ultralytics 8.3.221__tar.gz → 8.3.222__tar.gz

{ultralytics-8.3.221 → ultralytics-8.3.222}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.221
+Version: 8.3.222
 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>

{ultralytics-8.3.221 → ultralytics-8.3.222}/pyproject.toml

@@ -189,5 +189,5 @@ close-quotes-on-newline = true
 in-place = true
 
 [tool.codespell]
-ignore-words-list = "crate,nd,ned,strack,dota,ane,segway,fo,gool,winn,commend,bloc,nam,afterall"
-skip = '*.pt,*.pth,*.torchscript,*.onnx,*.tflite,*.pb,*.bin,*.param,*.mlmodel,*.engine,*.npy,*.data*,*.csv,*pnnx*,*venv*,*translat*,__pycache__*,*.ico,*.jpg,*.png,*.mp4,*.mov,/runs,/.git,./docs/??/*.md,./docs/mkdocs_??.yml'
+ignore-words-list = "grey,writeable,finalY,RepResNet,Idenfy,WIT,Smoot,EHR,ROUGE,ALS,iTerm,Carmel,FPR,Hach,Calle,ore,COO,MOT,crate,nd,ned,strack,dota,ane,segway,fo,gool,winn,commend,bloc,nam,afterall,skelton,goin"
+skip = "lvis.yaml,open-images-v7.yaml,ImageNet.yaml,*.pt,*.pth,*.torchscript,*.onnx,*.tflite,*.pb,*.bin,*.param,*.mlmodel,*.engine,*.npy,*.data*,*.csv,*pnnx*,*venv*,*translat*,*lock*,__pycache__*,*.ico,*.jpg,*.png,*.webp,*.avif,*.mp4,*.mov,/runs,/.git,./docs/??/*.md,./docs/mkdocs_??.yml"

{ultralytics-8.3.221 → ultralytics-8.3.222}/tests/test_python.py

@@ -136,23 +136,23 @@ def test_predict_visualize(model):
     YOLO(WEIGHTS_DIR / model)(SOURCE, imgsz=32, visualize=True)
 
 
-def test_predict_grey_and_4ch(tmp_path):
-    """Test YOLO prediction on SOURCE converted to greyscale and 4-channel images with various filenames."""
+def test_predict_gray_and_4ch(tmp_path):
+    """Test YOLO prediction on SOURCE converted to grayscale and 4-channel images with various filenames."""
     im = Image.open(SOURCE)
 
-    source_greyscale = tmp_path / "greyscale.jpg"
+    source_grayscale = tmp_path / "grayscale.jpg"
     source_rgba = tmp_path / "4ch.png"
     source_non_utf = tmp_path / "non_UTF_测试文件_tést_image.jpg"
     source_spaces = tmp_path / "image with spaces.jpg"
 
-    im.convert("L").save(source_greyscale)  # greyscale
+    im.convert("L").save(source_grayscale)  # grayscale
     im.convert("RGBA").save(source_rgba)  # 4-ch PNG with alpha
     im.save(source_non_utf)  # non-UTF characters in filename
     im.save(source_spaces)  # spaces in filename
 
     # Inference
     model = YOLO(MODEL)
-    for f in source_rgba, source_greyscale, source_non_utf, source_spaces:
+    for f in source_rgba, source_grayscale, source_non_utf, source_spaces:
         for source in Image.open(f), cv2.imread(str(f)), f:
             results = model(source, save=True, verbose=True, imgsz=32)
             assert len(results) == 1  # verify that an image was run

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.221"
+__version__ = "8.3.222"
 
 import importlib
 import os

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/data/base.py

@@ -307,7 +307,7 @@ class BaseDataset(Dataset):
             b += im.nbytes
             if not os.access(Path(im_file).parent, os.W_OK):
                 self.cache = None
-                LOGGER.warning(f"{self.prefix}Skipping caching images to disk, directory not writeable")
+                LOGGER.warning(f"{self.prefix}Skipping caching images to disk, directory not writable")
                 return False
         disk_required = b * self.ni / n * (1 + safety_margin)  # bytes required to cache dataset to disk
         total, _used, free = shutil.disk_usage(Path(self.im_files[0]).parent)

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/data/utils.py

@@ -804,4 +804,4 @@ def save_dataset_cache_file(prefix: str, path: Path, x: dict, version: str):
             np.save(file, x)
         LOGGER.info(f"{prefix}New cache created: {path}")
     else:
-        LOGGER.warning(f"{prefix}Cache directory {path.parent} is not writeable, cache not saved.")
+        LOGGER.warning(f"{prefix}Cache directory {path.parent} is not writable, cache not saved.")

