ultralytics 8.0.114__py3-none-any.whl → 8.0.116__py3-none-any.whl

ultralytics/__init__.py

@@ -1,11 +1,12 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = '8.0.114'
+__version__ = '8.0.116'
 
 from ultralytics.hub import start
 from ultralytics.vit.rtdetr import RTDETR
 from ultralytics.vit.sam import SAM
 from ultralytics.yolo.engine.model import YOLO
+from ultralytics.yolo.nas import NAS
 from ultralytics.yolo.utils.checks import check_yolo as checks
 
-__all__ = '__version__', 'YOLO', 'SAM', 'RTDETR', 'checks', 'start'  # allow simpler import
+__all__ = '__version__', 'YOLO', 'NAS', 'SAM', 'RTDETR', 'checks', 'start'  # allow simpler import

ultralytics/vit/rtdetr/model.py

@@ -110,3 +110,12 @@ class RTDETR:
         if args.batch == DEFAULT_CFG.batch:
             args.batch = 1  # default to 1 if not modified
         return Exporter(overrides=args)(model=self.model)
+
+    def __call__(self, source=None, stream=False, **kwargs):
+        """Calls the 'predict' function with given arguments to perform object detection."""
+        return self.predict(source, stream, **kwargs)
+
+    def __getattr__(self, attr):
+        """Raises error if object has no requested attribute."""
+        name = self.__class__.__name__
+        raise AttributeError(f"'{name}' object has no attribute '{attr}'. See valid attributes below.\n{self.__doc__}")

ultralytics/vit/sam/model.py

@@ -35,6 +35,15 @@ class SAM:
         """Run validation given dataset."""
         raise NotImplementedError("SAM models don't support validation")
 
+    def __call__(self, source=None, stream=False, **kwargs):
+        """Calls the 'predict' function with given arguments to perform object detection."""
+        return self.predict(source, stream, **kwargs)
+
+    def __getattr__(self, attr):
+        """Raises error if object has no requested attribute."""
+        name = self.__class__.__name__
+        raise AttributeError(f"'{name}' object has no attribute '{attr}'. See valid attributes below.\n{self.__doc__}")
+
     def info(self, detailed=False, verbose=True):
         """
         Logs model info.

ultralytics/yolo/data/utils.py

@@ -138,7 +138,7 @@ def polygon2mask(imgsz, polygons, color=1, downsample_ratio=1):
     """
     Args:
         imgsz (tuple): The image size.
-        polygons (np.ndarray): [N, M], N is the number of polygons, M is the number of points(Be divided by 2).
+        polygons (list[np.ndarray]): [N, M], N is the number of polygons, M is the number of points(Be divided by 2).
         color (int): color
         downsample_ratio (int): downsample ratio
     """

ultralytics/yolo/engine/model.py

@@ -9,8 +9,8 @@ from ultralytics.nn.tasks import (ClassificationModel, DetectionModel, PoseModel
                                   attempt_load_one_weight, guess_model_task, nn, yaml_model_load)
 from ultralytics.yolo.cfg import get_cfg
 from ultralytics.yolo.engine.exporter import Exporter
-from ultralytics.yolo.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, RANK, ROOT, callbacks,
-                                    is_git_dir, yaml_load)
+from ultralytics.yolo.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, NUM_THREADS, RANK, ROOT,
+                                    callbacks, is_git_dir, yaml_load)
 from ultralytics.yolo.utils.checks import check_file, check_imgsz, check_pip_update_available, check_yaml
 from ultralytics.yolo.utils.downloads import GITHUB_ASSET_STEMS
 from ultralytics.yolo.utils.torch_utils import smart_inference_mode
@@ -119,7 +119,7 @@ class YOLO:
     def is_hub_model(model):
         """Check if the provided model is a HUB model."""
         return any((
-            model.startswith('https://hub.ultra'),  # i.e. https://hub.ultralytics.com/models/MODEL_ID
+            model.startswith('https://hub.ultralytics.com/models/'),  # i.e. https://hub.ultralytics.com/models/MODEL_ID
             [len(x) for x in model.split('_')] == [42, 20],  # APIKEY_MODELID
             len(model) == 20 and not Path(model).exists() and all(x not in model for x in './\\')))  # MODELID
 
@@ -391,7 +391,7 @@ class YOLO:
              grace_period: int = 10,
              gpu_per_trial: int = None,
              max_samples: int = 10,
-             train_args: dict = {}):
+             train_args: dict = None):
         """
         Runs hyperparameter tuning using Ray Tune.
 
@@ -409,6 +409,8 @@ class YOLO:
         Raises:
             ModuleNotFoundError: If Ray Tune is not installed.
         """
+        if train_args is None:
+            train_args = {}
 
         try:
             from ultralytics.yolo.utils.tuner import (ASHAScheduler, RunConfig, WandbLoggerCallback, default_space,
@@ -443,7 +445,7 @@ class YOLO:
         space['data'] = data
 
         # Define the trainable function with allocated resources
-        trainable_with_resources = tune.with_resources(_tune, {'cpu': 8, 'gpu': gpu_per_trial if gpu_per_trial else 0})
+        trainable_with_resources = tune.with_resources(_tune, {'cpu': NUM_THREADS, 'gpu': gpu_per_trial or 0})
 
         # Define the ASHA scheduler for hyperparameter search
         asha_scheduler = ASHAScheduler(time_attr='epoch',
@@ -454,7 +456,7 @@ class YOLO:
                                        reduction_factor=3)
 
