ultralytics 8.2.27__py3-none-any.whl → 8.2.29__py3-none-any.whl

tests/test_python.py

@@ -140,7 +140,8 @@ def test_youtube():
     model = YOLO(MODEL)
     try:
         model.predict("https://youtu.be/G17sBkb38XQ", imgsz=96, save=True)
-    except urllib.error.HTTPError as e:  # handle 'urllib.error.HTTPError: HTTP Error 429: Too Many Requests'
+    # Handle internet connection errors and 'urllib.error.HTTPError: HTTP Error 429: Too Many Requests'
+    except (urllib.error.HTTPError, ConnectionError) as e:
         LOGGER.warning(f"WARNING: YouTube Test Error: {e}")
 
 

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.27"
+__version__ = "8.2.29"
 
 import os
 

ultralytics/cfg/__init__.py

@@ -95,10 +95,19 @@ CLI_HELP_MSG = f"""
     """
 
 # Define keys for arg type checks
-CFG_FLOAT_KEYS = {"warmup_epochs", "box", "cls", "dfl", "degrees", "shear", "time", "workspace"}
-CFG_FRACTION_KEYS = {
+CFG_FLOAT_KEYS = {  # integer or float arguments, i.e. x=2 and x=2.0
+    "warmup_epochs",
+    "box",
+    "cls",
+    "dfl",
+    "degrees",
+    "shear",
+    "time",
+    "workspace",
+    "batch",
+}
+CFG_FRACTION_KEYS = {  # fractional float arguments with 0.0<=values<=1.0
     "dropout",
-    "iou",
     "lr0",
     "lrf",
     "momentum",
@@ -121,11 +130,10 @@ CFG_FRACTION_KEYS = {
     "conf",
     "iou",
     "fraction",
-}  # fraction floats 0.0 - 1.0
-CFG_INT_KEYS = {
+}
+CFG_INT_KEYS = {  # integer-only arguments
     "epochs",
     "patience",
-    "batch",
     "workers",
     "seed",
     "close_mosaic",
@@ -136,7 +144,7 @@ CFG_INT_KEYS = {
     "nbs",
     "save_period",
 }
-CFG_BOOL_KEYS = {
+CFG_BOOL_KEYS = {  # boolean-only arguments
     "save",
     "exist_ok",
     "verbose",

ultralytics/engine/exporter.py

@@ -126,7 +126,7 @@ def gd_outputs(gd):
 
 
 def try_export(inner_func):
-    """YOLOv8 export decorator, i..e @try_export."""
+    """YOLOv8 export decorator, i.e. @try_export."""
     inner_args = get_default_args(inner_func)
 
     def outer_func(*args, **kwargs):
@@ -211,6 +211,9 @@ class Exporter:
             assert self.device.type == "cpu", "optimize=True not compatible with cuda devices, i.e. use device='cpu'"
         if edgetpu and not LINUX:
             raise SystemError("Edge TPU export only supported on Linux. See https://coral.ai/docs/edgetpu/compiler/")
+        elif edgetpu and self.args.batch != 1:  # see github.com/ultralytics/ultralytics/pull/13420
+            LOGGER.warning("WARNING ⚠️ Edge TPU export requires batch size 1, setting batch=1.")
+            self.args.batch = 1
         if isinstance(model, WorldModel):
             LOGGER.warning(
                 "WARNING ⚠️ YOLOWorld (original version) export is not supported to any format.\n"

ultralytics/engine/trainer.py

@@ -178,9 +178,9 @@ class BaseTrainer:
             if self.args.rect:
                 LOGGER.warning("WARNING ⚠️ 'rect=True' is incompatible with Multi-GPU training, setting 'rect=False'")
                 self.args.rect = False
-            if self.args.batch == -1:
+            if self.args.batch < 1.0:
                 LOGGER.warning(
-                    "WARNING ⚠️ 'batch=-1' for AutoBatch is incompatible with Multi-GPU training, setting "
+                    "WARNING ⚠️ 'batch<1' for AutoBatch is incompatible with Multi-GPU training, setting "
                     "default 'batch=16'"
                 )
                 self.args.batch = 16
@@ -269,8 +269,13 @@ class BaseTrainer:
         self.stride = gs  # for multiscale training
 
         # Batch size
-        if self.batch_size == -1 and RANK == -1:  # single-GPU only, estimate best batch size
-            self.args.batch = self.batch_size = check_train_batch_size(self.model, self.args.imgsz, self.amp)
+        if self.batch_size < 1 and RANK == -1:  # single-GPU only, estimate best batch size
+            self.args.batch = self.batch_size = check_train_batch_size(
+                model=self.model,
+                imgsz=self.args.imgsz,
+                amp=self.amp,
+                batch=self.batch_size,
+            )
 
         # Dataloaders
         batch_size = self.batch_size // max(world_size, 1)

ultralytics/models/yolo/model.py

@@ -92,7 +92,7 @@ class YOLOWorld(Model):
         Set classes.
 
