ultralytics 8.3.157__py3-none-any.whl → 8.3.159__py3-none-any.whl

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.157"
+__version__ = "8.3.159"
 
 import os
 

ultralytics/data/augment.py

@@ -2928,7 +2928,7 @@ class ToTensor:
         the color channels are reversed from BGR to RGB.
 
         Args:
-            im (numpy.ndarray): Input image as a numpy array with shape (H, W, C) in BGR order.
+            im (numpy.ndarray): Input image as a numpy array with shape (H, W, C) in RGB order.
 
         Returns:
             (torch.Tensor): The transformed image as a PyTorch tensor in float32 or float16, normalized
@@ -2941,7 +2941,7 @@ class ToTensor:
             >>> print(tensor_img.shape, tensor_img.dtype)
             torch.Size([3, 640, 640]) torch.float16
         """
-        im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1])  # HWC to CHW -> BGR to RGB -> contiguous
+        im = np.ascontiguousarray(im.transpose((2, 0, 1)))  # HWC to CHW -> contiguous
         im = torch.from_numpy(im)  # to torch
         im = im.half() if self.half else im.float()  # uint8 to fp16/32
         im /= 255.0  # 0-255 to 0.0-1.0

ultralytics/engine/exporter.py

@@ -1152,7 +1152,9 @@ class Exporter:
         )
         if getattr(self.model, "end2end", False):
             raise ValueError("IMX export is not supported for end2end models.")
-        check_requirements(("model-compression-toolkit>=2.3.0", "sony-custom-layers>=0.3.0", "edge-mdt-tpc>=1.1.0"))
+        check_requirements(
+            ("model-compression-toolkit>=2.3.0,<2.4.1", "sony-custom-layers>=0.3.0", "edge-mdt-tpc>=1.1.0")
+        )
         check_requirements("imx500-converter[pt]>=3.16.1")  # Separate requirements for imx500-converter
 
         import model_compression_toolkit as mct

ultralytics/models/yolo/classify/predict.py

@@ -19,7 +19,6 @@ class ClassificationPredictor(BasePredictor):
 
     Attributes:
         args (dict): Configuration arguments for the predictor.
-        _legacy_transform_name (str): Name of the legacy transform class for backward compatibility.
 
     Methods:
         preprocess: Convert input images to model-compatible format.
@@ -50,7 +49,6 @@ class ClassificationPredictor(BasePredictor):
         """
         super().__init__(cfg, overrides, _callbacks)
         self.args.task = "classify"
-        self._legacy_transform_name = "ultralytics.yolo.data.augment.ToTensor"
 
     def setup_source(self, source):
         """Set up source and inference mode and classify transforms."""
@@ -58,22 +56,18 @@ class ClassificationPredictor(BasePredictor):
         updated = (
             self.model.model.transforms.transforms[0].size != max(self.imgsz)
             if hasattr(self.model.model, "transforms") and hasattr(self.model.model.transforms.transforms[0], "size")
-            else True
+            else False
+        )
+        self.transforms = (
+            classify_transforms(self.imgsz) if updated or not self.model.pt else self.model.model.transforms
         )
-        self.transforms = self.model.model.transforms if not updated else classify_transforms(self.imgsz)
 
     def preprocess(self, img):
         """Convert input images to model-compatible tensor format with appropriate normalization."""
         if not isinstance(img, torch.Tensor):
-            is_legacy_transform = any(
-                self._legacy_transform_name in str(transform) for transform in self.transforms.transforms
+            img = torch.stack(
+                [self.transforms(Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))) for im in img], dim=0
             )
-            if is_legacy_transform:  # Handle legacy transforms
-                img = torch.stack([self.transforms(im) for im in img], dim=0)
-            else:
-                img = torch.stack(
-                    [self.transforms(Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))) for im in img], dim=0
-                )
         img = (img if isinstance(img, torch.Tensor) else torch.from_numpy(img)).to(self.model.device)
         return img.half() if self.model.fp16 else img.float()  # Convert uint8 to fp16/32
 

ultralytics/models/yolo/detect/val.py

@@ -2,7 +2,7 @@
 
 import os
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 import numpy as np
 import torch
@@ -219,6 +219,7 @@ class DetectionValidator(BaseValidator):
                 self.confusion_matrix.plot(save_dir=self.save_dir, normalize=normalize, on_plot=self.on_plot)
         self.metrics.speed = self.speed
         self.metrics.confusion_matrix = self.confusion_matrix
+        self.metrics.save_dir = self.save_dir
 
     def get_stats(self) -> Dict[str, Any]:
         """
@@ -392,38 +393,73 @@ class DetectionValidator(BaseValidator):
         Returns:
             (Dict[str, Any]): Updated statistics dictionary with COCO/LVIS evaluation results.
         """
-        if self.args.save_json and (self.is_coco or self.is_lvis) and len(self.jdict):
-            pred_json = self.save_dir / "predictions.json"  # predictions
-            anno_json = (
-                self.data["path"]
-                / "annotations"
-                / ("instances_val2017.json" if self.is_coco else f"lvis_v1_{self.args.split}.json")
-            )  # annotations
+        pred_json = self.save_dir / "predictions.json"  # predictions
+        anno_json = (
+            self.data["path"]
+            / "annotations"
+            / ("instances_val2017.json" if self.is_coco else f"lvis_v1_{self.args.split}.json")
+        )  # annotations
+        return self.coco_evaluate(stats, pred_json, anno_json)
+
+    def coco_evaluate(
+        self,
+        stats: Dict[str, Any],
+        pred_json: str,
+        anno_json: str,
+        iou_types: Union[str, List[str]] = "bbox",
+        suffix: Union[str, List[str]] = "Box",
+    ) -> Dict[str, Any]:
+        """
+        Evaluate COCO/LVIS metrics using faster-coco-eval library.
+
+        Performs evaluation using the faster-coco-eval library to compute mAP metrics
+        for object detection. Updates the provided stats dictionary with computed metrics
+        including mAP50, mAP50-95, and LVIS-specific metrics if applicable.
+
+        Args:
+            stats (Dict[str, Any]): Dictionary to store computed metrics and statistics.
+            pred_json (str | Path]): Path to JSON file containing predictions in COCO format.
+            anno_json (str | Path]): Path to JSON file containing ground truth annotations in COCO format.
+            iou_types (str | List[str]]): IoU type(s) for evaluation. Can be single string or list of strings.
+                Common values include "bbox", "segm", "keypoints". Defaults to "bbox".
+            suffix (str | List[str]]): Suffix to append to metric names in stats dictionary. Should correspond
+                to iou_types if multiple types provided. Defaults to "Box".
 