         # Define the callbacks for the hyperparameter search
-        tuner_callbacks = [WandbLoggerCallback(project='yolov8_tune')] if wandb else []
+        tuner_callbacks = [WandbLoggerCallback(project='YOLOv8-tune')] if wandb else []
 
         # Create the Ray Tune hyperparameter search tuner
         tuner = tune.Tuner(trainable_with_resources,

ultralytics/yolo/nas/__init__.py

@@ -0,0 +1,7 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from .model import NAS
+from .predict import NASPredictor
+from .val import NASValidator
+
+__all__ = 'NASPredictor', 'NASValidator', 'NAS'

ultralytics/yolo/nas/model.py

@@ -0,0 +1,125 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+"""
+# NAS model interface
+"""
+
+from pathlib import Path
+
+import torch
+
+from ultralytics.yolo.cfg import get_cfg
+from ultralytics.yolo.engine.exporter import Exporter
+from ultralytics.yolo.utils import DEFAULT_CFG, DEFAULT_CFG_DICT, LOGGER, ROOT, is_git_dir
+from ultralytics.yolo.utils.checks import check_imgsz
+
+from ...yolo.utils.torch_utils import model_info, smart_inference_mode
+from .predict import NASPredictor
+from .val import NASValidator
+
+
+class NAS:
+
+    def __init__(self, model='yolo_nas_s.pt') -> None:
+        # Load or create new NAS model
+        import super_gradients
+
+        self.predictor = None
+        suffix = Path(model).suffix
+        if suffix == '.pt':
+            self._load(model)
+        elif suffix == '':
+            self.model = super_gradients.training.models.get(model, pretrained_weights='coco')
+        self.task = 'detect'
+        self.model.args = DEFAULT_CFG_DICT  # attach args to model
+
+        # Standardize model
+        self.model.fuse = lambda verbose: self.model
+        self.model.stride = torch.tensor([32])
+        self.model.names = dict(enumerate(self.model._class_names))
+        self.model.is_fused = lambda: False  # for info()
+        self.model.yaml = {}  # for info()
+        self.info()
+
+    @smart_inference_mode()
+    def _load(self, weights: str):
+        self.model = torch.load(weights)
+
+    @smart_inference_mode()
+    def predict(self, source=None, stream=False, **kwargs):
+        """
+        Perform prediction using the YOLO model.
+
+        Args:
+            source (str | int | PIL | np.ndarray): The source of the image to make predictions on.
+                          Accepts all source types accepted by the YOLO model.
+            stream (bool): Whether to stream the predictions or not. Defaults to False.
+            **kwargs : Additional keyword arguments passed to the predictor.
+                       Check the 'configuration' section in the documentation for all available options.
+
+        Returns:
+            (List[ultralytics.yolo.engine.results.Results]): The prediction results.
+        """
+        if source is None:
+            source = ROOT / 'assets' if is_git_dir() else 'https://ultralytics.com/images/bus.jpg'
+            LOGGER.warning(f"WARNING ⚠️ 'source' is missing. Using 'source={source}'.")
+        overrides = dict(conf=0.25, task='detect', mode='predict')
+        overrides.update(kwargs)  # prefer kwargs
+        if not self.predictor:
+            self.predictor = NASPredictor(overrides=overrides)
+            self.predictor.setup_model(model=self.model)
+        else:  # only update args if predictor is already setup
+            self.predictor.args = get_cfg(self.predictor.args, overrides)
+        return self.predictor(source, stream=stream)
+
+    def train(self, **kwargs):
+        """Function trains models but raises an error as NAS models do not support training."""
+        raise NotImplementedError("NAS models don't support training")
+
+    def val(self, **kwargs):
+        """Run validation given dataset."""
+        overrides = dict(task='detect', mode='val')
+        overrides.update(kwargs)  # prefer kwargs
+        args = get_cfg(cfg=DEFAULT_CFG, overrides=overrides)
+        args.imgsz = check_imgsz(args.imgsz, max_dim=1)
+        validator = NASValidator(args=args)
+        validator(model=self.model)
+        self.metrics = validator.metrics
+        return validator.metrics
+
+    @smart_inference_mode()
+    def export(self, **kwargs):
+        """
+        Export model.
+
+        Args:
+            **kwargs : Any other args accepted by the predictors. To see all args check 'configuration' section in docs
+        """
+        overrides = dict(task='detect')
+        overrides.update(kwargs)
+        overrides['mode'] = 'export'
+        args = get_cfg(cfg=DEFAULT_CFG, overrides=overrides)
+        args.task = self.task
+        if args.imgsz == DEFAULT_CFG.imgsz:
+            args.imgsz = self.model.args['imgsz']  # use trained imgsz unless custom value is passed
+        if args.batch == DEFAULT_CFG.batch:
+            args.batch = 1  # default to 1 if not modified
+        return Exporter(overrides=args)(model=self.model)
+
+    def info(self, detailed=False, verbose=True):
+        """
+        Logs model info.
+
+        Args:
+            detailed (bool): Show detailed information about model.
+            verbose (bool): Controls verbosity.
+        """
+        return model_info(self.model, detailed=detailed, verbose=verbose, imgsz=640)
+
+    def __call__(self, source=None, stream=False, **kwargs):
+        """Calls the 'predict' function with given arguments to perform object detection."""
+        return self.predict(source, stream, **kwargs)
+
+    def __getattr__(self, attr):
+        """Raises error if object has no requested attribute."""
+        name = self.__class__.__name__
+        raise AttributeError(f"'{name}' object has no attribute '{attr}'. See valid attributes below.\n{self.__doc__}")

