=[900, 370], labels=[1])
 
+    # Predict a segment based on 3D points and 2D labels (multiple points per object).
+    model.predict(source, points=[[[900, 370], [1000, 100]]], labels=[[1, 1]])
+
     # Predict a segment based on a box prompt
     model.predict(source, bboxes=[439, 437, 524, 709], save=True)
 

tests/test_cuda.py

@@ -127,9 +127,21 @@ def test_predict_sam():
     # Run inference with bboxes prompt
     model(SOURCE, bboxes=[439, 437, 524, 709], device=0)
 
-    # Run inference with points prompt
+    # Run inference with no labels
+    model(ASSETS / "zidane.jpg", points=[900, 370], device=0)
+
+    # Run inference with 1D points and 1D labels
     model(ASSETS / "zidane.jpg", points=[900, 370], labels=[1], device=0)
 
+    # Run inference with 2D points and 1D labels
+    model(ASSETS / "zidane.jpg", points=[[900, 370]], labels=[1], device=0)
+
+    # Run inference with multiple 2D points and 1D labels
+    model(ASSETS / "zidane.jpg", points=[[400, 370], [900, 370]], labels=[1, 1], device=0)
+
+    # Run inference with 3D points and 2D labels (multiple points per object)
+    model(ASSETS / "zidane.jpg", points=[[[900, 370], [1000, 100]]], labels=[[1, 1]], device=0)
+
     # Create SAMPredictor
     overrides = dict(conf=0.25, task="segment", mode="predict", imgsz=1024, model=WEIGHTS_DIR / "mobile_sam.pt")
     predictor = SAMPredictor(overrides=overrides)

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.3.11"
+__version__ = "8.3.13"
 
 import os
 
@@ -8,7 +8,6 @@ import os
 if not os.environ.get("OMP_NUM_THREADS"):
     os.environ["OMP_NUM_THREADS"] = "1"  # default for reduced CPU utilization during training
 
-from ultralytics.data.explorer.explorer import Explorer
 from ultralytics.models import NAS, RTDETR, SAM, YOLO, FastSAM, YOLOWorld
 from ultralytics.utils import ASSETS, SETTINGS
 from ultralytics.utils.checks import check_yolo as checks
@@ -27,5 +26,4 @@ __all__ = (
     "checks",
     "download",
     "settings",
-    "Explorer",
 )

ultralytics/cfg/__init__.py

@@ -79,14 +79,11 @@ CLI_HELP_MSG = f"""
 
     4. Export a YOLO11n classification model to ONNX format at image size 224 by 128 (no TASK required)
         yolo export model=yolo11n-cls.pt format=onnx imgsz=224,128
-
-    5. Explore your datasets using semantic search and SQL with a simple GUI powered by Ultralytics Explorer API
-        yolo explorer data=data.yaml model=yolo11n.pt
     
-    6. Streamlit real-time webcam inference GUI
+    5. Streamlit real-time webcam inference GUI
         yolo streamlit-predict
         
-    7. Run special commands:
+    6. Run special commands:
         yolo help
         yolo checks
         yolo version
@@ -546,35 +543,6 @@ def handle_yolo_settings(args: List[str]) -> None:
         LOGGER.warning(f"WARNING ⚠️ settings error: '{e}'. Please see {url} for help.")
 
 
-def handle_explorer(args: List[str]):
-    """
-    Launches a graphical user interface that provides tools for interacting with and analyzing datasets using the
-    Ultralytics Explorer API. It checks for the required 'streamlit' package and informs the user that the Explorer
-    dashboard is loading.
-
-    Args:
-        args (List[str]): A list of optional command line arguments.
-
-    Examples:
-        ```bash
-        yolo explorer data=data.yaml model=yolo11n.pt
-        ```
-
-    Notes:
-        - Requires 'streamlit' package version 1.29.0 or higher.
-        - The function does not take any arguments or return any values.
-        - It is typically called from the command line interface using the 'yolo explorer' command.
-    """
-    checks.check_requirements("streamlit>=1.29.0")
-    LOGGER.info("💡 Loading Explorer dashboard...")
-    cmd = ["streamlit", "run", ROOT / "data/explorer/gui/dash.py", "--server.maxMessageSize", "2048"]
-    new = dict(parse_key_value_pair(a) for a in args)
-    check_dict_alignment(base={k: DEFAULT_CFG_DICT[k] for k in ["model", "data"]}, custom=new)
-    for k, v in new.items():
-        cmd += [k, v]
-    subprocess.run(cmd)
-
-
 def handle_streamlit_inference():
     """
     Open the Ultralytics Live Inference Streamlit app for real-time object detection.
@@ -715,7 +683,6 @@ def entrypoint(debug=""):
         "login": lambda: handle_yolo_hub(args),
         "logout": lambda: handle_yolo_hub(args),
         "copy-cfg": copy_default_cfg,
-        "explorer": lambda: handle_explorer(args[1:]),
         "streamlit-predict": lambda: handle_streamlit_inference(),
     }
     full_args_dict = {**DEFAULT_CFG_DICT, **{k: None for k in TASKS}, **{k: None for k in MODES}, **special}