+        Returns:
+            (Dict[str, Any]): Updated stats dictionary containing the computed COCO/LVIS evaluation metrics.
+        """
+        if self.args.save_json and (self.is_coco or self.is_lvis) and len(self.jdict):
             LOGGER.info(f"\nEvaluating faster-coco-eval mAP using {pred_json} and {anno_json}...")
             try:
                 for x in pred_json, anno_json:
                     assert x.is_file(), f"{x} file not found"
+                iou_types = [iou_types] if isinstance(iou_types, str) else iou_types
+                suffix = [suffix] if isinstance(suffix, str) else suffix
                 check_requirements("faster-coco-eval>=1.6.7")
                 from faster_coco_eval import COCO, COCOeval_faster
 
                 anno = COCO(anno_json)
                 pred = anno.loadRes(pred_json)
-                val = COCOeval_faster(anno, pred, iouType="bbox", lvis_style=self.is_lvis, print_function=LOGGER.info)
-                val.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # images to eval
-                val.evaluate()
-                val.accumulate()
-                val.summarize()
+                for i, iou_type in enumerate(iou_types):
+                    val = COCOeval_faster(
+                        anno, pred, iouType=iou_type, lvis_style=self.is_lvis, print_function=LOGGER.info
+                    )
+                    val.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # images to eval
+                    val.evaluate()
+                    val.accumulate()
+                    val.summarize()
+
+                    # update mAP50-95 and mAP50
+                    stats[f"metrics/mAP50({suffix[i][0]})"] = val.stats_as_dict["AP_all"]
+                    stats[f"metrics/mAP50-95({suffix[i][0]})"] = val.stats_as_dict["AP_50"]
 
-                # update mAP50-95 and mAP50
-                stats[self.metrics.keys[-1]] = val.stats_as_dict["AP_all"]
-                stats[self.metrics.keys[-2]] = val.stats_as_dict["AP_50"]
+                    if self.is_lvis:
+                        stats[f"metrics/APr({suffix[i][0]})"] = val.stats_as_dict["APr"]
+                        stats[f"metrics/APc({suffix[i][0]})"] = val.stats_as_dict["APc"]
+                        stats[f"metrics/APf({suffix[i][0]})"] = val.stats_as_dict["APf"]
 
                 if self.is_lvis:
-                    stats["metrics/APr(B)"] = val.stats_as_dict["APr"]
-                    stats["metrics/APc(B)"] = val.stats_as_dict["APc"]
-                    stats["metrics/APf(B)"] = val.stats_as_dict["APf"]
-                    stats["fitness"] = val.stats_as_dict["AP_all"]
+                    stats["fitness"] = stats["metrics/mAP50-95(B)"]  # always use box mAP50-95 for fitness
             except Exception as e:
                 LOGGER.warning(f"faster-coco-eval unable to run: {e}")
         return stats

ultralytics/models/yolo/pose/val.py

@@ -8,7 +8,6 @@ import torch
 
 from ultralytics.models.yolo.detect import DetectionValidator
 from ultralytics.utils import LOGGER, ops
-from ultralytics.utils.checks import check_requirements
 from ultralytics.utils.metrics import OKS_SIGMA, PoseMetrics, kpt_iou
 
 
@@ -289,29 +288,6 @@ class PoseValidator(DetectionValidator):
 
     def eval_json(self, stats: Dict[str, Any]) -> Dict[str, Any]:
         """Evaluate object detection model using COCO JSON format."""
-        if self.args.save_json and self.is_coco and len(self.jdict):
-            anno_json = self.data["path"] / "annotations/person_keypoints_val2017.json"  # annotations
-            pred_json = self.save_dir / "predictions.json"  # predictions
-            LOGGER.info(f"\nEvaluating faster-coco-eval mAP using {pred_json} and {anno_json}...")
-            try:
-                check_requirements("faster-coco-eval>=1.6.7")
-                from faster_coco_eval import COCO, COCOeval_faster
-
-                for x in anno_json, pred_json:
-                    assert x.is_file(), f"{x} file not found"
-                anno = COCO(anno_json)  # init annotations api
-                pred = anno.loadRes(pred_json)  # init predictions api (must pass string, not Path)
-                kwargs = dict(cocoGt=anno, cocoDt=pred, print_function=LOGGER.info)
-                for i, eval in enumerate(
-                    [COCOeval_faster(iouType="bbox", **kwargs), COCOeval_faster(iouType="keypoints", **kwargs)]
-                ):
-                    eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # im to eval
-                    eval.evaluate()
-                    eval.accumulate()
-                    eval.summarize()
-                    idx = i * 4 + 2
-                    # update mAP50-95 and mAP50
-                    stats[self.metrics.keys[idx + 1]], stats[self.metrics.keys[idx]] = eval.stats[:2]
-            except Exception as e:
-                LOGGER.warning(f"faster-coco-eval unable to run: {e}")
-        return stats
+        anno_json = self.data["path"] / "annotations/person_keypoints_val2017.json"  # annotations
+        pred_json = self.save_dir / "predictions.json"  # predictions
+        return super().coco_evaluate(stats, pred_json, anno_json, ["bbox", "keypoints"], suffix=["Box", "Pose"])