         Args:
-            classes (List(str)): A list of categories i.e ["person"].
+            classes (List(str)): A list of categories i.e. ["person"].
         """
         self.model.set_classes(classes)
         # Remove background if it's given

ultralytics/models/yolo/world/train_world.py

@@ -1,3 +1,5 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
 from ultralytics.data import YOLOConcatDataset, build_grounding, build_yolo_dataset
 from ultralytics.data.utils import check_det_dataset
 from ultralytics.models.yolo.world import WorldTrainer

ultralytics/nn/autobackend.py

@@ -184,7 +184,7 @@ class AutoBackend(nn.Module):
             LOGGER.info(f"Loading {w} for ONNX Runtime inference...")
             check_requirements(("onnx", "onnxruntime-gpu" if cuda else "onnxruntime"))
             if IS_RASPBERRYPI or IS_JETSON:
-                # Fix error: module 'numpy.linalg._umath_linalg' has no attribute '_ilp64' when exporting to Tensorflow SavedModel on RPi and Jetson
+                # Fix 'numpy.linalg._umath_linalg' has no attribute '_ilp64' for TF SavedModel on RPi and Jetson
                 check_requirements("numpy==1.23.5")
             import onnxruntime
 
@@ -320,6 +320,10 @@ class AutoBackend(nn.Module):
             with open(w, "rb") as f:
                 gd.ParseFromString(f.read())
             frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs=gd_outputs(gd))
+            try:  # attempt to retrieve metadata from SavedModel file potentially alongside GraphDef file
+                metadata = next(Path(w).resolve().parent.rglob(f"{Path(w).stem}_saved_model*/metadata.yaml"))
+            except StopIteration:
+                pass  # no metadata file found
 
         # TFLite or TFLite Edge TPU
         elif tflite or edgetpu:  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
@@ -402,7 +406,7 @@ class AutoBackend(nn.Module):
         # Load external metadata YAML
         if isinstance(metadata, (str, Path)) and Path(metadata).exists():
             metadata = yaml_load(metadata)
-        if metadata:
+        if metadata and isinstance(metadata, dict):
             for k, v in metadata.items():
                 if k in {"stride", "batch"}:
                     metadata[k] = int(v)
@@ -563,7 +567,7 @@ class AutoBackend(nn.Module):
                     y = [y]
             elif self.pb:  # GraphDef
                 y = self.frozen_func(x=self.tf.constant(im))
-                if len(y) == 2 and len(self.names) == 999:  # segments and names not defined
+                if (self.task == "segment" or len(y) == 2) and len(self.names) == 999:  # segments and names not defined
                     ip, ib = (0, 1) if len(y[0].shape) == 4 else (1, 0)  # index of protos, boxes
                     nc = y[ib].shape[1] - y[ip].shape[3] - 4  # y = (1, 160, 160, 32), (1, 116, 8400)
                     self.names = {i: f"class{i}" for i in range(nc)}
@@ -620,6 +624,8 @@ class AutoBackend(nn.Module):
         Args:
             imgsz (tuple): The shape of the dummy input tensor in the format (batch_size, channels, height, width)
         """
+        import torchvision  # noqa (import here so torchvision import time not recorded in postprocess time)
+
         warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb, self.triton, self.nn_module
         if any(warmup_types) and (self.device.type != "cpu" or self.triton):
             im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input

ultralytics/nn/tasks.py

@@ -157,7 +157,7 @@ class BaseModel(nn.Module):
             None
         """
         c = m == self.model[-1] and isinstance(x, list)  # is final layer list, copy input as inplace fix
-        flops = thop.profile(m, inputs=[x.copy() if c else x], verbose=False)[0] / 1e9 * 2 if thop else 0  # FLOPs
+        flops = thop.profile(m, inputs=[x.copy() if c else x], verbose=False)[0] / 1e9 * 2 if thop else 0  # GFLOPs
         t = time_sync()
         for _ in range(10):
             m(x.copy() if c else x)

ultralytics/solutions/analytics.py

@@ -11,7 +11,7 @@ from matplotlib.figure import Figure
 
 
 class Analytics:
-    """A class to create and update various types of charts (line, bar, pie) for visual analytics."""
+    """A class to create and update various types of charts (line, bar, pie, area) for visual analytics."""
 
     def __init__(
         self,
@@ -25,6 +25,7 @@ class Analytics:
         fg_color="black",
         line_color="yellow",
         line_width=2,
+        points_width=10,
         fontsize=13,
         view_img=False,
         save_img=True,
@@ -34,7 +35,7 @@ class Analytics:
         Initialize the Analytics class with various chart types.
 