ultralytics/yolo/nas/predict.py

@@ -0,0 +1,35 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+import torch
+
+from ultralytics.yolo.engine.predictor import BasePredictor
+from ultralytics.yolo.engine.results import Results
+from ultralytics.yolo.utils import ops
+from ultralytics.yolo.utils.ops import xyxy2xywh
+
+
+class NASPredictor(BasePredictor):
+
+    def postprocess(self, preds_in, img, orig_imgs):
+        """Postprocesses predictions and returns a list of Results objects."""
+
+        # Cat boxes and class scores
+        boxes = xyxy2xywh(preds_in[0][0])
+        preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1)
+
+        preds = ops.non_max_suppression(preds,
+                                        self.args.conf,
+                                        self.args.iou,
+                                        agnostic=self.args.agnostic_nms,
+                                        max_det=self.args.max_det,
+                                        classes=self.args.classes)
+
+        results = []
+        for i, pred in enumerate(preds):
+            orig_img = orig_imgs[i] if isinstance(orig_imgs, list) else orig_imgs
+            if not isinstance(orig_imgs, torch.Tensor):
+                pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
+            path = self.batch[0]
+            img_path = path[i] if isinstance(path, list) else path
+            results.append(Results(orig_img=orig_img, path=img_path, names=self.model.names, boxes=pred))
+        return results

ultralytics/yolo/nas/val.py

@@ -0,0 +1,25 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+import torch
+
+from ultralytics.yolo.utils import ops
+from ultralytics.yolo.utils.ops import xyxy2xywh
+from ultralytics.yolo.v8.detect import DetectionValidator
+
+__all__ = ['NASValidator']
+
+
+class NASValidator(DetectionValidator):
+
+    def postprocess(self, preds_in):
+        """Apply Non-maximum suppression to prediction outputs."""
+        boxes = xyxy2xywh(preds_in[0][0])
+        preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1)
+        return ops.non_max_suppression(preds,
+                                       self.args.conf,
+                                       self.args.iou,
+                                       labels=self.lb,
+                                       multi_label=False,
+                                       agnostic=self.args.single_cls,
+                                       max_det=self.args.max_det,
+                                       max_time_img=0.5)

ultralytics/yolo/utils/__init__.py

@@ -37,7 +37,7 @@ AUTOINSTALL = str(os.getenv('YOLO_AUTOINSTALL', True)).lower() == 'true'  # glob
 VERBOSE = str(os.getenv('YOLO_VERBOSE', True)).lower() == 'true'  # global verbose mode
 TQDM_BAR_FORMAT = '{l_bar}{bar:10}{r_bar}'  # tqdm bar format
 LOGGING_NAME = 'ultralytics'
-MACOS, LINUX, WINDOWS = (platform.system() == x for x in ['Darwin', 'Linux', 'Windows'])  # environment booleans
+MACOS, LINUX, WINDOWS = (platform.system() == x for x in {'Darwin', 'Linux', 'Windows'})  # environment booleans
 HELP_MSG = \
     """
     Usage examples for running YOLOv8:
@@ -224,6 +224,11 @@ def set_logging(name=LOGGING_NAME, verbose=True):
                 'propagate': False}}})
 
 
+def emojis(string=''):
+    """Return platform-dependent emoji-safe version of string."""
+    return string.encode().decode('ascii', 'ignore') if WINDOWS else string
+
+
 class EmojiFilter(logging.Filter):
     """
     A custom logging filter class for removing emojis in log messages.
@@ -533,6 +538,7 @@ def get_user_config_dir(sub_dir='Ultralytics'):
     # GCP and AWS lambda fix, only /tmp is writeable
     if not is_dir_writeable(str(path.parent)):
         path = Path('/tmp') / sub_dir
+        LOGGER.warning(f"WARNING ⚠️ user config directory is not writeable, defaulting to '{path}'.")
 
     # Create the subdirectory if it does not exist
     path.mkdir(parents=True, exist_ok=True)
@@ -544,11 +550,6 @@ USER_CONFIG_DIR = Path(os.getenv('YOLO_CONFIG_DIR', get_user_config_dir()))  # U
 SETTINGS_YAML = USER_CONFIG_DIR / 'settings.yaml'
 
 
-def emojis(string=''):
-    """Return platform-dependent emoji-safe version of string."""
-    return string.encode().decode('ascii', 'ignore') if WINDOWS else string
-
-
 def colorstr(*input):
     """Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e.  colorstr('blue', 'hello world')."""
     *args, string = input if len(input) > 1 else ('blue', 'bold', input[0])  # color arguments, string

ultralytics/yolo/utils/benchmarks.py

@@ -90,7 +90,7 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt',
                 filename = model.ckpt_path or model.cfg
                 export = model  # PyTorch format
             else:
-                filename = model.export(imgsz=imgsz, format=format, half=half, int8=int8, device=device)  # all others
+                filename = model.export(imgsz=imgsz, format=format, half=half, int8=int8, device=device, verbose=False)
                 export = YOLO(filename, task=model.task)
                 assert suffix in str(filename), 'export failed'
             emoji = '❎'  # indicates export succeeded
@@ -196,8 +196,17 @@ class ProfileModels:
                 model.fuse()  # to report correct params and GFLOPs in model.info()
                 model_info = model.info()
                 if self.trt and self.device.type != 'cpu' and not engine_file.is_file():
-                    engine_file = model.export(format='engine', half=True, imgsz=self.imgsz, device=self.device)
-                onnx_file = model.export(format='onnx', half=True, imgsz=self.imgsz, simplify=True, device=self.device)
+                    engine_file = model.export(format='engine',
+                                               half=True,
+                                               imgsz=self.imgsz,
+                                               device=self.device,
+                                               verbose=False)
+                onnx_file = model.export(format='onnx',
+                                         half=True,
+                                         imgsz=self.imgsz,
+                                         simplify=True,
+                                         device=self.device,
+                                         verbose=False)
             elif file.suffix == '.onnx':
                 model_info = self.get_onnx_model_info(file)
                 onnx_file = file
@@ -254,7 +263,7 @@ class ProfileModels:
         for _ in range(3):
             start_time = time.time()
             for _ in range(self.num_warmup_runs):
-                model(input_data, verbose=False)
+                model(input_data, imgsz=self.imgsz, verbose=False)
             elapsed = time.time() - start_time
 