ultralytics/models/yolo/segment/val.py

@@ -272,45 +272,10 @@ class SegmentationValidator(DetectionValidator):
 
     def eval_json(self, stats: Dict[str, Any]) -> Dict[str, Any]:
         """Return COCO-style instance segmentation evaluation metrics."""
-        if self.args.save_json and (self.is_lvis or self.is_coco) and len(self.jdict):
-            pred_json = self.save_dir / "predictions.json"  # predictions
-            anno_json = (
-                self.data["path"]
-                / "annotations"
-                / ("instances_val2017.json" if self.is_coco else f"lvis_v1_{self.args.split}.json")
-            )  # annotations
-
-            LOGGER.info(f"\nEvaluating faster-coco-eval mAP using {pred_json} and {anno_json}...")
-            try:
-                for x in anno_json, pred_json:
-                    assert x.is_file(), f"{x} file not found"
-                check_requirements("faster-coco-eval>=1.6.7")
-                from faster_coco_eval import COCO, COCOeval_faster
-
-                anno = COCO(anno_json)  # init annotations api
-                pred = anno.loadRes(pred_json)  # init predictions api (must pass string, not Path)
-                kwargs = dict(cocoGt=anno, cocoDt=pred, lvis_style=self.is_lvis, print_function=LOGGER.info)
-                for i, eval in enumerate(
-                    [COCOeval_faster(iouType="bbox", **kwargs), COCOeval_faster(iouType="segm", **kwargs)]
-                ):
-                    eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # im to eval
-                    eval.evaluate()
-                    eval.accumulate()
-                    eval.summarize()
-                    idx = i * 4 + 2
-                    # update mAP50-95 and mAP50
-                    stats[self.metrics.keys[idx + 1]] = eval.stats_as_dict["AP_all"]
-                    stats[self.metrics.keys[idx]] = eval.stats_as_dict["AP_50"]
-
-                    if self.is_lvis:
-                        tag = "B" if i == 0 else "M"
-                        stats[f"metrics/APr({tag})"] = eval.stats_as_dict["APr"]
-                        stats[f"metrics/APc({tag})"] = eval.stats_as_dict["APc"]
-                        stats[f"metrics/APf({tag})"] = eval.stats_as_dict["APf"]
-
-                if self.is_lvis:
-                    stats["fitness"] = stats["metrics/mAP50-95(B)"]
-
-            except Exception as e:
-                LOGGER.warning(f"faster-coco-eval unable to run: {e}")
-        return stats
+        pred_json = self.save_dir / "predictions.json"  # predictions
+        anno_json = (
+            self.data["path"]
+            / "annotations"
+            / ("instances_val2017.json" if self.is_coco else f"lvis_v1_{self.args.split}.json")
+        )  # annotations
+        return super().coco_evaluate(stats, pred_json, anno_json, ["bbox", "segm"], suffix=["Box", "Mask"])

ultralytics/nn/autobackend.py

@@ -259,7 +259,11 @@ class AutoBackend(nn.Module):
                 session = onnxruntime.InferenceSession(w, providers=providers)
             else:
                 check_requirements(
-                    ["model-compression-toolkit>=2.3.0", "sony-custom-layers[torch]>=0.3.0", "onnxruntime-extensions"]
+                    [
+                        "model-compression-toolkit>=2.3.0,<2.4.1",
+                        "sony-custom-layers[torch]>=0.3.0",
+                        "onnxruntime-extensions",
+                    ]
                 )
                 w = next(Path(w).glob("*.onnx"))
                 LOGGER.info(f"Loading {w} for ONNX IMX inference...")

ultralytics/nn/text_model.py

@@ -6,6 +6,7 @@ from typing import List, Union
 
 import torch
 import torch.nn as nn
+from PIL import Image
 
 from ultralytics.utils import checks
 from ultralytics.utils.torch_utils import smart_inference_mode
@@ -68,7 +69,7 @@ class CLIP(TextModel):
         >>> print(text_features.shape)
     """
 
-    def __init__(self, size: str, device: torch.device):
+    def __init__(self, size: str, device: torch.device) -> None:
         """
         Initialize the CLIP text encoder.
 
@@ -85,12 +86,12 @@ class CLIP(TextModel):
             >>> text_features = clip_model.encode_text(["a photo of a cat", "a photo of a dog"])
         """
         super().__init__()
-        self.model = clip.load(size, device=device)[0]
+        self.model, self.image_preprocess = clip.load(size, device=device)
         self.to(device)
         self.device = device
         self.eval()
 
-    def tokenize(self, texts: Union[str, List[str]]):
+    def tokenize(self, texts: Union[str, List[str]]) -> torch.Tensor:
         """
         Convert input texts to CLIP tokens.
 
@@ -108,7 +109,7 @@ class CLIP(TextModel):
         return clip.tokenize(texts).to(self.device)
 
     @smart_inference_mode()
-    def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32):
+    def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32) -> torch.Tensor:
         """
         Encode tokenized texts into normalized feature vectors.
 