         Args:
-            type (str): Type of chart to initialize ('line', 'bar', or 'pie').
+            type (str): Type of chart to initialize ('line', 'bar', 'pie', or 'area').
             writer (object): Video writer object to save the frames.
             im0_shape (tuple): Shape of the input image (width, height).
             title (str): Title of the chart.
@@ -44,6 +45,7 @@ class Analytics:
             fg_color (str): Foreground (text) color of the chart.
             line_color (str): Line color for line charts.
             line_width (int): Width of the lines in line charts.
+            points_width (int): Width of line points highlighter
             fontsize (int): Font size for chart text.
             view_img (bool): Whether to display the image.
             save_img (bool): Whether to save the image.
@@ -57,17 +59,24 @@ class Analytics:
         self.title = title
         self.writer = writer
         self.max_points = max_points
+        self.line_color = line_color
+        self.x_label = x_label
+        self.y_label = y_label
+        self.points_width = points_width
+        self.line_width = line_width
+        self.fontsize = fontsize
 
         # Set figure size based on image shape
         figsize = (im0_shape[0] / 100, im0_shape[1] / 100)
 
-        if type == "line":
-            # Initialize line plot
+        if type in {"line", "area"}:
+            # Initialize line or area plot
             self.lines = {}
-            fig = Figure(facecolor=self.bg_color, figsize=figsize)
-            self.canvas = FigureCanvas(fig)
-            self.ax = fig.add_subplot(111, facecolor=self.bg_color)
-            (self.line,) = self.ax.plot([], [], color=line_color, linewidth=line_width)
+            self.fig = Figure(facecolor=self.bg_color, figsize=figsize)
+            self.canvas = FigureCanvas(self.fig)
+            self.ax = self.fig.add_subplot(111, facecolor=self.bg_color)
+            if type == "line":
+                (self.line,) = self.ax.plot([], [], color=self.line_color, linewidth=self.line_width)
 
         elif type in {"bar", "pie"}:
             # Initialize bar or pie plot
@@ -93,11 +102,73 @@ class Analytics:
             self.ax.axis("equal") if type == "pie" else None
 
         # Set common axis properties
-        self.ax.set_title(self.title, color=self.fg_color, fontsize=fontsize)
-        self.ax.set_xlabel(x_label, color=self.fg_color, fontsize=fontsize - 3)
-        self.ax.set_ylabel(y_label, color=self.fg_color, fontsize=fontsize - 3)
+        self.ax.set_title(self.title, color=self.fg_color, fontsize=self.fontsize)
+        self.ax.set_xlabel(x_label, color=self.fg_color, fontsize=self.fontsize - 3)
+        self.ax.set_ylabel(y_label, color=self.fg_color, fontsize=self.fontsize - 3)
         self.ax.tick_params(axis="both", colors=self.fg_color)
 
+    def update_area(self, frame_number, counts_dict):
+        """
+        Update the area graph with new data for multiple classes.
+
+        Args:
+            frame_number (int): The current frame number.
+            counts_dict (dict): Dictionary with class names as keys and counts as values.
+        """
+
+        x_data = np.array([])
+        y_data_dict = {key: np.array([]) for key in counts_dict.keys()}
+
+        if self.ax.lines:
+            x_data = self.ax.lines[0].get_xdata()
+            for line, key in zip(self.ax.lines, counts_dict.keys()):
+                y_data_dict[key] = line.get_ydata()
+
+        x_data = np.append(x_data, float(frame_number))
+        max_length = len(x_data)
+
+        for key in counts_dict.keys():
+            y_data_dict[key] = np.append(y_data_dict[key], float(counts_dict[key]))
+            if len(y_data_dict[key]) < max_length:
+                y_data_dict[key] = np.pad(y_data_dict[key], (0, max_length - len(y_data_dict[key])), "constant")
+
+        # Remove the oldest points if the number of points exceeds max_points
+        if len(x_data) > self.max_points:
+            x_data = x_data[1:]
+            for key in counts_dict.keys():
+                y_data_dict[key] = y_data_dict[key][1:]
+
+        self.ax.clear()
+
+        colors = ["#E1FF25", "#0BDBEB", "#FF64DA", "#111F68", "#042AFF"]
+        color_cycle = cycle(colors)
+
+        for key, y_data in y_data_dict.items():
+            color = next(color_cycle)
+            self.ax.fill_between(x_data, y_data, color=color, alpha=0.6)
+            self.ax.plot(
+                x_data,
+                y_data,
+                color=color,
+                linewidth=self.line_width,
+                marker="o",
+                markersize=self.points_width,
+                label=f"{key} Data Points",
+            )
+
+        self.ax.set_title(self.title, color=self.fg_color, fontsize=self.fontsize)
+        self.ax.set_xlabel(self.x_label, color=self.fg_color, fontsize=self.fontsize - 3)
+        self.ax.set_ylabel(self.y_label, color=self.fg_color, fontsize=self.fontsize - 3)
+        legend = self.ax.legend(loc="upper left", fontsize=13, facecolor=self.bg_color, edgecolor=self.fg_color)
+
+        # Set legend text color
+        for text in legend.get_texts():
+            text.set_color(self.fg_color)
+
+        self.canvas.draw()
+        im0 = np.array(self.canvas.renderer.buffer_rgba())
+        self.write_and_display(im0)
+
     def update_line(self, frame_number, total_counts):
         """
         Update the line graph with new data.
@@ -117,7 +188,7 @@ class Analytics:
         self.ax.autoscale_view()
         self.canvas.draw()
         im0 = np.array(self.canvas.renderer.buffer_rgba())
-        self.write_and_display_line(im0)
+        self.write_and_display(im0)
 