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/engine/exporter.py

@@ -367,10 +367,10 @@ class Exporter:
             if not self.args.int8:
                 LOGGER.warning("IMX export requires int8=True, setting int8=True.")
                 self.args.int8 = True
-            if not self.args.nms:
+            if not self.args.nms and model.task in {"detect", "pose"}:
                 LOGGER.warning("IMX export requires nms=True, setting nms=True.")
                 self.args.nms = True
-            if model.task not in {"detect", "pose"}:
+            if model.task not in {"detect", "pose", "classify"}:
                 raise ValueError("IMX export only supported for detection and pose estimation models.")
         if not hasattr(model, "names"):
             model.names = default_class_names()
@@ -396,8 +396,6 @@ class Exporter:
             assert self.args.name in RKNN_CHIPS, (
                 f"Invalid processor name '{self.args.name}' for Rockchip RKNN export. Valid names are {RKNN_CHIPS}."
             )
-        if self.args.int8 and tflite:
-            assert not getattr(model, "end2end", False), "TFLite INT8 export not supported for end2end models."
         if self.args.nms:
             assert not isinstance(model, ClassificationModel), "'nms=True' is not valid for classification models."
             assert not tflite or not ARM64 or not LINUX, "TFLite export with NMS unsupported on ARM64 Linux"
@@ -1510,17 +1508,16 @@ class NMSModel(torch.nn.Module):
             box, score, cls, extra = box[mask], score[mask], cls[mask], extra[mask]
             nmsbox = box.clone()
             # `8` is the minimum value experimented to get correct NMS results for obb
-            multiplier = 8 if self.obb else 1
+            multiplier = (8 if self.obb else 1) / max(len(self.model.names), 1)
             # Normalize boxes for NMS since large values for class offset causes issue with int8 quantization
             if self.args.format == "tflite":  # TFLite is already normalized
                 nmsbox *= multiplier
             else:
-                nmsbox = multiplier * nmsbox / torch.tensor(x.shape[2:], **kwargs).max()
-            if not self.args.agnostic_nms:  # class-specific NMS
+                nmsbox = multiplier * (nmsbox / torch.tensor(x.shape[2:], **kwargs).max())
+            if not self.args.agnostic_nms:  # class-wise NMS
                 end = 2 if self.obb else 4
                 # fully explicit expansion otherwise reshape error
-                # large max_wh causes issues when quantizing
-                cls_offset = cls.reshape(-1, 1).expand(nmsbox.shape[0], end)
+                cls_offset = cls.view(cls.shape[0], 1).expand(cls.shape[0], end)
                 offbox = nmsbox[:, :end] + cls_offset * multiplier
                 nmsbox = torch.cat((offbox, nmsbox[:, end:]), dim=-1)
             nms_fn = (

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/engine/model.py

@@ -877,7 +877,7 @@ class Model(torch.nn.Module):
             >>> model = model._apply(lambda t: t.cuda())  # Move model to GPU
         """
         self._check_is_pytorch_model()
-        self = super()._apply(fn)  # noqa
+        self = super()._apply(fn)
         self.predictor = None  # reset predictor as device may have changed
         self.overrides["device"] = self.device  # was str(self.device) i.e. device(type='cuda', index=0) -> 'cuda:0'
         return self

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/engine/trainer.py

@@ -727,7 +727,7 @@ class BaseTrainer:
 
     def label_loss_items(self, loss_items=None, prefix="train"):
         """
-        Return a loss dict with labelled training loss items tensor.
+        Return a loss dict with labeled training loss items tensor.
 
         Note:
             This is not needed for classification but necessary for segmentation & detection

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/models/yolo/classify/train.py

@@ -38,7 +38,7 @@ class ClassificationTrainer(BaseTrainer):
         preprocess_batch: Preprocess a batch of images and classes.
         progress_string: Return a formatted string showing training progress.
         get_validator: Return an instance of ClassificationValidator.
-        label_loss_items: Return a loss dict with labelled training loss items.
+        label_loss_items: Return a loss dict with labeled training loss items.
         final_eval: Evaluate trained model and save validation results.
         plot_training_samples: Plot training samples with their annotations.
 