@@ -133,6 +134,38 @@ class CLIP(TextModel):
         txt_feats = txt_feats / txt_feats.norm(p=2, dim=-1, keepdim=True)
         return txt_feats
 
+    @smart_inference_mode()
+    def encode_image(self, image: Union[Image.Image, torch.Tensor], dtype: torch.dtype = torch.float32) -> torch.Tensor:
+        """
+        Encode preprocessed images into normalized feature vectors.
+
+        This method processes preprocessed image inputs through the CLIP model to generate feature vectors, which are then
+        normalized to unit length. These normalized vectors can be used for text-image similarity comparisons.
+
+        Args:
+            image (PIL.Image | torch.Tensor): Preprocessed image input. If a PIL Image is provided, it will be
+                converted to a tensor using the model's image preprocessing function.
+            dtype (torch.dtype, optional): Data type for output features.
+
+        Returns:
+            (torch.Tensor): Normalized image feature vectors with unit length (L2 norm = 1).
+
+        Examples:
+            >>> from ultralytics.nn.text_model import CLIP
+            >>> from PIL import Image
+            >>> clip_model = CLIP("ViT-B/32", device="cuda")
+            >>> image = Image.open("path/to/image.jpg")
+            >>> image_tensor = clip_model.image_preprocess(image).unsqueeze(0).to("cuda")
+            >>> features = clip_model.encode_image(image_tensor)
+            >>> features.shape
+            torch.Size([1, 512])
+        """
+        if isinstance(image, Image.Image):
+            image = self.image_preprocess(image).unsqueeze(0).to(self.device)
+        img_feats = self.model.encode_image(image).to(dtype)
+        img_feats = img_feats / img_feats.norm(p=2, dim=-1, keepdim=True)
+        return img_feats
+
 
 class MobileCLIP(TextModel):
     """
@@ -160,7 +193,7 @@ class MobileCLIP(TextModel):
 
     config_size_map = {"s0": "s0", "s1": "s1", "s2": "s2", "b": "b", "blt": "b"}
 
-    def __init__(self, size: str, device: torch.device):
+    def __init__(self, size: str, device: torch.device) -> None:
         """
         Initialize the MobileCLIP text encoder.
 
@@ -201,7 +234,7 @@ class MobileCLIP(TextModel):
         self.device = device
         self.eval()
 
-    def tokenize(self, texts: List[str]):
+    def tokenize(self, texts: List[str]) -> torch.Tensor:
         """
         Convert input texts to MobileCLIP tokens.
 
@@ -218,7 +251,7 @@ class MobileCLIP(TextModel):
         return self.tokenizer(texts).to(self.device)
 
     @smart_inference_mode()
-    def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32):
+    def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32) -> torch.Tensor:
         """
         Encode tokenized texts into normalized feature vectors.
 
@@ -286,7 +319,7 @@ class MobileCLIPTS(TextModel):
         self.tokenizer = clip.clip.tokenize
         self.device = device
 
-    def tokenize(self, texts: List[str]):
+    def tokenize(self, texts: List[str]) -> torch.Tensor:
         """
         Convert input texts to MobileCLIP tokens.
 
@@ -303,7 +336,7 @@ class MobileCLIPTS(TextModel):
         return self.tokenizer(texts).to(self.device)
 
     @smart_inference_mode()
-    def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32):
+    def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32) -> torch.Tensor:
         """
         Encode tokenized texts into normalized feature vectors.
 
@@ -322,10 +355,10 @@ class MobileCLIPTS(TextModel):
             torch.Size([2, 512])  # Actual dimension depends on model size
         """
         # NOTE: no need to do normalization here as it's embedded in the torchscript model
-        return self.encoder(texts)
+        return self.encoder(texts).to(dtype)
 
 
-def build_text_model(variant: str, device: torch.device = None):
+def build_text_model(variant: str, device: torch.device = None) -> TextModel:
     """
     Build a text encoding model based on the specified variant.
 

ultralytics/solutions/object_counter.py

@@ -133,7 +133,7 @@ class ObjectCounter(BaseSolution):
             str.capitalize(key): f"{'IN ' + str(value['IN']) if self.show_in else ''} "
             f"{'OUT ' + str(value['OUT']) if self.show_out else ''}".strip()
             for key, value in self.classwise_counts.items()
-            if value["IN"] != 0 or value["OUT"] != 0
+            if value["IN"] != 0 or value["OUT"] != 0 and (self.show_in or self.show_out)
         }
         if labels_dict:
             self.annotator.display_analytics(plot_im, labels_dict, (104, 31, 17), (255, 255, 255), self.margin)

ultralytics/solutions/similarity_search.py

@@ -5,10 +5,10 @@ from pathlib import Path
 from typing import Any, List
 
 import numpy as np
-import torch
 from PIL import Image
 
 from ultralytics.data.utils import IMG_FORMATS
+from ultralytics.nn.text_model import build_text_model
 from ultralytics.solutions.solutions import BaseSolution
 from ultralytics.utils.checks import check_requirements
 from ultralytics.utils.torch_utils import select_device
@@ -29,10 +29,8 @@ class VisualAISearch(BaseSolution):
         device (str): Computation device, e.g., 'cpu' or 'cuda'.
         faiss_index (str): Path to the FAISS index file.
         data_path_npy (str): Path to the numpy file storing image paths.
-        model_name (str): Name of the CLIP model to use.
         data_dir (Path): Path object for the data directory.
         model: Loaded CLIP model.
-        preprocess: CLIP preprocessing function.
         index: FAISS index for similarity search.
         image_paths (List[str]): List of image file paths.
 
