ultralytics 8.3.111__py3-none-any.whl → 8.3.113__py3-none-any.whl

ultralytics/data/split.py

@@ -0,0 +1,123 @@
+import random
+import shutil
+from pathlib import Path
+
+from ultralytics.data.utils import IMG_FORMATS, img2label_paths
+from ultralytics.utils import DATASETS_DIR, LOGGER, TQDM
+
+
+def split_classify_dataset(source_dir, train_ratio=0.8):
+    """
+    Split dataset into train and val directories in a new directory.
+
+    Creates a new directory '{source_dir}_split' with train/val subdirectories, preserving the original class
+    structure with an 80/20 split by default.
+
+    Directory structure:
+        Before:
+            caltech/
+            ├── class1/
+            │   ├── img1.jpg
+            │   ├── img2.jpg
+            │   └── ...
+            ├── class2/
+            │   ├── img1.jpg
+            │   └── ...
+            └── ...
+
+        After:
+            caltech_split/
+            ├── train/
+            │   ├── class1/
+            │   │   ├── img1.jpg
+            │   │   └── ...
+            │   ├── class2/
+            │   │   ├── img1.jpg
+            │   │   └── ...
+            │   └── ...
+            └── val/
+                ├── class1/
+                │   ├── img2.jpg
+                │   └── ...
+                ├── class2/
+                │   └── ...
+                └── ...
+
+    Args:
+        source_dir (str | Path): Path to Caltech dataset root directory.
+        train_ratio (float): Ratio for train split, between 0 and 1.
+
+    Examples:
+        >>> # Split dataset with default 80/20 ratio
+        >>> split_classify_dataset("path/to/caltech")
+        >>> # Split with custom ratio
+        >>> split_classify_dataset("path/to/caltech", 0.75)
+    """
+    source_path = Path(source_dir)
+    split_path = Path(f"{source_path}_split")
+    train_path, val_path = split_path / "train", split_path / "val"
+
+    # Create directory structure
+    split_path.mkdir(exist_ok=True)
+    train_path.mkdir(exist_ok=True)
+    val_path.mkdir(exist_ok=True)
+
+    # Process class directories
+    class_dirs = [d for d in source_path.iterdir() if d.is_dir()]
+    total_images = sum(len(list(d.glob("*.*"))) for d in class_dirs)
+    stats = f"{len(class_dirs)} classes, {total_images} images"
+    LOGGER.info(f"Splitting {source_path} ({stats}) into {train_ratio:.0%} train, {1 - train_ratio:.0%} val...")
+
+    for class_dir in class_dirs:
+        # Create class directories
+        (train_path / class_dir.name).mkdir(exist_ok=True)
+        (val_path / class_dir.name).mkdir(exist_ok=True)
+
+        # Split and copy files
+        image_files = list(class_dir.glob("*.*"))
+        random.shuffle(image_files)
+        split_idx = int(len(image_files) * train_ratio)
+
+        for img in image_files[:split_idx]:
+            shutil.copy2(img, train_path / class_dir.name / img.name)
+
+        for img in image_files[split_idx:]:
+            shutil.copy2(img, val_path / class_dir.name / img.name)
+
+    LOGGER.info(f"Split complete in {split_path} ✅")
+    return split_path
+
+
+def autosplit(path=DATASETS_DIR / "coco8/images", weights=(0.9, 0.1, 0.0), annotated_only=False):
+    """
+    Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files.
+
+    Args:
+        path (Path, optional): Path to images directory.
+        weights (list | tuple, optional): Train, validation, and test split fractions.
+        annotated_only (bool, optional): If True, only images with an associated txt file are used.
+
+    Examples:
+        >>> from ultralytics.data.split import autosplit
+        >>> autosplit()
+    """
+    path = Path(path)  # images dir
+    files = sorted(x for x in path.rglob("*.*") if x.suffix[1:].lower() in IMG_FORMATS)  # image files only
+    n = len(files)  # number of files
+    random.seed(0)  # for reproducibility
+    indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
+
+    txt = ["autosplit_train.txt", "autosplit_val.txt", "autosplit_test.txt"]  # 3 txt files
+    for x in txt:
+        if (path.parent / x).exists():
+            (path.parent / x).unlink()  # remove existing
+
+    LOGGER.info(f"Autosplitting images from {path}" + ", using *.txt labeled images only" * annotated_only)
+    for i, img in TQDM(zip(indices, files), total=n):
+        if not annotated_only or Path(img2label_paths([str(img)])[0]).exists():  # check label
+            with open(path.parent / txt[i], "a", encoding="utf-8") as f:
+                f.write(f"./{img.relative_to(path.parent).as_posix()}" + "\n")  # add image to txt file
+
+
+if __name__ == "__main__":
+    split_classify_dataset("../datasets/caltech101")