ultralytics/cfg/solutions/default.yaml

@@ -14,3 +14,4 @@ up_angle: 145.0 # Workouts up_angle for counts, 145.0 is default value. You can
 down_angle: 90 # Workouts down_angle for counts, 90 is default value. You can change it for different workouts, based on position of keypoints.
 kpts: [6, 8, 10] # Keypoints for workouts monitoring, i.e. If you want to consider keypoints for pushups that have mostly values of [6, 8, 10].
 colormap: # Colormap for heatmap, Only OPENCV supported colormaps can be used. By default COLORMAP_PARULA will be used for visualization.
+analytics_type: "line" # Analytics type i.e "line", "pie", "bar" or "area" charts. By default, "line" analytics will be used for processing.

ultralytics/engine/exporter.py

@@ -960,7 +960,15 @@ class Exporter:
         LOGGER.info(f"\n{prefix} starting export with Edge TPU compiler {ver}...")
         f = str(tflite_model).replace(".tflite", "_edgetpu.tflite")  # Edge TPU model
 
-        cmd = f'edgetpu_compiler -s -d -k 10 --out_dir "{Path(f).parent}" "{tflite_model}"'
+        cmd = (
+            "edgetpu_compiler "
+            f'--out_dir "{Path(f).parent}" '
+            "--show_operations "
+            "--search_delegate "
+            "--delegate_search_step 30 "
+            "--timeout_sec 180 "
+            f'"{tflite_model}"'
+        )
         LOGGER.info(f"{prefix} running '{cmd}'")
         subprocess.run(cmd, shell=True)
         self._add_tflite_metadata(f)

ultralytics/models/sam/predict.py

@@ -213,11 +213,14 @@ class Predictor(BasePredictor):
         Args:
             im (torch.Tensor): Preprocessed input image tensor with shape (N, C, H, W).
             bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
-            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2), in pixels.
-            labels (np.ndarray | List | None): Point prompt labels with shape (N,). 1 for foreground, 0 for background.
+            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | List | None): Point prompt labels with shape (N,) or (N, num_points). 1 for foreground, 0 for background.
             masks (np.ndarray | None): Low-res masks from previous predictions with shape (N, H, W). For SAM, H=W=256.
             multimask_output (bool): Flag to return multiple masks for ambiguous prompts.
 
+        Raises:
+            AssertionError: If the number of points don't match the number of labels, in case labels were passed.
+
         Returns:
             (tuple): Tuple containing:
                 - np.ndarray: Output masks with shape (C, H, W), where C is the number of generated masks.
@@ -232,26 +235,7 @@ class Predictor(BasePredictor):
         """
         features = self.get_im_features(im) if self.features is None else self.features
 
-        src_shape, dst_shape = self.batch[1][0].shape[:2], im.shape[2:]
-        r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1])
-        # Transform input prompts
-        if points is not None:
-            points = torch.as_tensor(points, dtype=torch.float32, device=self.device)
-            points = points[None] if points.ndim == 1 else points
-            # Assuming labels are all positive if users don't pass labels.
-            if labels is None:
-                labels = np.ones(points.shape[0])
-            labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device)
-            points *= r
-            # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1)
-            points, labels = points[:, None, :], labels[:, None]
-        if bboxes is not None:
-            bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
-            bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
-            bboxes *= r
-        if masks is not None:
-            masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)
-
+        bboxes, points, labels, masks = self._prepare_prompts(im.shape[2:], bboxes, points, labels, masks)
         points = (points, labels) if points is not None else None
         # Embed prompts
         sparse_embeddings, dense_embeddings = self.model.prompt_encoder(points=points, boxes=bboxes, masks=masks)
@@ -269,6 +253,48 @@ class Predictor(BasePredictor):
         # `d` could be 1 or 3 depends on `multimask_output`.
         return pred_masks.flatten(0, 1), pred_scores.flatten(0, 1)
 
+    def _prepare_prompts(self, dst_shape, bboxes=None, points=None, labels=None, masks=None):
+        """
+        Prepares and transforms the input prompts for processing based on the destination shape.
+
+        Args:
+            dst_shape (tuple): The target shape (height, width) for the prompts.
+            bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
+            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | List | None): Point prompt labels with shape (N,) or (N, num_points). 1 for foreground, 0 for background.
+            masks (List | np.ndarray, Optional): Masks for the objects, where each mask is a 2D array.
+
+        Raises:
+            AssertionError: If the number of points don't match the number of labels, in case labels were passed.
+
+        Returns:
+            (tuple): A tuple containing transformed bounding boxes, points, labels, and masks.
+        """
+        src_shape = self.batch[1][0].shape[:2]
+        r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1])
+        # Transform input prompts
+        if points is not None:
+            points = torch.as_tensor(points, dtype=torch.float32, device=self.device)
+            points = points[None] if points.ndim == 1 else points
+            # Assuming labels are all positive if users don't pass labels.
+            if labels is None:
+                labels = np.ones(points.shape[:-1])
+            labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device)
+            assert (
+                points.shape[-2] == labels.shape[-1]
+            ), f"Number of points {points.shape[-2]} should match number of labels {labels.shape[-1]}."
+            points *= r
+            if points.ndim == 2:
+                # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1)
+                points, labels = points[:, None, :], labels[:, None]
+        if bboxes is not None:
+            bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
+            bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
+            bboxes *= r
+        if masks is not None:
+            masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)
+        return bboxes, points, labels, masks
+
     def generate(
         self,
         im,
@@ -686,34 +712,7 @@ class SAM2Predictor(Predictor):
         """
         features = self.get_im_features(im) if self.features is None else self.features
 