@@ -51,13 +49,11 @@ class VisualAISearch(BaseSolution):
     def __init__(self, **kwargs: Any) -> None:
         """Initialize the VisualAISearch class with FAISS index and CLIP model."""
         super().__init__(**kwargs)
-        check_requirements(["git+https://github.com/ultralytics/CLIP.git", "faiss-cpu"])
+        check_requirements("faiss-cpu")
 
         self.faiss = __import__("faiss")
-        self.clip = __import__("clip")
         self.faiss_index = "faiss.index"
         self.data_path_npy = "paths.npy"
-        self.model_name = "ViT-B/32"
         self.data_dir = Path(self.CFG["data"])
         self.device = select_device(self.CFG["device"])
 
@@ -70,7 +66,7 @@ class VisualAISearch(BaseSolution):
             safe_download(url=f"{ASSETS_URL}/images.zip", unzip=True, retry=3)
             self.data_dir = Path("images")
 
-        self.model, self.preprocess = self.clip.load(self.model_name, device=self.device)
+        self.model = build_text_model("clip:ViT-B/32", device=self.device)
 
         self.index = None
         self.image_paths = []
@@ -79,16 +75,11 @@ class VisualAISearch(BaseSolution):
 
     def extract_image_feature(self, path: Path) -> np.ndarray:
         """Extract CLIP image embedding from the given image path."""
-        image = Image.open(path)
-        tensor = self.preprocess(image).unsqueeze(0).to(self.device)
-        with torch.no_grad():
-            return self.model.encode_image(tensor).cpu().numpy()
+        return self.model.encode_image(Image.open(path)).cpu().numpy()
 
     def extract_text_feature(self, text: str) -> np.ndarray:
         """Extract CLIP text embedding from the given text query."""
-        tokens = self.clip.tokenize([text]).to(self.device)
-        with torch.no_grad():
-            return self.model.encode_text(tokens).cpu().numpy()
+        return self.model.encode_text(self.model.tokenize([text])).cpu().numpy()
 
     def load_or_build_index(self) -> None:
         """

ultralytics/solutions/streamlit_inference.py

@@ -4,12 +4,15 @@ import io
 from typing import Any, List
 
 import cv2
+import torch
 
 from ultralytics import YOLO
 from ultralytics.utils import LOGGER
 from ultralytics.utils.checks import check_requirements
 from ultralytics.utils.downloads import GITHUB_ASSETS_STEMS
 
+torch.classes.__path__ = []  # Torch module __path__._path issue: https://github.com/datalab-to/marker/issues/442
+
 
 class Inference:
     """
@@ -133,7 +136,15 @@ class Inference:
     def configure(self) -> None:
         """Configure the model and load selected classes for inference."""
         # Add dropdown menu for model selection
-        available_models = [x.replace("yolo", "YOLO") for x in GITHUB_ASSETS_STEMS if x.startswith("yolo11")]
+        M_ORD, T_ORD = ["yolo11n", "yolo11s", "yolo11m", "yolo11l", "yolo11x"], ["", "-seg", "-pose", "-obb", "-cls"]
+        available_models = sorted(
+            [
+                x.replace("yolo", "YOLO")
+                for x in GITHUB_ASSETS_STEMS
+                if any(x.startswith(b) for b in M_ORD) and "grayscale" not in x
+            ],
+            key=lambda x: (M_ORD.index(x[:7].lower()), T_ORD.index(x[7:].lower() or "")),
+        )
         if self.model_path:  # If user provided the custom model, insert model without suffix as *.pt is added later
             available_models.insert(0, self.model_path.split(".pt", 1)[0])
         selected_model = self.st.sidebar.selectbox("Model", available_models)

ultralytics/utils/plotting.py

@@ -694,7 +694,7 @@ def plot_images(
 
     Args:
         labels (Dict[str, Any]): Dictionary containing detection data with keys like 'cls', 'bboxes', 'conf', 'masks', 'keypoints', 'batch_idx', 'img'.
-        images (Union[torch.Tensor, np.ndarray]): Batch of images to plot. Shape: (batch_size, channels, height, width).
+        images (torch.Tensor | np.ndarray]): Batch of images to plot. Shape: (batch_size, channels, height, width).
         paths (Optional[List[str]]): List of file paths for each image in the batch.
         fname (str): Output filename for the plotted image grid.
         names (Optional[Dict[int, str]]): Dictionary mapping class indices to class names.

{ultralytics-8.3.157.dist-info → ultralytics-8.3.159.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.157
+Version: 8.3.159
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -87,7 +87,7 @@ Dynamic: license-file
       <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/banner-yolov8.png" alt="Ultralytics YOLO banner"></a>
   </p>
 
-[中文](https://docs.ultralytics.com/zh) | [한국어](https://docs.ultralytics.com/ko) | [日本語](https://docs.ultralytics.com/ja) | [Русский](https://docs.ultralytics.com/ru) | [Deutsch](https://docs.ultralytics.com/de) | [Français](https://docs.ultralytics.com/fr) | [Español](https://docs.ultralytics.com/es) | [Português](https://docs.ultralytics.com/pt) | [Türkçe](https://docs.ultralytics.com/tr) | [Tiếng Việt](https://docs.ultralytics.com/vi) | [العربية](https://docs.ultralytics.com/ar) <br>
+[中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es) | [Português](https://docs.ultralytics.com/pt/) | [Türkçe](https://docs.ultralytics.com/tr/) | [Tiếng Việt](https://docs.ultralytics.com/vi/) | [العربية](https://docs.ultralytics.com/ar/) <br>
 
 <div>
     <a href="https://github.com/ultralytics/ultralytics/actions/workflows/ci.yml"><img src="https://github.com/ultralytics/ultralytics/actions/workflows/ci.yml/badge.svg" alt="Ultralytics CI"></a>