     def update_multiple_lines(self, counts_dict, labels_list, frame_number):
         """
@@ -131,7 +202,7 @@ class Analytics:
         warnings.warn("Display is not supported for multiple lines, output will be stored normally!")
         for obj in labels_list:
             if obj not in self.lines:
-                (line,) = self.ax.plot([], [], label=obj, marker="o", markersize=15)
+                (line,) = self.ax.plot([], [], label=obj, marker="o", markersize=self.points_width)
                 self.lines[obj] = line
 
             x_data = self.lines[obj].get_xdata()
@@ -153,16 +224,14 @@ class Analytics:
 
         im0 = np.array(self.canvas.renderer.buffer_rgba())
         self.view_img = False  # for multiple line view_img not supported yet, coming soon!
-        self.write_and_display_line(im0)
+        self.write_and_display(im0)
 
-    def write_and_display_line(self, im0):
+    def write_and_display(self, im0):
         """
         Write and display the line graph
         Args:
             im0 (ndarray): Image for processing
         """
-
-        # convert image to BGR format
         im0 = cv2.cvtColor(im0[:, :, :3], cv2.COLOR_RGBA2BGR)
         cv2.imshow(self.title, im0) if self.view_img else None
         self.writer.write(im0) if self.save_img else None
@@ -204,10 +273,7 @@ class Analytics:
         canvas.draw()
         buf = canvas.buffer_rgba()
         im0 = np.asarray(buf)
-        im0 = cv2.cvtColor(im0, cv2.COLOR_RGBA2BGR)
-
-        self.writer.write(im0) if self.save_img else None
-        cv2.imshow(self.title, im0) if self.view_img else None
+        self.write_and_display(im0)
 
     def update_pie(self, classes_dict):
         """
@@ -239,9 +305,7 @@ class Analytics:
         # Display and save the updated chart
         im0 = self.fig.canvas.draw()
         im0 = np.array(self.fig.canvas.renderer.buffer_rgba())
-        im0 = cv2.cvtColor(im0[:, :, :3], cv2.COLOR_RGBA2BGR)
-        self.writer.write(im0) if self.save_img else None
-        cv2.imshow(self.title, im0) if self.view_img else None
+        self.write_and_display(im0)
 
 
 if __name__ == "__main__":

ultralytics/utils/autobatch.py

@@ -10,9 +10,9 @@ from ultralytics.utils import DEFAULT_CFG, LOGGER, colorstr
 from ultralytics.utils.torch_utils import profile
 
 
-def check_train_batch_size(model, imgsz=640, amp=True):
+def check_train_batch_size(model, imgsz=640, amp=True, batch=-1):
     """
-    Check YOLO training batch size using the autobatch() function.
+    Compute optimal YOLO training batch size using the autobatch() function.
 
     Args:
         model (torch.nn.Module): YOLO model to check batch size for.
@@ -24,7 +24,7 @@ def check_train_batch_size(model, imgsz=640, amp=True):
     """
 
     with torch.cuda.amp.autocast(amp):
-        return autobatch(deepcopy(model).train(), imgsz)  # compute optimal batch size
+        return autobatch(deepcopy(model).train(), imgsz, fraction=batch if 0.0 < batch < 1.0 else 0.6)
 
 
 def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch):
@@ -43,7 +43,7 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch):
 
     # Check device
     prefix = colorstr("AutoBatch: ")
-    LOGGER.info(f"{prefix}Computing optimal batch size for imgsz={imgsz}")
+    LOGGER.info(f"{prefix}Computing optimal batch size for imgsz={imgsz} at {fraction * 100}% CUDA memory utilization.")
     device = next(model.parameters()).device  # get model device
     if device.type == "cpu":
         LOGGER.info(f"{prefix}CUDA not detected, using default CPU batch-size {batch_size}")

ultralytics/utils/callbacks/tensorboard.py

@@ -1,4 +1,5 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
+
 import contextlib
 
 from ultralytics.utils import LOGGER, SETTINGS, TESTS_RUNNING, colorstr

ultralytics/utils/ops.py

@@ -215,7 +215,7 @@ def non_max_suppression(
 
     bs = prediction.shape[0]  # batch size
     nc = nc or (prediction.shape[1] - 4)  # number of classes
-    nm = prediction.shape[1] - nc - 4
+    nm = prediction.shape[1] - nc - 4  # number of masks
     mi = 4 + nc  # mask start index
     xc = prediction[:, 4:mi].amax(1) > conf_thres  # candidates
 
@@ -402,7 +402,7 @@ def xyxy2xywh(x):
 def xywh2xyxy(x):
     """
     Convert bounding box coordinates from (x, y, width, height) format to (x1, y1, x2, y2) format where (x1, y1) is the
-    top-left corner and (x2, y2) is the bottom-right corner.
+    top-left corner and (x2, y2) is the bottom-right corner. Note: ops per 2 channels faster than per channel.
 