         # Compute number of runs as higher of min_time or num_timed_runs
@@ -263,7 +272,7 @@ class ProfileModels:
         # Timed runs
         run_times = []
         for _ in tqdm(range(num_runs), desc=engine_file):
-            results = model(input_data, verbose=False)
+            results = model(input_data, imgsz=self.imgsz, verbose=False)
             run_times.append(results[0].speed['inference'])  # Convert to milliseconds
 
         run_times = self.iterative_sigma_clipping(np.array(run_times), sigma=2, max_iters=3)  # sigma clipping

ultralytics/yolo/utils/callbacks/dvc.py

@@ -1,8 +1,10 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
 import os
 
+import pkg_resources as pkg
+
 from ultralytics.yolo.utils import LOGGER, TESTS_RUNNING
-from ultralytics.yolo.utils.torch_utils import get_flops, get_num_params
+from ultralytics.yolo.utils.torch_utils import model_info_for_loggers
 
 try:
     from importlib.metadata import version
@@ -10,8 +12,12 @@ try:
     import dvclive
 
     assert not TESTS_RUNNING  # do not log pytest
-    assert version('dvclive')
-except (ImportError, AssertionError):
+
+    ver = version('dvclive')
+    if pkg.parse_version(ver) < pkg.parse_version('2.11.0'):
+        LOGGER.debug(f'DVCLive is detected but version {ver} is incompatible (>=2.11 required).')
+        dvclive = None  # noqa: F811
+except (ImportError, AssertionError, TypeError):
     dvclive = None
 
 # DVCLive logger instance
@@ -36,7 +42,7 @@ def _log_images(image_path, prefix=''):
 def _log_plots(plots, prefix=''):
     for name, params in plots.items():
         timestamp = params['timestamp']
-        if _processed_plots.get(name, None) != timestamp:
+        if _processed_plots.get(name) != timestamp:
             _log_images(name, prefix)
             _processed_plots[name] = timestamp
 
@@ -94,12 +100,7 @@ def on_fit_epoch_end(trainer):
             live.log_metric(metric, value)
 
         if trainer.epoch == 0:
-            model_info = {
-                'model/parameters': get_num_params(trainer.model),
-                'model/GFLOPs': round(get_flops(trainer.model), 3),
-                'model/speed(ms)': round(trainer.validator.speed['inference'], 3)}
-
-            for metric, value in model_info.items():
+            for metric, value in model_info_for_loggers(trainer).items():
                 live.log_metric(metric, value, plot=False)
 
         _log_plots(trainer.plots, 'train')

ultralytics/yolo/utils/callbacks/neptune.py

@@ -93,7 +93,6 @@ def on_train_end(trainer):
         # Log the final model
         run[f'weights/{trainer.args.name or trainer.args.task}/{str(trainer.best.name)}'].upload(File(str(
             trainer.best)))
-        run.stop()
 
 
 callbacks = {

ultralytics/yolo/utils/checks.py

@@ -19,9 +19,9 @@ import requests
 import torch
 from matplotlib import font_manager
 
-from ultralytics.yolo.utils import (AUTOINSTALL, LOGGER, ONLINE, ROOT, USER_CONFIG_DIR, TryExcept, clean_url, colorstr,
-                                    downloads, emojis, is_colab, is_docker, is_kaggle, is_online, is_pip_package,
-                                    url2file)
+from ultralytics.yolo.utils import (AUTOINSTALL, LOGGER, ONLINE, RANK, ROOT, USER_CONFIG_DIR, TryExcept, clean_url,
+                                    colorstr, downloads, emojis, is_colab, is_docker, is_kaggle, is_online,
+                                    is_pip_package, url2file)
 
 
 def is_ascii(s) -> bool:
@@ -164,23 +164,26 @@ def check_font(font='Arial.ttf'):
     Returns:
         file (Path): Resolved font file path.
     """
-    name = Path(font).name
-
-    # Check USER_CONFIG_DIR
-    file = USER_CONFIG_DIR / name
-    if file.exists():
-        return file
-
-    # Check system fonts
-    matches = [s for s in font_manager.findSystemFonts() if font in s]
-    if any(matches):
-        return matches[0]
-
-    # Download to USER_CONFIG_DIR if missing
-    url = f'https://ultralytics.com/assets/{name}'
-    if downloads.is_url(url):
-        downloads.safe_download(url=url, file=file)
-        return file
+    from ultralytics.yolo.utils.torch_utils import torch_distributed_zero_first
+
+    with torch_distributed_zero_first(RANK):
+        name = Path(font).name
+
+        # Check USER_CONFIG_DIR
+        file = USER_CONFIG_DIR / name
+        if file.exists():
+            return file
+
+        # Check system fonts
+        matches = [s for s in font_manager.findSystemFonts() if font in s]
+        if any(matches):
+            return matches[0]
+
+        # Download to USER_CONFIG_DIR if missing
+        url = f'https://ultralytics.com/assets/{name}'
+        if downloads.is_url(url):
+            downloads.safe_download(url=url, file=file)
+            return file
 
 
 def check_python(minimum: str = '3.7.0') -> bool:

ultralytics/yolo/utils/instance.py

@@ -209,9 +209,10 @@ class Instances:
         """Convert bounding box format."""
         self._bboxes.convert(format=format)
 