{ultralytics-8.3.157.dist-info → ultralytics-8.3.159.dist-info}/RECORD

@@ -7,7 +7,7 @@ tests/test_exports.py,sha256=HmMKOTCia9ZDC0VYc_EPmvBTM5LM5eeI1NF_pKjLpd8,9677
 tests/test_integrations.py,sha256=kl_AKmE_Qs1GB0_91iVwbzNxofm_hFTt0zzU6JF-pg4,6323
 tests/test_python.py,sha256=nOoaPDg-0j7ZPRz9-uGFny3uocxjUM1ze5wA3BpGxKQ,27865
 tests/test_solutions.py,sha256=tuf6n_fsI8KvSdJrnc-cqP2qYdiYqCWuVrx0z9dOz3Q,13213
-ultralytics/__init__.py,sha256=2mwBem7xtvNmrW5pBkCtYV3rgq4UvYlvOHu6FkTIDKs,730
+ultralytics/__init__.py,sha256=sbeS4zCdUAcxO1GIm2GxM1Pk92RQ2Kom9Fk52c9syUs,730
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=ds63URbbeRj5UxkCSyl62OrNw6HQy7xeit5-0wGDEKg,39699
@@ -105,7 +105,7 @@ ultralytics/cfg/trackers/botsort.yaml,sha256=TpRaK5kH_-QbjCQ7ekM4s_7j8I8ti3q8Hs7
 ultralytics/cfg/trackers/bytetrack.yaml,sha256=6u-tiZlk16EqEwkNXaMrza6PAQmWj_ypgv26LGCtPDg,886
 ultralytics/data/__init__.py,sha256=nAXaL1puCc7z_NjzQNlJnhbVhT9Fla2u7Dsqo7q1dAc,644
 ultralytics/data/annotator.py,sha256=uAgd7K-yudxiwdNqHz0ubfFg5JsfNlae4cgxdvCMyuY,3030
-ultralytics/data/augment.py,sha256=yAUn0P7z9dQ37DwoIXF6Tz2PvTxxHMMj54311mOSWP8,129050
+ultralytics/data/augment.py,sha256=Zxqp6dWKALAbUYha-R_MVrcysdlBj9glm4Nsth_JLrg,129030
 ultralytics/data/base.py,sha256=mRcuehK1thNuuzQGL6D1AaZkod71oHRdYTod_zdQZQg,19688
 ultralytics/data/build.py,sha256=13gPxCJIZRjgcNh7zbzanCgtyK6_oZM0ho9KQhHcM6c,11153
 ultralytics/data/converter.py,sha256=oKW8ODtvFOKBx9Un8n87xUUm3b5GStU4ViIBH5UDylM,27200
@@ -119,7 +119,7 @@ ultralytics/data/scripts/get_coco.sh,sha256=UuJpJeo3qQpTHVINeOpmP0NYmg8PhEFE3A8J
 ultralytics/data/scripts/get_coco128.sh,sha256=qmRQl_hOKrsdHrTrnyQuFIH01oDz3lfaz138OgGfLt8,650
 ultralytics/data/scripts/get_imagenet.sh,sha256=hr42H16bM47iT27rgS7MpEo-GeOZAYUQXgr0B2cwn48,1705
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
-ultralytics/engine/exporter.py,sha256=Q3y4yo0h8zLuCWE_FEvGV_eUwMfKjDrdZsmN_bc24R8,73041
+ultralytics/engine/exporter.py,sha256=n9mRjOWdX-3T9SroICwdMaRRVi9h98coAfCzDYopyW4,73070
 ultralytics/engine/model.py,sha256=DwugtVxUbCGzpY2pStFMcEloim0ai6LrT6kTbwskSJ8,53302
 ultralytics/engine/predictor.py,sha256=88zrgZP91ehwdeGl8BM_cQ_caeuwKIPDy3OzxcRBjTU,22474
 ultralytics/engine/results.py,sha256=Mb8pBTOrBtQh0PQtGVbhRZ_C1VyqYFumjLggiKCRIJs,72295
@@ -166,13 +166,13 @@ ultralytics/models/utils/ops.py,sha256=Pr77n8XW25SUEx4X3bBvXcVIbRdJPoaXJuG0KWWaw
 ultralytics/models/yolo/__init__.py,sha256=or0j5xvcM0usMlsFTYhNAOcQUri7reD0cD9JR5b7zDk,307
 ultralytics/models/yolo/model.py,sha256=C0wInQC6rFuFOGpdAen1s2e5LIFDmqevto8uPbpmB8c,18449
 ultralytics/models/yolo/classify/__init__.py,sha256=9--HVaNOfI1K7rn_rRqclL8FUAnpfeBrRqEQIaQw2xM,383
-ultralytics/models/yolo/classify/predict.py,sha256=_GiN6muuZOBrMS1KER85FE4ktcw_Onn1bZdGvpbsGCE,4618
+ultralytics/models/yolo/classify/predict.py,sha256=FqAC2YXe25bRwedMZhF3Lw0waoY-a60xMKELhxApP9I,4149
 ultralytics/models/yolo/classify/train.py,sha256=V-hevc6X7xemnpyru84OfTRA77eNnkVSMEz16_OUvo4,10244
 ultralytics/models/yolo/classify/val.py,sha256=YakPxBVZCd85Kp4wFKx8KH6JJFiU7nkFS3r9_ZSwFRM,10036
 ultralytics/models/yolo/detect/__init__.py,sha256=GIRsLYR-kT4JJx7lh4ZZAFGBZj0aebokuU0A7JbjDVA,257
 ultralytics/models/yolo/detect/predict.py,sha256=ySUsdIf8dw00bzWhcxN1jZwLWKPRT2M7-N7TNL3o4zo,5387
 ultralytics/models/yolo/detect/train.py,sha256=HlaCoHJ6Y2TpCXXWabMRZApAYqBvjuM_YQJUV5JYCvw,9907
-ultralytics/models/yolo/detect/val.py,sha256=nY3NhT50fMLk0wMwQBv3AnLAVoPMI6mx37OJw9-QT5A,18541