     Args:
         x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x, y, width, height) format.
@@ -412,12 +412,10 @@ def xywh2xyxy(x):
     """
     assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}"
     y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x)  # faster than clone/copy
-    dw = x[..., 2] / 2  # half-width
-    dh = x[..., 3] / 2  # half-height
-    y[..., 0] = x[..., 0] - dw  # top left x
-    y[..., 1] = x[..., 1] - dh  # top left y
-    y[..., 2] = x[..., 0] + dw  # bottom right x
-    y[..., 3] = x[..., 1] + dh  # bottom right y
+    xy = x[..., :2]  # centers
+    wh = x[..., 2:] / 2  # half width-height
+    y[..., :2] = xy - wh  # top left xy
+    y[..., 2:] = xy + wh  # bottom right xy
     return y
 
 

ultralytics/utils/torch_utils.py

@@ -146,11 +146,17 @@ def select_device(device="", batch=0, newline=False, verbose=True):
     if not cpu and not mps and torch.cuda.is_available():  # prefer GPU if available
         devices = device.split(",") if device else "0"  # range(torch.cuda.device_count())  # i.e. 0,1,6,7
         n = len(devices)  # device count
-        if n > 1 and batch > 0 and batch % n != 0:  # check batch_size is divisible by device_count
-            raise ValueError(
-                f"'batch={batch}' must be a multiple of GPU count {n}. Try 'batch={batch // n * n}' or "
-                f"'batch={batch // n * n + n}', the nearest batch sizes evenly divisible by {n}."
-            )
+        if n > 1:  # multi-GPU
+            if batch < 1:
+                raise ValueError(
+                    "AutoBatch with batch<1 not supported for Multi-GPU training, "
+                    "please specify a valid batch size, i.e. batch=16."
+                )
+            if batch >= 0 and batch % n != 0:  # check batch_size is divisible by device_count
+                raise ValueError(
+                    f"'batch={batch}' must be a multiple of GPU count {n}. Try 'batch={batch // n * n}' or "
+                    f"'batch={batch // n * n + n}', the nearest batch sizes evenly divisible by {n}."
+                )
         space = " " * (len(s) + 1)
         for i, d in enumerate(devices):
             p = torch.cuda.get_device_properties(i)

{ultralytics-8.2.27.dist-info → ultralytics-8.2.29.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.27
+Version: 8.2.29
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu
@@ -41,9 +41,9 @@ Requires-Dist: torchvision >=0.9.0
 Requires-Dist: tqdm >=4.64.0
 Requires-Dist: psutil
 Requires-Dist: py-cpuinfo
-Requires-Dist: thop >=0.1.1
 Requires-Dist: pandas >=1.1.4
 Requires-Dist: seaborn >=0.11.0
+Requires-Dist: ultralytics-thop >=0.2.5
 Provides-Extra: dev
 Requires-Dist: ipython ; extra == 'dev'
 Requires-Dist: check-manifest ; extra == 'dev'
@@ -56,7 +56,7 @@ Requires-Dist: mkdocs-material >=9.5.9 ; extra == 'dev'
 Requires-Dist: mkdocstrings[python] ; extra == 'dev'
 Requires-Dist: mkdocs-jupyter ; extra == 'dev'
 Requires-Dist: mkdocs-redirects ; extra == 'dev'
-Requires-Dist: mkdocs-ultralytics-plugin >=0.0.44 ; extra == 'dev'
+Requires-Dist: mkdocs-ultralytics-plugin >=0.0.45 ; extra == 'dev'
 Provides-Extra: explorer
 Requires-Dist: lancedb ; extra == 'explorer'
 Requires-Dist: duckdb <=0.9.2 ; extra == 'explorer'