-        src_shape, dst_shape = self.batch[1][0].shape[:2], im.shape[2:]
-        r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1])
-        # Transform input prompts
-        if points is not None:
-            points = torch.as_tensor(points, dtype=torch.float32, device=self.device)
-            points = points[None] if points.ndim == 1 else points
-            # Assuming labels are all positive if users don't pass labels.
-            if labels is None:
-                labels = torch.ones(points.shape[0])
-            labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device)
-            points *= r
-            # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1)
-            points, labels = points[:, None], labels[:, None]
-        if bboxes is not None:
-            bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
-            bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
-            bboxes = bboxes.view(-1, 2, 2) * r
-            bbox_labels = torch.tensor([[2, 3]], dtype=torch.int32, device=bboxes.device).expand(len(bboxes), -1)
-            # NOTE: merge "boxes" and "points" into a single "points" input
-            # (where boxes are added at the beginning) to model.sam_prompt_encoder
-            if points is not None:
-                points = torch.cat([bboxes, points], dim=1)
-                labels = torch.cat([bbox_labels, labels], dim=1)
-            else:
-                points, labels = bboxes, bbox_labels
-        if masks is not None:
-            masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)
-
+        bboxes, points, labels, masks = self._prepare_prompts(im.shape[2:], bboxes, points, labels, masks)
         points = (points, labels) if points is not None else None
 
         sparse_embeddings, dense_embeddings = self.model.sam_prompt_encoder(
@@ -737,6 +736,36 @@ class SAM2Predictor(Predictor):
         # `d` could be 1 or 3 depends on `multimask_output`.
         return pred_masks.flatten(0, 1), pred_scores.flatten(0, 1)
 
+    def _prepare_prompts(self, dst_shape, bboxes=None, points=None, labels=None, masks=None):
+        """
+        Prepares and transforms the input prompts for processing based on the destination shape.
+
+        Args:
+            dst_shape (tuple): The target shape (height, width) for the prompts.
+            bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
+            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | List | None): Point prompt labels with shape (N,) or (N, num_points). 1 for foreground, 0 for background.
+            masks (List | np.ndarray, Optional): Masks for the objects, where each mask is a 2D array.
+
+        Raises:
+            AssertionError: If the number of points don't match the number of labels, in case labels were passed.
+
+        Returns:
+            (tuple): A tuple containing transformed bounding boxes, points, labels, and masks.
+        """
+        bboxes, points, labels, masks = super()._prepare_prompts(dst_shape, bboxes, points, labels, masks)
+        if bboxes is not None:
+            bboxes = bboxes.view(-1, 2, 2)
+            bbox_labels = torch.tensor([[2, 3]], dtype=torch.int32, device=bboxes.device).expand(len(bboxes), -1)
+            # NOTE: merge "boxes" and "points" into a single "points" input
+            # (where boxes are added at the beginning) to model.sam_prompt_encoder
+            if points is not None:
+                points = torch.cat([bboxes, points], dim=1)
+                labels = torch.cat([bbox_labels, labels], dim=1)
+            else:
+                points, labels = bboxes, bbox_labels
+        return bboxes, points, labels, masks
+
     def set_image(self, image):
         """
         Preprocesses and sets a single image for inference using the SAM2 model.

ultralytics/models/yolo/classify/train.py

@@ -8,7 +8,7 @@ from ultralytics.data import ClassificationDataset, build_dataloader
 from ultralytics.engine.trainer import BaseTrainer
 from ultralytics.models import yolo
 from ultralytics.nn.tasks import ClassificationModel
-from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK, colorstr
+from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
 from ultralytics.utils.plotting import plot_images, plot_results
 from ultralytics.utils.torch_utils import is_parallel, strip_optimizer, torch_distributed_zero_first
 
@@ -141,7 +141,6 @@ class ClassificationTrainer(BaseTrainer):
                     self.metrics = self.validator(model=f)
                     self.metrics.pop("fitness", None)
                     self.run_callbacks("on_fit_epoch_end")
-        LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}")
 
     def plot_training_samples(self, batch, ni):
         """Plots training samples with their annotations."""