+ultralytics/models/yolo/detect/val.py,sha256=Yhs7SdS8O_4_61N_ZxzGaEfm4tnpEzIRV5XcMsrI-e4,20485
 ultralytics/models/yolo/obb/__init__.py,sha256=tQmpG8wVHsajWkZdmD6cjGohJ4ki64iSXQT8JY_dydo,221
 ultralytics/models/yolo/obb/predict.py,sha256=4r1eSld6TNJlk9JG56e-DX6oPL8uBBqiuztyBpxWlHE,2888
 ultralytics/models/yolo/obb/train.py,sha256=bnYFAMur7Uvbw5Dc09-S2ge7B05iGX-t37Ksgc0ef6g,3921
@@ -180,11 +180,11 @@ ultralytics/models/yolo/obb/val.py,sha256=nT82lKXewUw3bgX45Ms045rzcYn2A1j8g3Dxig
 ultralytics/models/yolo/pose/__init__.py,sha256=63xmuHZLNzV8I76HhVXAq4f2W0KTk8Oi9eL-Y204LyQ,227
 ultralytics/models/yolo/pose/predict.py,sha256=M0C7ZfVXx4QXgv-szjnaXYEPas76ZLGAgDNNh1GG0vI,3743
 ultralytics/models/yolo/pose/train.py,sha256=GyvNnDPJ3UFq_90HN8_FJ0dbwRkw3JJTVpkMFH0vC0o,5457
-ultralytics/models/yolo/pose/val.py,sha256=8d7AthoJYUK8BK01ptxpANdcR9_-REEMKicB1hCYgio,15330
+ultralytics/models/yolo/pose/val.py,sha256=abAll3lWT6IRwoHOFNsgAZyNQtTtPBXHq0Wszpu9p5E,13994
 ultralytics/models/yolo/segment/__init__.py,sha256=3IThhZ1wlkY9FvmWm9cE-5-ZyE6F1FgzAtQ6jOOFzzw,275
 ultralytics/models/yolo/segment/predict.py,sha256=qlprQCZn4_bpjpI08U0MU9Q9_1gpHrw_7MXwtXE1l1Y,5377
 ultralytics/models/yolo/segment/train.py,sha256=XrPkXUiNu1Jvhn8iDew_RaLLjZA3un65rK-QH9mtNIw,3802
-ultralytics/models/yolo/segment/val.py,sha256=Iai-oK1XeD6y23WWq7FouiE_Az7o4C24E770OPCO2WY,14168
+ultralytics/models/yolo/segment/val.py,sha256=AnvY0O7HhD5xZ2BE2artLTAVW4SNmHbVopBJsYRcmk8,12328
 ultralytics/models/yolo/world/__init__.py,sha256=nlh8I6t8hMGz_vZg8QSlsUW1R-2eKvn9CGUoPPQEGhA,131
 ultralytics/models/yolo/world/train.py,sha256=94_hgCluzsv39JkBVDmR2gjuycYjeJC8wVrCfrjpENk,7806
 ultralytics/models/yolo/world/train_world.py,sha256=YJm37ZTgr0CoE_sYrjxN45w9mICr2RMWfWZrriiHqbM,9022
@@ -194,9 +194,9 @@ ultralytics/models/yolo/yoloe/train.py,sha256=Dt6orqXcQTzyoAqMVvleP1FQbXChMvEj3Q
 ultralytics/models/yolo/yoloe/train_seg.py,sha256=aCV7M8oQOvODFnU4piZdJh3tIrBJYAzZfRVRx1vRgxo,4956
 ultralytics/models/yolo/yoloe/val.py,sha256=yebPkxwKKt__cY05Zbh1YXg4_BKzzpcDc3Cv3FJ5SAA,9769
 ultralytics/nn/__init__.py,sha256=rjociYD9lo_K-d-1s6TbdWklPLjTcEHk7OIlRDJstIE,615
-ultralytics/nn/autobackend.py,sha256=smyYoozUOtXPNKW9Rd24dZX-EY36CDvXMr7xH-uLEs0,41256
+ultralytics/nn/autobackend.py,sha256=yk1IXPChI1D7rupJdH2TMvUqFv6PVmBU3tgfZOquQ_8,41358
 ultralytics/nn/tasks.py,sha256=aCXYmWan2LTznH3i_-2OwMagG3ZwnVL1gjKtY-3oShM,72456
-ultralytics/nn/text_model.py,sha256=m4jDB5bzOLOS8XNmFi9oQk-skzRHiIpJy4K-_SIARR0,13498
+ultralytics/nn/text_model.py,sha256=cYwD-0el4VeToDBP4iPFOQGqyEQatJOBHrVyONL3K_s,15282
 ultralytics/nn/modules/__init__.py,sha256=2nY0X69Z5DD5SWt6v3CUTZa5gXSzC9TQr3VTVqhyGho,3158
 ultralytics/nn/modules/activation.py,sha256=75JcIMH2Cu9GTC2Uf55r_5YLpxcrXQDaVoeGQ0hlUAU,2233
 ultralytics/nn/modules/block.py,sha256=JfOjWEgUNfwFCt-P2awhga4B7GXeDlkKVhLBp7oA-Es,70652
@@ -212,16 +212,16 @@ ultralytics/solutions/distance_calculation.py,sha256=r05_ufxb2Mpw3EIX8X32PIWlh9r
 ultralytics/solutions/heatmap.py,sha256=vEdzLSYCNIFC9CsBWYSnCLiM8xNuYLJ-1i7enjQgOQw,5516
 ultralytics/solutions/instance_segmentation.py,sha256=qsIQkvuR1Ur2bdEsCCJP2IEO1Hz2l0wfR2KUBo247xE,3795
 ultralytics/solutions/object_blurrer.py,sha256=wHbfrudh6li_JADc-dTHGGMI8GU-MvesoTvVlX6YuYc,3998
-ultralytics/solutions/object_counter.py,sha256=Zt6FNfPSPN3L69zks1u4DSPM3A6mdl7p29im4O-2QFQ,9406