{ultralytics-8.2.27.dist-info → ultralytics-8.2.29.dist-info}/RECORD

@@ -6,11 +6,11 @@ tests/test_engine.py,sha256=fFzcbqZuMkzZHjA5FMddWcqVE703iq8HB_a0Q2lcBKM,4705
 tests/test_explorer.py,sha256=r1pWer2y290Y0DqsM-La7egfEY0497YCdC4rwq3URV4,2178
 tests/test_exports.py,sha256=qc4YOgsGixqYLO6IRNY16-v6z14R0dp5fdni1v222xw,8034
 tests/test_integrations.py,sha256=8Ru7GyKV8j44EEc8X9_E7q7aR4CTOIMPuSagXjSGUxw,5847
-tests/test_python.py,sha256=3qV963KPGGnYwSiEG5YcDf6g_ozo3NtQEjDDtH32rV4,20212
-ultralytics/__init__.py,sha256=9lgJTJTMVbv_Y67eEbEFa_KC-wW_1I99noo9PENPhlg,694
+tests/test_python.py,sha256=5cTM45P77LoOl-qixJ7TQmf66zw69adj01kNaaSxHqE,20265
+ultralytics/__init__.py,sha256=PSQpLxNliz53D2Ljo-b2c-ew7HEU_DQVtKL-hHrFpUc,694
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
-ultralytics/cfg/__init__.py,sha256=lR6jykSO_0cigsjrqSyFj_8JG_LvYi796viasyWhcfs,21358
+ultralytics/cfg/__init__.py,sha256=JblkT6Ze9MZ8hSs8gkV8JPcEKNMm-YqRqM4x501Dn9g,21507
 ultralytics/cfg/default.yaml,sha256=Amh7abuPtqqtjq_f-KqRiRlP9yc40RnDz0Wc31tKfMo,8228
 ultralytics/cfg/datasets/Argoverse.yaml,sha256=FyeuJT5CHq_9d4hlfAf0kpZlnbUMO0S--UJ1yIqcdKk,3134
 ultralytics/cfg/datasets/DOTAv1.5.yaml,sha256=YDsyFPI6F6-OQXLBM3hOXo3vADYREwZzmMQfJNdpWyM,1193
@@ -88,11 +88,11 @@ ultralytics/data/explorer/utils.py,sha256=EvvukQiQUTBrsZznmMnyEX2EqTuwZo_Geyc8yf
 ultralytics/data/explorer/gui/__init__.py,sha256=mHtJuK4hwF8cuV-VHDc7tp6u6D1gHz2Z7JI8grmQDTs,42
 ultralytics/data/explorer/gui/dash.py,sha256=3mLrH0h-k_AthlgqVNXOHdlKoqjwNwFlnMYiMPAdL6Q,10059
 ultralytics/engine/__init__.py,sha256=mHtJuK4hwF8cuV-VHDc7tp6u6D1gHz2Z7JI8grmQDTs,42
-ultralytics/engine/exporter.py,sha256=_Pl42UD1kRsTUPGLXmr7tZFYuDEYv4FdYIluQE-1h-0,58216
+ultralytics/engine/exporter.py,sha256=K4wqYvPViL4qzO4J2VGi2yy3R2z3_VVaxNwxGJdKFnI,58449
 ultralytics/engine/model.py,sha256=IE6HE9VIzqO3DscxSLexub0LUR673eiPFrCPCt6ozEE,40103
 ultralytics/engine/predictor.py,sha256=wQRKdWGDTP5A6CS0gTC6U3RPDMhP3QkEzWSPm6eqCkU,17022
 ultralytics/engine/results.py,sha256=zRuEIrBtpoCQ3M6a_YscnyXrWSP-zpL3ACv0gTdrDaw,30987
-ultralytics/engine/trainer.py,sha256=P5XbPxh5hj4TLwuKeriuAlvcBWmILStm40-SgPrYvLk,35149
+ultralytics/engine/trainer.py,sha256=Gkh7tFa5BlQv4pZhcAKCfKBHwR28w4AHLqALxKa8ask,35264
 ultralytics/engine/tuner.py,sha256=iZrgMmXSDpfuDu4bdFRflmAsscys2-8W8qAGxSyOVJE,11844
 ultralytics/engine/validator.py,sha256=Y21Uo8_Zto4qjk_YqQk6k7tyfpq_Qk9cfjeXeyDRxs8,14643
 ultralytics/hub/__init__.py,sha256=zXam81eSJ2IkH0CwPy_VhG1XHZem9vs9jR4uG7s-uAY,5383
@@ -130,7 +130,7 @@ ultralytics/models/utils/__init__.py,sha256=mHtJuK4hwF8cuV-VHDc7tp6u6D1gHz2Z7JI8
 ultralytics/models/utils/loss.py,sha256=PmlKDe4xQTiYkPSCdNUabxJC7bh43zGxiKVIxsXBVGE,15135
 ultralytics/models/utils/ops.py,sha256=sn1vdwIK2LaCvxvuuP31Yw2HXEMAmQdo7KD9JVh4GM4,13244
 ultralytics/models/yolo/__init__.py,sha256=e1cZr9pbSbf3Ya2OvkTjGRwD_E2YZpe610xskBM8gEk,247
-ultralytics/models/yolo/model.py,sha256=ds9ArYRlA8QSF1cGg87JNavbo4wXpTUCtF6MIA9SkoA,4040