+    @property
     def bbox_areas(self):
         """Calculate the area of bounding boxes."""
-        self._bboxes.areas()
+        return self._bboxes.areas()
 
     def scale(self, scale_w, scale_h, bbox_only=False):
         """this might be similar with denormalize func but without normalized sign."""
@@ -328,9 +329,9 @@ class Instances:
 
     def remove_zero_area_boxes(self):
         """Remove zero-area boxes, i.e. after clipping some boxes may have zero width or height. This removes them."""
-        good = self._bboxes.areas() > 0
+        good = self.bbox_areas > 0
         if not all(good):
-            self._bboxes = Bboxes(self._bboxes.bboxes[good], format=self._bboxes.format)
+            self._bboxes = self._bboxes[good]
             if len(self.segments):
                 self.segments = self.segments[good]
             if self.keypoints is not None:

ultralytics/yolo/utils/torch_utils.py

@@ -64,6 +64,8 @@ def select_device(device='', batch=0, newline=False, verbose=True):
     if cpu or mps:
         os.environ['CUDA_VISIBLE_DEVICES'] = '-1'  # force torch.cuda.is_available() = False
     elif device:  # non-cpu device requested
+        if device == 'cuda':
+            device = '0'
         visible = os.environ.get('CUDA_VISIBLE_DEVICES', None)
         os.environ['CUDA_VISIBLE_DEVICES'] = device  # set environment variable - must be before assert is_available()
         if not (torch.cuda.is_available() and torch.cuda.device_count() >= len(device.replace(',', ''))):

ultralytics/yolo/v8/detect/val.py

@@ -223,7 +223,7 @@ class DetectionValidator(BaseValidator):
     def plot_predictions(self, batch, preds, ni):
         """Plots predicted bounding boxes on input images and saves the result."""
         plot_images(batch['img'],
-                    *output_to_target(preds, max_det=15),
+                    *output_to_target(preds, max_det=self.args.max_det),
                     paths=batch['im_file'],
                     fname=self.save_dir / f'val_batch{ni}_pred.jpg',
                     names=self.names,

ultralytics/yolo/v8/pose/val.py

@@ -156,7 +156,7 @@ class PoseValidator(DetectionValidator):
         """Plots predictions for YOLO model."""
         pred_kpts = torch.cat([p[:, 6:].view(-1, *self.kpt_shape)[:15] for p in preds], 0)
         plot_images(batch['img'],
-                    *output_to_target(preds, max_det=15),
+                    *output_to_target(preds, max_det=self.args.max_det),
                     kpts=pred_kpts,
                     paths=batch['im_file'],
                     fname=self.save_dir / f'val_batch{ni}_pred.jpg',

ultralytics/yolo/v8/segment/val.py

@@ -179,13 +179,14 @@ class SegmentationValidator(DetectionValidator):
 
     def plot_predictions(self, batch, preds, ni):
         """Plots batch predictions with masks and bounding boxes."""
-        plot_images(batch['img'],
-                    *output_to_target(preds[0], max_det=15),
-                    torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks,
-                    paths=batch['im_file'],
-                    fname=self.save_dir / f'val_batch{ni}_pred.jpg',
-                    names=self.names,
-                    on_plot=self.on_plot)  # pred
+        plot_images(
+            batch['img'],
+            *output_to_target(preds[0], max_det=15),  # not set to self.args.max_det due to slow plotting speed
+            torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks,
+            paths=batch['im_file'],
+            fname=self.save_dir / f'val_batch{ni}_pred.jpg',
+            names=self.names,
+            on_plot=self.on_plot)  # pred
         self.plot_masks.clear()
 
     def pred_to_json(self, predn, filename, pred_masks):

{ultralytics-8.0.114.dist-info → ultralytics-8.0.116.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.0.114
+Version: 8.0.116
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Home-page: https://github.com/ultralytics/ultralytics
 Author: Ultralytics
@@ -161,9 +161,11 @@ path = model.export(format="onnx")  # export the model to ONNX format
 
 ## <div align="center">Models</div>
 
-All YOLOv8 pretrained models are available here. Detect, Segment and Pose models are pretrained on the [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/coco.yaml) dataset, while Classify models are pretrained on the [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/ImageNet.yaml) dataset.
+YOLOv8 [Detect](https://docs.ultralytics.com/tasks/detect), [Segment](https://docs.ultralytics.com/tasks/segment) and [Pose](https://docs.ultralytics.com/tasks/pose) models pretrained on the [COCO](https://docs.ultralytics.com/datasets/detect/coco) dataset are available here, as well as YOLOv8 [Classify](https://docs.ultralytics.com/modes/classify) models pretrained on the [ImageNet](https://docs.ultralytics.com/datasets/classify/imagenet) dataset. [Track](https://docs.ultralytics.com/modes/track) mode is available for all Detect, Segment and Pose models.
 
-[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use.
+<img width="1024" src="https://raw.githubusercontent.com/ultralytics/assets/tasks/im/banner-tasks.png">
+
+All [Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use.
 