@@ -178,7 +178,7 @@ class ClassificationTrainer(BaseTrainer):
 
     def label_loss_items(self, loss_items: torch.Tensor | None = None, prefix: str = "train"):
         """
-        Return a loss dict with labelled training loss items tensor.
+        Return a loss dict with labeled training loss items tensor.
 
         Args:
             loss_items (torch.Tensor, optional): Loss tensor items.

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/utils/__init__.py

@@ -795,13 +795,13 @@ def is_pip_package(filepath: str = __name__) -> bool:
 
 def is_dir_writeable(dir_path: str | Path) -> bool:
     """
-    Check if a directory is writeable.
+    Check if a directory is writable.
 
     Args:
         dir_path (str | Path): The path to the directory.
 
     Returns:
-        (bool): True if the directory is writeable, False otherwise.
+        (bool): True if the directory is writable, False otherwise.
     """
     return os.access(str(dir_path), os.W_OK)
 
@@ -882,14 +882,14 @@ def get_user_config_dir(sub_dir="Ultralytics"):
         p.mkdir(parents=True, exist_ok=True)
         return p
 
-    # Fallbacks for Docker, GCP/AWS functions where only /tmp is writeable
+    # Fallbacks for Docker, GCP/AWS functions where only /tmp is writable
     for alt in [Path("/tmp") / sub_dir, Path.cwd() / sub_dir]:
         if alt.exists():
             return alt
         if is_dir_writeable(alt.parent):
             alt.mkdir(parents=True, exist_ok=True)
             LOGGER.warning(
-                f"user config directory '{p}' is not writeable, using '{alt}'. Set YOLO_CONFIG_DIR to override."
+                f"user config directory '{p}' is not writable, using '{alt}'. Set YOLO_CONFIG_DIR to override."
             )
             return alt
 

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/utils/benchmarks.py

@@ -144,7 +144,9 @@ def benchmark(
             if format == "imx":
                 assert not is_end2end
                 assert not isinstance(model, YOLOWorld), "YOLOWorldv2 IMX exports not supported"
-                assert model.task == "detect", "IMX only supported for detection task"
+                assert model.task in {"detect", "classify", "pose"}, (
+                    "IMX export is only supported for detection, classification and pose estimation tasks"
+                )
                 assert "C2f" in model.__str__(), "IMX only supported for YOLOv8n and YOLO11n"
             if format == "rknn":
                 assert not isinstance(model, YOLOWorld), "YOLOWorldv2 RKNN exports not supported yet"

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/utils/export/imx.py

@@ -6,6 +6,7 @@ import subprocess
 import types
 from pathlib import Path
 
+import numpy as np
 import torch
 
 from ultralytics.nn.modules import Detect, Pose
@@ -13,6 +14,32 @@ from ultralytics.utils import LOGGER
 from ultralytics.utils.tal import make_anchors
 from ultralytics.utils.torch_utils import copy_attr
 
+# Configuration for Model Compression Toolkit (MCT) quantization
+MCT_CONFIG = {
+    "YOLO11": {
+        "detect": {
+            "layer_names": ["sub", "mul_2", "add_14", "cat_21"],
+            "weights_memory": 2585350.2439,
+            "n_layers": 238,
+        },
+        "pose": {
+            "layer_names": ["sub", "mul_2", "add_14", "cat_22", "cat_23", "mul_4", "add_15"],
+            "weights_memory": 2437771.67,
+            "n_layers": 257,
+        },
+        "classify": {"layer_names": [], "weights_memory": np.inf, "n_layers": 112},
+    },
+    "YOLOv8": {
+        "detect": {"layer_names": ["sub", "mul", "add_6", "cat_17"], "weights_memory": 2550540.8, "n_layers": 168},
+        "pose": {
+            "layer_names": ["add_7", "mul_2", "cat_19", "mul", "sub", "add_6", "cat_18"],
+            "weights_memory": 2482451.85,
+            "n_layers": 187,
+        },
+        "classify": {"layer_names": [], "weights_memory": np.inf, "n_layers": 73},
+    },
+}
+
 
 class FXModel(torch.nn.Module):
     """
@@ -200,30 +227,13 @@ def torch2imx(
     tpc = get_target_platform_capabilities(tpc_version="4.0", device_type="imx500")
 