+ultralytics/models/yolo/model.py,sha256=wOrJ6HWU9KhG7pVcgK4HdI8xe2GSShe8V4v4bJDVydM,4041
 ultralytics/models/yolo/classify/__init__.py,sha256=t-4pUHmgI2gjhc-l3bqNEcEtKD1dO40nD4Vc6Y2xD6o,355
 ultralytics/models/yolo/classify/predict.py,sha256=wFY4GIlWxe7idMndEw1RnDI63o53MTfiHKz0s2fOjAY,2513
 ultralytics/models/yolo/classify/train.py,sha256=9CRqtLkePo4ZkAzMTxDY4ztrNaWE34qnytYymfCEBzs,6888
@@ -153,10 +153,10 @@ ultralytics/models/yolo/segment/train.py,sha256=aOQpDIptZfKSl9mFa6B-3W3QccMRlmBI
 ultralytics/models/yolo/segment/val.py,sha256=DxEpR0FaQePlOXb19-FO4G0Nl9rWf9smtAh9eH__2g0,11806
 ultralytics/models/yolo/world/__init__.py,sha256=3VTH0q4NOt2EWRom15yCymvmvm0Etp2bmETJUhsVTBI,103
 ultralytics/models/yolo/world/train.py,sha256=acYN2-onL69LrL4av6_hY2r5AY0urC0WViDstn7npfI,3686
-ultralytics/models/yolo/world/train_world.py,sha256=ICPsYNbuPkq_qf3FHl2YJ-q3g7ik0pI-zhMpLmHa5-4,4805
+ultralytics/models/yolo/world/train_world.py,sha256=pcVyTfUMXAZ8u98uFJxs5pKEunDFEHRRPfPRpkjCWSU,4848
 ultralytics/nn/__init__.py,sha256=4BPLHY89xEM_al5uK0aOmFgiML6CMGEZbezxOvTjOEs,587
-ultralytics/nn/autobackend.py,sha256=6amaXnbDlvh0kTIbeHV3kIM6X7P1r0T3le1GPxIgkOs,30864
-ultralytics/nn/tasks.py,sha256=JK-sKA0RWz612RpVfUI9zeevy4M7Fh6bysbana90wMs,43679
+ultralytics/nn/autobackend.py,sha256=8Eg57h3LZi4Bx2BLfy3xuFSpILB2spdMRnc7kff3JU4,31294
+ultralytics/nn/tasks.py,sha256=_Ko4Eg88oqs5jNuXeXC3ghDNQz9E08dFgdXzXQ390es,43680
 ultralytics/nn/modules/__init__.py,sha256=EohTpjqDmi9-ZWu7B9UDyl-esFvv6_S-VvPKNzHK2OU,2351
 ultralytics/nn/modules/block.py,sha256=smIz3oNTDA7UKrAH5FfSMh08C12-avgWTeIkbgZIv18,25251
 ultralytics/nn/modules/conv.py,sha256=Ywe87IhuaS22mR2JJ9xjnW8Sb-m7WTjxuqIxV_Dv8lI,12722
@@ -165,7 +165,7 @@ ultralytics/nn/modules/transformer.py,sha256=AxD9uURpCl-EqvXe3DiG6JW-pBzB16G-Aah
 ultralytics/nn/modules/utils.py,sha256=779QnnKp9v8jv251ESduTXJ0ol8HkIOLbGQWwEGQjhU,3196
 ultralytics/solutions/__init__.py,sha256=S4m7p_rpg2pk9PdnqqD-6Sk--wDHxZSo7cUZjSwj_iQ,561
 ultralytics/solutions/ai_gym.py,sha256=HDzzvBVFqWgQw2IgtEx5Eo3tEKbFRY3gkiVqax-4j2w,4683
-ultralytics/solutions/analytics.py,sha256=_gnK8xFjwUa0nyO7t9t6NAaBr86OFdLMIAxxDFHomoY,9062
+ultralytics/solutions/analytics.py,sha256=UI8HoegfIJGgvQPOt4-e9A0ss2_ofM7zzxcbKlhe66k,11572
 ultralytics/solutions/distance_calculation.py,sha256=pSIkyytHGRAaNzIrkkNkiOnSVWU1PYvURlCIV_jRORA,6505
 ultralytics/solutions/heatmap.py,sha256=AHXnmXhoQ95ph74zsdrvX_Lfy3wF0SsH0MIeTixE7Qg,10386
 ultralytics/solutions/object_counter.py,sha256=htcQGWJX1y-vXVV1yUiTDT3sm8ByItjSNfu2Rl2IEmk,10808
@@ -182,7 +182,7 @@ ultralytics/trackers/utils/gmc.py,sha256=vwcPA1n5zjPaBGhCDt8ItN7rq_6Sczsjn4gsXJf
 ultralytics/trackers/utils/kalman_filter.py,sha256=0oqhk59NKEiwcJ2FXnw6_sT4bIFC6Wu5IY2B-TGxJKU,15168
 ultralytics/trackers/utils/matching.py,sha256=UxhSGa5pN6WoYwYSBAkkt-O7xMxUR47VuUB6PfVNkb4,5404
 ultralytics/utils/__init__.py,sha256=dlKr7P0h2Ez3Q-WLQ49p0jsjjWkKq3CRkhlCJLGKlMk,38620
-ultralytics/utils/autobatch.py,sha256=ygZ3f2ByIkcujB89ENcTnGWWnAQw5Pbg6nBuShg-5t4,3863