 <details open><summary>Detection</summary>
 

{ultralytics-8.0.114.dist-info → ultralytics-8.0.116.dist-info}/RECORD

@@ -1,4 +1,4 @@
-ultralytics/__init__.py,sha256=-5ruX60HT01AHs6Qv3SuMvZDh8fTz0Ln4eYxVQMy0Ck,383
+ultralytics/__init__.py,sha256=kGXynKiWGuj7CVtgwKm1YG31e0E0Ppqx104S-9rSBgk,427
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/datasets/Argoverse.yaml,sha256=Q6hKRtI52JOYt4qmjkeo192mmgSkuCdOnfiUTxtBy5A,2751
@@ -59,14 +59,14 @@ ultralytics/tracker/utils/kalman_filter.py,sha256=gMc4gDKo_dkMiL-Zkt-U7mTxjK_z4A
 ultralytics/tracker/utils/matching.py,sha256=O_wJb-6ZuucIl2TuLsVe7QmqqxUNP8aoCjaWxnhk_Xg,8699
 ultralytics/vit/__init__.py,sha256=_lrglMOLuopqBVEAwGFnM8Huc6SJAHcysuGc0dmA8l0,149
 ultralytics/vit/rtdetr/__init__.py,sha256=1Zpc6ZcizFO0EMhP8X4m3DG27vDBX4aM4RX0rMSeo6E,197
-ultralytics/vit/rtdetr/model.py,sha256=1LdCA9IP6GKMA-U3L1amlwMvIQYw8vy042dbO9M8jk4,4610
+ultralytics/vit/rtdetr/model.py,sha256=CVtRbvCTQLFmG5d2CCFfVdnWrv9ClL8vaw4_BPtDrBs,5077
 ultralytics/vit/rtdetr/predict.py,sha256=zYV0c5lWr79h_J8kBhcFPB5wcDOyGdgR1qr_Z_l6Rj4,1902
 ultralytics/vit/rtdetr/val.py,sha256=6ERi9xIFOEkoEvWuy9DuOc5u1OaI2jm2Jag9l9zesvw,4790
 ultralytics/vit/sam/__init__.py,sha256=qAi91Krwqwsu2jruHiJgLabEkWo9yeZ5gDIHIKzX-PE,130
 ultralytics/vit/sam/amg.py,sha256=tzpbVPiyIwENW0xgtdy08kVGgn69zOk4VGjHmEFTCeE,13304
 ultralytics/vit/sam/autosize.py,sha256=3lym72tdiJFvbyIOMzxUzumqx82PY3lYEB3ctWNgM4s,3878
 ultralytics/vit/sam/build.py,sha256=Cp0LhlNcjLl-2OA_06eaeYlA3lK3N0KqUfhmZJ7A8Hw,3781
-ultralytics/vit/sam/model.py,sha256=ynJtuLhvhva4-69o2TDtTk7viIuOpJpVGr-u-Rf5D6E,1807
+ultralytics/vit/sam/model.py,sha256=kS-zpGw8wXKkU0yWCH-uGvmMFWB_AnEAa6NMVdsUDEA,2274
 ultralytics/vit/sam/predict.py,sha256=RcC3uLs3RiqWeW7UxdyjK6LcmqysFqRRfz3f-pV_mPQ,2139
 ultralytics/vit/sam/modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ultralytics/vit/sam/modules/decoders.py,sha256=MJhFLPA7broz2oiYI5tUi3ROWgPxNshhKFXKUP4CEPc,6351
@@ -86,43 +86,47 @@ ultralytics/yolo/data/build.py,sha256=9eVmHXp79QpTLVB-sbaZSM6Qaet9YbiiiTW4TviAGE
 ultralytics/yolo/data/converter.py,sha256=D-O9eOcO1qg7ultRv2xLAQR39JjVIUkR--g05zquQDA,9190
 ultralytics/yolo/data/dataset.py,sha256=jmbIpgMaWhQtLfWC4hP8LBaBG2wpFGpxXDg0478FF58,13372
 ultralytics/yolo/data/dataset_wrappers.py,sha256=a5uwWLhWDRCG5VFto6I3zknxaElxnrcOHiuTAKmmmYg,1776
-ultralytics/yolo/data/utils.py,sha256=aBAp1jBzLOPwxGrelDqCi0J2kl3T1CuzpzwRJlzAviU,24050
+ultralytics/yolo/data/utils.py,sha256=nqo_SJNnlBANLEOzvmJGFxz_Ai0OvAQe-CEmMCgDUBo,24056
 ultralytics/yolo/data/dataloaders/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ultralytics/yolo/data/dataloaders/stream_loaders.py,sha256=0bg7lPloNLml7zO9Qe-fz4Cw7VbbSZjrEUbBe-lfpzc,14905
 ultralytics/yolo/data/dataloaders/v5augmentations.py,sha256=t39RSuHCDCX4MV9EkIoJWaPOjkYlNbbpi-30fg725rw,17646
 ultralytics/yolo/data/dataloaders/v5loader.py,sha256=RoBWZljfI7Zme_gqF6nq6-2WkMOF7MuL-YCYUpk0bAU,51260
 ultralytics/yolo/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ultralytics/yolo/engine/exporter.py,sha256=Cq54zAtkL7Qs7Z4RPoDqi0BNG8-sm43sVpeFWm0R_0E,40922
-ultralytics/yolo/engine/model.py,sha256=e0wfnPLq6pdlrOSZ-WS0nrD5r62hgiojI3IIvSGnqSc,22061
+ultralytics/yolo/engine/model.py,sha256=OLzx4v7nijKDUcRrt4iQhkZgSw766LmVG2TUHyWT8jE,22144