     bit_cfg = mct.core.BitWidthConfig()
-    if "C2PSA" in model.__str__():  # YOLO11
-        if model.task == "detect":
-            layer_names = ["sub", "mul_2", "add_14", "cat_21"]
-            weights_memory = 2585350.2439
-            n_layers = 238  # 238 layers for fused YOLO11n
-        elif model.task == "pose":
-            layer_names = ["sub", "mul_2", "add_14", "cat_22", "cat_23", "mul_4", "add_15"]
-            weights_memory = 2437771.67
-            n_layers = 257  # 257 layers for fused YOLO11n-pose
-    else:  # YOLOv8
-        if model.task == "detect":
-            layer_names = ["sub", "mul", "add_6", "cat_17"]
-            weights_memory = 2550540.8
-            n_layers = 168  # 168 layers for fused YOLOv8n
-        elif model.task == "pose":
-            layer_names = ["add_7", "mul_2", "cat_19", "mul", "sub", "add_6", "cat_18"]
-            weights_memory = 2482451.85
-            n_layers = 187  # 187 layers for fused YOLO11n-pose
+    mct_config = MCT_CONFIG["YOLO11" if "C2PSA" in model.__str__() else "YOLOv8"][model.task]
 
     # Check if the model has the expected number of layers
-    if len(list(model.modules())) != n_layers:
+    if len(list(model.modules())) != mct_config["n_layers"]:
         raise ValueError("IMX export only supported for YOLOv8n and YOLO11n models.")
 
-    for layer_name in layer_names:
+    for layer_name in mct_config["layer_names"]:
         bit_cfg.set_manual_activation_bit_width([mct.core.common.network_editors.NodeNameFilter(layer_name)], 16)
 
     config = mct.core.CoreConfig(
@@ -232,7 +242,7 @@ def torch2imx(
         bit_width_config=bit_cfg,
     )
 
-    resource_utilization = mct.core.ResourceUtilization(weights_memory=weights_memory)
+    resource_utilization = mct.core.ResourceUtilization(weights_memory=mct_config["weights_memory"])
 
     quant_model = (
         mct.gptq.pytorch_gradient_post_training_quantization(  # Perform Gradient-Based Post Training Quantization
@@ -255,13 +265,14 @@ def torch2imx(
         )[0]
     )
 
-    quant_model = NMSWrapper(
-        model=quant_model,
-        score_threshold=conf or 0.001,
-        iou_threshold=iou,
-        max_detections=max_det,
-        task=model.task,
-    )
+    if model.task != "classify":
+        quant_model = NMSWrapper(
+            model=quant_model,
+            score_threshold=conf or 0.001,
+            iou_threshold=iou,
+            max_detections=max_det,
+            task=model.task,
+        )
 
     f = Path(str(file).replace(file.suffix, "_imx_model"))
     f.mkdir(exist_ok=True)

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/utils/metrics.py

@@ -663,7 +663,7 @@ def plot_pr_curve(
         for i, y in enumerate(py.T):
             ax.plot(px, y, linewidth=1, label=f"{names[i]} {ap[i, 0]:.3f}")  # plot(recall, precision)
     else:
-        ax.plot(px, py, linewidth=1, color="grey")  # plot(recall, precision)
+        ax.plot(px, py, linewidth=1, color="gray")  # plot(recall, precision)
 
     ax.plot(px, py.mean(1), linewidth=3, color="blue", label=f"all classes {ap[:, 0].mean():.3f} mAP@0.5")
     ax.set_xlabel("Recall")
@@ -708,7 +708,7 @@ def plot_mc_curve(
         for i, y in enumerate(py):
             ax.plot(px, y, linewidth=1, label=f"{names[i]}")  # plot(confidence, metric)
     else:
-        ax.plot(px, py.T, linewidth=1, color="grey")  # plot(confidence, metric)
+        ax.plot(px, py.T, linewidth=1, color="gray")  # plot(confidence, metric)
 
     y = smooth(py.mean(0), 0.1)
     ax.plot(px, y, linewidth=3, color="blue", label=f"all classes {y.max():.2f} at {px[y.argmax()]:.3f}")

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics/utils/plotting.py

@@ -722,7 +722,7 @@ def plot_images(
         convert tensor inputs to numpy arrays for processing.
 
         Channel Support:
-        - 1 channel: Greyscale
+        - 1 channel: Grayscale
         - 2 channels: Third channel added as zeros
         - 3 channels: Used as-is (standard RGB)
         - 4+ channels: Cropped to first 3 channels

{ultralytics-8.3.221 → ultralytics-8.3.222}/ultralytics.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.221
+Version: 8.3.222
 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>