+ultralytics/solutions/object_counter.py,sha256=djg6XIgOuseoKCEY5PrLRf4Z1JjbTEBXrERRV8dOSlU,9442
 ultralytics/solutions/object_cropper.py,sha256=mS3iT_CgqfqG9ldM_AM5ptq5bfYFyTycPQY5DxxMlSA,3525
 ultralytics/solutions/parking_management.py,sha256=IfPUn15aelxz6YZNo9WYkVEl5IOVSw8VD0OrpKtExPE,13613
 ultralytics/solutions/queue_management.py,sha256=u0VFzRqa0OxIWY7xXItsXEm073CzkQGFhhXG-6VK3SI,4393
 ultralytics/solutions/region_counter.py,sha256=j6f5VAaE1JWGdWOecZpWMFp6yF1GdCnHjftN6CRybjQ,5967
 ultralytics/solutions/security_alarm.py,sha256=U6FTbg3cthKLfWeLunsFhOJvB6GGmwYDDxZ3K0GCx-Q,6351
-ultralytics/solutions/similarity_search.py,sha256=Tx5R_IVzQjUVLrraS0oJkoJLkx8dJCyaf_Nwbu_4yyo,9982
+ultralytics/solutions/similarity_search.py,sha256=ri8bf65tt6xyS6Xa-ikj2AgvfCsFOtaQk6IM_k7FhKg,9579
 ultralytics/solutions/solutions.py,sha256=N5t1DgZpuFBbDvLVZ7wRkafmgu8SS1VC9VNjuupglwQ,37532
 ultralytics/solutions/speed_estimation.py,sha256=chg_tBuKFw3EnFiv_obNDaUXLAo-FypxC7gsDeB_VUI,5878
-ultralytics/solutions/streamlit_inference.py,sha256=lqHh0UDCVmWIeh3yzpvoV7j9K6Ipx7pJBkOsb0ZpZes,10034
+ultralytics/solutions/streamlit_inference.py,sha256=SqL-YxU3RCxCKscH2AYUTkmJknilV9jCCco6ufqsFk4,10501
 ultralytics/solutions/trackzone.py,sha256=kIS94rNfL3yVPAtSbnW8F-aLMxXowQtsfKNB-jLezz8,3941
 ultralytics/solutions/vision_eye.py,sha256=nlIdXhfM5EwJh4vqVhz3AEOoHXIELMo1OG8Cr1tMQRw,3008
 ultralytics/solutions/templates/similarity-search.html,sha256=vdz9XCH6VHbksvSW_sSg6Z2xVp82_EanaS_rY7xjZBE,4743
@@ -249,7 +249,7 @@ ultralytics/utils/loss.py,sha256=fbOWc3Iu0QOJiWbi-mXWA9-1otTYlehtmUsI7os7ydM,397
 ultralytics/utils/metrics.py,sha256=1XaTT3n3tfLms6LOCiEzg_QGHQJzjZmfjFoAYsCCc24,62646
 ultralytics/utils/ops.py,sha256=Jkh80ujyi0XDQwNqCUYyomH8NQ145AH9doMUS8Vt8GE,34545
 ultralytics/utils/patches.py,sha256=P2uQy7S4RzSHBfwJEXJsjyuRUluaaUusiVU84lV3moQ,6577
-ultralytics/utils/plotting.py,sha256=OzanAqs7Z02ddAd1LiXce0Jjjo8DSjAjbKViE6S5CKg,47176
+ultralytics/utils/plotting.py,sha256=SCpG5DHZUPlFUsu72kNH3DYGpsjgkd3eIZ9-QTllY88,47171
 ultralytics/utils/tal.py,sha256=aXawOnhn8ni65tJWIW-PYqWr_TRvltbHBjrTo7o6lDQ,20924
 ultralytics/utils/torch_utils.py,sha256=iIAjf2g4hikzBeHvKN-EQK8QFlC_QtWWRuYQuBF2zIk,39184
 ultralytics/utils/triton.py,sha256=M7qe4RztiADBJQEWQKaIQsp94ERFJ_8_DUHDR6TXEOM,5410
@@ -265,9 +265,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=j8pecmlcsM8FGzLKWoBw5xUsi5t8E5HuxY
 ultralytics/utils/callbacks/raytune.py,sha256=S6Bq16oQDQ8BQgnZzA0zJHGN_BBr8iAM_WtGoLiEcwg,1283
 ultralytics/utils/callbacks/tensorboard.py,sha256=MDPBW7aDes-66OE6YqKXXvqA_EocjzEMHWGM-8z9vUQ,5281
 ultralytics/utils/callbacks/wb.py,sha256=Tm_-aRr2CN32MJkY9tylpMBJkb007-MSRNSQ7rDJ5QU,7521
-ultralytics-8.3.157.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.157.dist-info/METADATA,sha256=vZ9QsDSUEX148oGlo6qNsbooXGnT_pK-mlPBdc0k-L4,37212
-ultralytics-8.3.157.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ultralytics-8.3.157.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.157.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.157.dist-info/RECORD,,
+ultralytics-8.3.159.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.159.dist-info/METADATA,sha256=rDjTuSzOBsjgNEKv23itvJdbVi69RoZGid-Nx5IjscA,37222
+ultralytics-8.3.159.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ultralytics-8.3.159.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.159.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.159.dist-info/RECORD,,