 ultralytics/yolo/engine/predictor.py,sha256=j1F6f6AHs-LNBta4IG45VyLXEs78UaYpjoIE5rco8EM,16204
 ultralytics/yolo/engine/results.py,sha256=KNiXW_xkSN8qJJl7gqQKCz_6zjU0nyBHKqD3yoIf-2E,24287
 ultralytics/yolo/engine/trainer.py,sha256=Xie6mlF-jCESk-3tMLMf1nY8bI8_-9Owgg2EAQPfMLI,31199
 ultralytics/yolo/engine/validator.py,sha256=ZbOde8CClZQgTFXJ68v4DP_etR1prJYrwMayyKUcfTk,11715
-ultralytics/yolo/utils/__init__.py,sha256=8XWq2-gOpwnmm5PMkXjlfZVZu1pJLOemyQGS0_VGUdY,27849
+ultralytics/yolo/nas/__init__.py,sha256=O7qvgqJqoLB1NXwjTNHMJHJRhDwNHS2P_oyUV_b1qq8,179
+ultralytics/yolo/nas/model.py,sha256=LU0NaoZjcJEDvKQetavJ7YmVzn-kGO-IJDDw8vKz-S4,4977
+ultralytics/yolo/nas/predict.py,sha256=WbO9fxO2o_WA3nM7KkgHDgr2eJWdYsT725BcJ6_Qtrs,1465
+ultralytics/yolo/nas/val.py,sha256=D9jIFcafuD768X5l9Q56hrXIz-Jl45uEReIsPyrlNgs,953
+ultralytics/yolo/utils/__init__.py,sha256=OJ0x67npaXsLYD5TzKmlMZ-n74Jq0hG43fHglT8SMkE,27955
 ultralytics/yolo/utils/autobatch.py,sha256=-8eEMRN9KyX9nslL5XAC2gMTFAH5YFA33q6nnQDj1qU,3846
-ultralytics/yolo/utils/benchmarks.py,sha256=M2bC3dVTDyBpWMVz4FMTAI9iREp2bvTZBHc7Jre3-3U,15428
-ultralytics/yolo/utils/checks.py,sha256=dgD4pO_epK8eUN9LQB_n5cPYDY2azxh3Gj2cWzF10GI,17380
+ultralytics/yolo/utils/benchmarks.py,sha256=lFdnVqrXlI2n8JC-B1UgW2zip-Tsii7HjrJrCQmDV-g,15888
+ultralytics/yolo/utils/checks.py,sha256=3kLYaCCuZpGNKaX9RYDEHfiPgKD-Sc3Ep5kmR-LBQFI,17568
 ultralytics/yolo/utils/dist.py,sha256=qavAVcOeyLV0z31Spo1G9batXljnYzp1NN8YWFoBTxk,2596
 ultralytics/yolo/utils/downloads.py,sha256=w_Pnw_0_s6rNno54J1-qIm8Zy_I0jr7B9fSdD-TwX8g,12114
 ultralytics/yolo/utils/errors.py,sha256=u8NUGZbWVrr4O3ez6UXnabNb_zRwJUPJqDOUSpmX3-k,317
 ultralytics/yolo/utils/files.py,sha256=7431UxyB9-D2vhkp8JqO_IXApYoWsWfSH3H5JNemKjU,3588
-ultralytics/yolo/utils/instance.py,sha256=Eul_ZaDyCCUzllLype5hlfO0r9vuerl8rI5OGRbnne4,14661
+ultralytics/yolo/utils/instance.py,sha256=7pVtdcSR4tfPffhFXaNtZiW2lOYMawtVdSoqz8XU5LQ,14634
 ultralytics/yolo/utils/loss.py,sha256=iP1YPMRGsHYjIr7jGFdHxhMAgX7ou9V0HE4o7foRVrk,18090
 ultralytics/yolo/utils/metrics.py,sha256=mPTMcW4vyfzmh8gvdcStuHkMd3AADML3m_crLaal1I4,43799
 ultralytics/yolo/utils/ops.py,sha256=ne7GC7hOuAS3Lnk7eDx5w8LOMtbb_l7nJcb0wpBVJRQ,28273
 ultralytics/yolo/utils/patches.py,sha256=lxG_qZlTxiCcKWrVFtvSVA8WULRa483fOJ4ffYyGQ50,1241
 ultralytics/yolo/utils/plotting.py,sha256=ScX-_AasukwuQpOT8q18YMSKMwJBDKFM8q1o8oY8MqE,24431
 ultralytics/yolo/utils/tal.py,sha256=BFovrLm0m5_Pv-hFzYMAD3oonS1MvDqdy51f_Cx6Aq8,13645
-ultralytics/yolo/utils/torch_utils.py,sha256=S2emgg-VTZZ0pV2YE6VMxaUgaVpA7HVdO_U2RLtvJos,22177
+ultralytics/yolo/utils/torch_utils.py,sha256=mpAdku7PNYFLOFcijSWA3poZ6ShIShOlEHlqvBDzJp4,22231
 ultralytics/yolo/utils/tuner.py,sha256=yq3nYsnug2LC-iJJwLlXrQwJJT2VanujFFKnY-06CBQ,2300
 ultralytics/yolo/utils/callbacks/__init__.py,sha256=nhrnMPpPDb5fgqw42w8e7fC5TjEPC-jp04dpQtaQtkU,214
 ultralytics/yolo/utils/callbacks/base.py,sha256=VpiMIW9qiyncMq9cLRmm5WGr38On0LVTK2XNDmliEbE,5593
 ultralytics/yolo/utils/callbacks/clearml.py,sha256=VYtuNTlB8M5rIFQupm53uhDEXe8qZrrOjXXHTI0bIUw,5902
 ultralytics/yolo/utils/callbacks/comet.py,sha256=_Dm-Qbeyi36nSSETsoiObG52gceLw6RE2TodEYW7sUY,12978