ultralytics/data/utils.py

@@ -66,7 +66,7 @@ def check_file_speeds(files, threshold_ms=10, max_files=5, prefix=""):
         >>> check_file_speeds(image_files, threshold_ms=15)
     """
     if not files or len(files) == 0:
-        LOGGER.warning(f"{prefix}WARNING ⚠️ Image speed checks: No files to check")
+        LOGGER.warning(f"{prefix}Image speed checks: No files to check")
         return
 
     # Sample files (max 5)
@@ -96,7 +96,7 @@ def check_file_speeds(files, threshold_ms=10, max_files=5, prefix=""):
             pass
 
     if not ping_times:
-        LOGGER.warning(f"{prefix}WARNING ⚠️ Image speed checks: failed to access files")
+        LOGGER.warning(f"{prefix}Image speed checks: failed to access files")
         return
 
     # Calculate stats with uncertainties
@@ -116,7 +116,7 @@ def check_file_speeds(files, threshold_ms=10, max_files=5, prefix=""):
         LOGGER.info(f"{prefix}Fast image access ✅ ({ping_msg}{speed_msg}{size_msg})")
     else:
         LOGGER.warning(
-            f"{prefix}WARNING ⚠️ Slow image access detected ({ping_msg}{speed_msg}{size_msg}). "
+            f"{prefix}Slow image access detected ({ping_msg}{speed_msg}{size_msg}). "
             f"Use local storage instead of remote/mounted storage for better performance. "
             f"See https://docs.ultralytics.com/guides/model-training-tips/"
         )
@@ -166,11 +166,11 @@ def verify_image(args):
                 f.seek(-2, 2)
                 if f.read() != b"\xff\xd9":  # corrupt JPEG
                     ImageOps.exif_transpose(Image.open(im_file)).save(im_file, "JPEG", subsampling=0, quality=100)
-                    msg = f"{prefix}WARNING ⚠️ {im_file}: corrupt JPEG restored and saved"
+                    msg = f"{prefix}{im_file}: corrupt JPEG restored and saved"
         nf = 1
     except Exception as e:
         nc = 1
-        msg = f"{prefix}WARNING ⚠️ {im_file}: ignoring corrupt image/label: {e}"
+        msg = f"{prefix}{im_file}: ignoring corrupt image/label: {e}"
     return (im_file, cls), nf, nc, msg
 
 
@@ -192,7 +192,7 @@ def verify_image_label(args):
                 f.seek(-2, 2)
                 if f.read() != b"\xff\xd9":  # corrupt JPEG
                     ImageOps.exif_transpose(Image.open(im_file)).save(im_file, "JPEG", subsampling=0, quality=100)
-                    msg = f"{prefix}WARNING ⚠️ {im_file}: corrupt JPEG restored and saved"
+                    msg = f"{prefix}{im_file}: corrupt JPEG restored and saved"
 