+ultralytics/utils/autobatch.py,sha256=u9sWmDCQMRb_o0MjYacinke_I4-2Pp3iZMhbt08ZZdg,3945
 ultralytics/utils/benchmarks.py,sha256=dCuhgqEXcuEYFhja6Dj3t9J0DuCRa4HgYwgABtMj7Lk,23804
 ultralytics/utils/checks.py,sha256=4OQkddqlxh6Lldvhr8YOpyqaLVCohgTvr0R15Uanzq4,28376
 ultralytics/utils/dist.py,sha256=3HeNbY2gp7vYhcvVhsrvTrQXpQmgT8tpmnzApf3eQRA,2267
@@ -192,11 +192,11 @@ ultralytics/utils/files.py,sha256=TVfY0Wi5IsUc4YdsDzC0dAg-jAP5exYvwqB3VmXhDLY,67
 ultralytics/utils/instance.py,sha256=5daM5nkxBv9hr5QzyII8zmuFj24hHuNtcr4EMCHAtpY,15654
 ultralytics/utils/loss.py,sha256=ejXnPEIAzNEoNz2UjW0_fcdeUs9Hy-jPzUrJ3FiIIwE,32717
 ultralytics/utils/metrics.py,sha256=XPD-xP0fchR8KgCuTcihV2-n0EK1cWi3-53BWN_pLuA,53518
-ultralytics/utils/ops.py,sha256=5E6S_aYSg4OjNd9c-mpdbHkW-MMIWu9dNmlIdJmF9wE,33123
+ultralytics/utils/ops.py,sha256=J9wbb9aTW9aaI5DJRqA72BZAX77cmVyCJdnGuwkDu-k,33089
 ultralytics/utils/patches.py,sha256=SgMqeMsq2K6JoBJP1NplXMl9C6rK0JeJUChjBrJOneo,2750
 ultralytics/utils/plotting.py,sha256=47mfSDCP7Pt3jT_IlgnIwIH3wcBeSh04lbzep_F2wPc,48207
 ultralytics/utils/tal.py,sha256=xuIyryUjaaYHkHPG9GvBwh1xxN2Hq4y3hXOtuERehwY,16017
-ultralytics/utils/torch_utils.py,sha256=6AjQsncSsXZ3Cf_YzxWBeEBbks9s7gvPVpU6-dV3psg,26771
+ultralytics/utils/torch_utils.py,sha256=G8gVzI3sOSVSHORi5a2u-iFhUCGGHn5_eKHaOaLfsOY,27047
 ultralytics/utils/triton.py,sha256=gg1finxno_tY2Ge9PMhmu7PI9wvoFZoiicdT4Bhqv3w,3936
 ultralytics/utils/tuner.py,sha256=49KAadKZsUeCpwIm5Sn0grb0RPcMNI8vHGLwroDEJNI,6171
 ultralytics/utils/callbacks/__init__.py,sha256=YrWqC3BVVaTLob4iCPR6I36mUxIUOpPJW7B_LjT78Qw,214
@@ -208,11 +208,11 @@ ultralytics/utils/callbacks/hub.py,sha256=IPNnCRlAEFA-Dt18JWTuHhaQpcAy3XGgxBD4Jh
 ultralytics/utils/callbacks/mlflow.py,sha256=AVuYE4UKA5Eeg8sffbkCOe4tGgtCvBlGG4D9PMLm1Z0,5323
 ultralytics/utils/callbacks/neptune.py,sha256=5Z3ua5YBTUS56FH8VQKQG1aaIo9fH8GEyzC5q7p4ipQ,3756
 ultralytics/utils/callbacks/raytune.py,sha256=ODVYzy-CoM4Uge0zjkh3Hnh9nF2M0vhDrSenXnvcizw,705
-ultralytics/utils/callbacks/tensorboard.py,sha256=Z1veCVcn9THPhdplWuIzwlsW2yF7y-On9IZIk3khM0Y,4135
+ultralytics/utils/callbacks/tensorboard.py,sha256=QEgOVhUqY9akOs5TJIwz1Rvn6l32xWLpOxlwEyWF0B8,4136
 ultralytics/utils/callbacks/wb.py,sha256=DViD0KeXH_i3eVT_CLR4bZFs1TMMUZBVBBYIS3aUfp0,6745
-ultralytics-8.2.27.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.2.27.dist-info/METADATA,sha256=e_OAAn54qG7kXEU1jhJkvEPvNzOKlK8jkWuERxkGgt4,41200
-ultralytics-8.2.27.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-ultralytics-8.2.27.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.2.27.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.2.27.dist-info/RECORD,,
+ultralytics-8.2.29.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.2.29.dist-info/METADATA,sha256=PVt2gluWjecXemoXiSviwOBcb0U2kATzj9gPuemTNQc,41212
+ultralytics-8.2.29.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+ultralytics-8.2.29.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.2.29.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.2.29.dist-info/RECORD,,