-ultralytics/yolo/utils/callbacks/dvc.py,sha256=JUjAIQ0SJvAPSbiKwnDiaG7IEEqCy-Nvbtvm0Q-kCWo,4299
+ultralytics/yolo/utils/callbacks/dvc.py,sha256=7xNhDoTQqapOULEVrwxluZGOdKZVK74EPLFu4Rm47Tw,4301
 ultralytics/yolo/utils/callbacks/hub.py,sha256=Z-F48IcG2PtlJo3mnzp31YdXrS8nyMn6004-Ke6NLyM,3310
 ultralytics/yolo/utils/callbacks/mlflow.py,sha256=fCp4zNefamIzqZpOkoG2UqKVkeuIX41_em2Uw33iasY,2493
-ultralytics/yolo/utils/callbacks/neptune.py,sha256=FO-E5v7udasGkOg8Mg-cNVRKJkZW-1WLfqP_nP4UYvY,3698
+ultralytics/yolo/utils/callbacks/neptune.py,sha256=lBvXuXkgHfiDkdeRAM7TbK7xQBSAKxYQQAwHt7SMNi8,3679
 ultralytics/yolo/utils/callbacks/raytune.py,sha256=wHdhqCDtK1GbDQTixpxJPzS8NWtEkXpkdIlhQmEZdHg,495
 ultralytics/yolo/utils/callbacks/tensorboard.py,sha256=05UPBY4sBzh2FaQmWgav0sFgoLlhLqJg-5gfSz7AYpY,1525
 ultralytics/yolo/utils/callbacks/wb.py,sha256=LfDZhxZyWigN20LWWuG9NEStp55HwBHY7VpXYyb1sm4,2170
@@ -134,18 +138,18 @@ ultralytics/yolo/v8/classify/val.py,sha256=b8VJuuAUDbOwTmg5IEcn_NqTFJ5BCubc9FGdY
 ultralytics/yolo/v8/detect/__init__.py,sha256=1w44OZNPKQOlDIbxRqFDULl7RphH8KAT6cJawNY2uKU,277
 ultralytics/yolo/v8/detect/predict.py,sha256=BbsRQpswiBvF88uWuOfwNguRbyXIJO7HZ7WYBblcCvY,1854
 ultralytics/yolo/v8/detect/train.py,sha256=uorDhWqt1GMjUnc3m4xamnEDROHGWcty3cJFUANbpok,7199
-ultralytics/yolo/v8/detect/val.py,sha256=5_tUnvLJeP75M-ofzZfsuYzoCiIQBi4Ta8GEwQXNr4s,14715
+ultralytics/yolo/v8/detect/val.py,sha256=uZGSs7Vgq8UGEgz-oMsVSYarfKz_czW0AS1S1FJvdns,14730
 ultralytics/yolo/v8/pose/__init__.py,sha256=V9epZgW3BaNv6zouhdeX_MMwWqmzPl6V8F8uBIfsfEE,247
 ultralytics/yolo/v8/pose/predict.py,sha256=0XTJWgxYZMzNyKHgswQFMSnzHYcfJbbrIQ7eysyCPtI,2375
 ultralytics/yolo/v8/pose/train.py,sha256=lfim51E8qvUmcuxa-fGVw8nPOr6Z6Nisv5AXLm6qVz8,2790
-ultralytics/yolo/v8/pose/val.py,sha256=C7YUht88_OB1fzO7GsQkkSjRem0oEL4IFeaq8uI2Ww0,10917
+ultralytics/yolo/v8/pose/val.py,sha256=v_pyWKhIZWowNzt4ACzdtyJJaRHXMT7rpzhODXVGtlQ,10932
 ultralytics/yolo/v8/segment/__init__.py,sha256=TOdf3ju-D5hSi-PYMpETFmv-wyhIRKGujdoeGDx7hbs,295
 ultralytics/yolo/v8/segment/predict.py,sha256=QSwXjC7sq7l7kT0W1UrwGZrUXNqkveRGRIsRnlQlWYM,2839
 ultralytics/yolo/v8/segment/train.py,sha256=Ag0uHlJp297dljtECqZ5VVfnWj7m86oD1Dy1_s4vIEs,2499
-ultralytics/yolo/v8/segment/val.py,sha256=P73flBisvAHh5SRYXes1DzrHGxsOzN2OELV4V1veP8M,12882
-ultralytics-8.0.114.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.0.114.dist-info/METADATA,sha256=lzNVo3huNDUQIJiTPTSgpT5FLD5MN9cb3NTCHh0BF9Q,26843
-ultralytics-8.0.114.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
-ultralytics-8.0.114.dist-info/entry_points.txt,sha256=Ck1F6qKNokeHozQD5pmaFgXHL6dKyC2qCdyXao2e6Yg,103
-ultralytics-8.0.114.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.0.114.dist-info/RECORD,,
+ultralytics/yolo/v8/segment/val.py,sha256=R3D_itui1lU0iXC1aqmZvmwGX77oJt--bQ7MhTErsBY,12906
+ultralytics-8.0.116.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.0.116.dist-info/METADATA,sha256=fhzEqGcUjDMa-o-bqGrtVJHMhLse8F6-KqsHmd5r9Ug,27157
+ultralytics-8.0.116.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
+ultralytics-8.0.116.dist-info/entry_points.txt,sha256=Ck1F6qKNokeHozQD5pmaFgXHL6dKyC2qCdyXao2e6Yg,103
+ultralytics-8.0.116.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.0.116.dist-info/RECORD,,