         # Verify labels
         if os.path.isfile(lb_file):
@@ -227,7 +227,7 @@ def verify_image_label(args):
                     lb = lb[i]  # remove duplicates
                     if segments:
                         segments = [segments[x] for x in i]
-                    msg = f"{prefix}WARNING ⚠️ {im_file}: {nl - len(i)} duplicate labels removed"
+                    msg = f"{prefix}{im_file}: {nl - len(i)} duplicate labels removed"
             else:
                 ne = 1  # label empty
                 lb = np.zeros((0, (5 + nkpt * ndim) if keypoint else 5), dtype=np.float32)
@@ -243,7 +243,7 @@ def verify_image_label(args):
         return im_file, lb, shape, segments, keypoints, nm, nf, ne, nc, msg
     except Exception as e:
         nc = 1
-        msg = f"{prefix}WARNING ⚠️ {im_file}: ignoring corrupt image/label: {e}"
+        msg = f"{prefix}{im_file}: ignoring corrupt image/label: {e}"
         return [None, None, None, None, None, nm, nf, ne, nc, msg]
 
 
@@ -408,7 +408,7 @@ def check_det_dataset(dataset, autodownload=True):
                 raise SyntaxError(
                     emojis(f"{dataset} '{k}:' key missing ❌.\n'train' and 'val' are required in all data YAMLs.")
                 )
-            LOGGER.info("WARNING ⚠️ renaming data YAML 'validation' key to 'val' to match YOLO format.")
+            LOGGER.warning("renaming data YAML 'validation' key to 'val' to match YOLO format.")
             data["val"] = data.pop("validation")  # replace 'validation' key with 'val' key
     if "names" not in data and "nc" not in data:
         raise SyntaxError(emojis(f"{dataset} key missing ❌.\n either 'names' or 'nc' are required in all data YAMLs."))
@@ -420,6 +420,7 @@ def check_det_dataset(dataset, autodownload=True):
         data["nc"] = len(data["names"])
 
     data["names"] = check_class_names(data["names"])
+    data["channels"] = data.get("channels", 3)  # get image channels, default to 3
 
     # Resolve paths
     path = Path(extract_dir or data.get("path") or Path(data.get("yaml_file", "")).parent)  # dataset root
@@ -444,7 +445,8 @@ def check_det_dataset(dataset, autodownload=True):
         val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])]  # val path
         if not all(x.exists() for x in val):
             name = clean_url(dataset)  # dataset name with URL auth stripped
-            m = f"\nDataset '{name}' images not found ⚠️, missing path '{[x for x in val if not x.exists()][0]}'"
+            LOGGER.info("")
+            m = f"Dataset '{name}' images not found, missing path '{[x for x in val if not x.exists()][0]}'"
             if s and autodownload:
                 LOGGER.warning(m)
             else:
@@ -496,16 +498,27 @@ def check_cls_dataset(dataset, split=""):
     dataset = Path(dataset)
     data_dir = (dataset if dataset.is_dir() else (DATASETS_DIR / dataset)).resolve()
     if not data_dir.is_dir():
-        LOGGER.warning(f"\nDataset not found ⚠️, missing path {data_dir}, attempting download...")
+        LOGGER.info("")
+        LOGGER.warning(f"Dataset not found, missing path {data_dir}, attempting download...")
         t = time.time()
         if str(dataset) == "imagenet":
             subprocess.run(f"bash {ROOT / 'data/scripts/get_imagenet.sh'}", shell=True, check=True)
         else:
             url = f"https://github.com/ultralytics/assets/releases/download/v0.0.0/{dataset}.zip"
             download(url, dir=data_dir.parent)
-        s = f"Dataset download success ✅ ({time.time() - t:.1f}s), saved to {colorstr('bold', data_dir)}\n"
-        LOGGER.info(s)
+        LOGGER.info(f"Dataset download success ✅ ({time.time() - t:.1f}s), saved to {colorstr('bold', data_dir)}\n")
     train_set = data_dir / "train"
+    if not train_set.is_dir():
+        LOGGER.warning(f"Dataset 'split=train' not found at {train_set}")
+        image_files = list(data_dir.rglob("*.jpg")) + list(data_dir.rglob("*.png"))
+        if image_files:
+            from ultralytics.data.split import split_classify_dataset
+
+            LOGGER.info(f"Found {len(image_files)} images in subdirectories. Attempting to split...")
+            data_dir = split_classify_dataset(data_dir, train_ratio=0.8)
+            train_set = data_dir / "train"
+        else:
+            LOGGER.error(f"No images found in {data_dir} or its subdirectories.")
     val_set = (
         data_dir / "val"
         if (data_dir / "val").exists()
@@ -515,10 +528,10 @@ def check_cls_dataset(dataset, split=""):
     )  # data/test or data/val
     test_set = data_dir / "test" if (data_dir / "test").exists() else None  # data/val or data/test
     if split == "val" and not val_set:
-        LOGGER.warning("WARNING ⚠️ Dataset 'split=val' not found, using 'split=test' instead.")
+        LOGGER.warning("Dataset 'split=val' not found, using 'split=test' instead.")
         val_set = test_set
     elif split == "test" and not test_set:
-        LOGGER.warning("WARNING ⚠️ Dataset 'split=test' not found, using 'split=val' instead.")
+        LOGGER.warning("Dataset 'split=test' not found, using 'split=val' instead.")
         test_set = val_set
 
     nc = len([x for x in (data_dir / "train").glob("*") if x.is_dir()])  # number of classes
@@ -536,15 +549,15 @@ def check_cls_dataset(dataset, split=""):
             nd = len({file.parent for file in files})  # number of directories
             if nf == 0:
                 if k == "train":
-                    raise FileNotFoundError(emojis(f"{dataset} '{k}:' no training images found ❌ "))
+                    raise FileNotFoundError(f"{dataset} '{k}:' no training images found")
                 else:
-                    LOGGER.warning(f"{prefix} found {nf} images in {nd} classes: WARNING ⚠️ no images found")
+                    LOGGER.warning(f"{prefix} found {nf} images in {nd} classes (no images found)")
             elif nd != nc:
-                LOGGER.warning(f"{prefix} found {nf} images in {nd} classes: ERROR ❌️ requires {nc} classes, not {nd}")
+                LOGGER.error(f"{prefix} found {nf} images in {nd} classes (requires {nc} classes, not {nd})")
             else:
                 LOGGER.info(f"{prefix} found {nf} images in {nd} classes ✅ ")
 
-    return {"train": train_set, "val": val_set, "test": test_set, "nc": nc, "names": names}
+    return {"train": train_set, "val": val_set, "test": test_set, "nc": nc, "names": names, "channels": 3}
 
 
 class HUBDatasetStats:
@@ -728,7 +741,7 @@ def compress_one_image(f, f_new=None, max_dim=1920, quality=50):
             im = im.resize((int(im.width * r), int(im.height * r)))
         im.save(f_new or f, "JPEG", quality=quality, optimize=True)  # save
     except Exception as e:  # use OpenCV
-        LOGGER.info(f"WARNING ⚠️ HUB ops PIL failure {f}: {e}")
+        LOGGER.warning(f"HUB ops PIL failure {f}: {e}")
         im = cv2.imread(f)
         im_height, im_width = im.shape[:2]
         r = max_dim / max(im_height, im_width)  # ratio
@@ -737,37 +750,6 @@ def compress_one_image(f, f_new=None, max_dim=1920, quality=50):
         cv2.imwrite(str(f_new or f), im)
 
 
-def autosplit(path=DATASETS_DIR / "coco8/images", weights=(0.9, 0.1, 0.0), annotated_only=False):
-    """
-    Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files.
-
-    Args:
-        path (Path, optional): Path to images directory.
-        weights (list | tuple, optional): Train, validation, and test split fractions.
-        annotated_only (bool, optional): If True, only images with an associated txt file are used.
-
-    Examples:
-        >>> from ultralytics.data.utils import autosplit
-        >>> autosplit()
-    """
-    path = Path(path)  # images dir
-    files = sorted(x for x in path.rglob("*.*") if x.suffix[1:].lower() in IMG_FORMATS)  # image files only
-    n = len(files)  # number of files
-    random.seed(0)  # for reproducibility
-    indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
-
-    txt = ["autosplit_train.txt", "autosplit_val.txt", "autosplit_test.txt"]  # 3 txt files
-    for x in txt:
-        if (path.parent / x).exists():
-            (path.parent / x).unlink()  # remove existing
-
-    LOGGER.info(f"Autosplitting images from {path}" + ", using *.txt labeled images only" * annotated_only)
-    for i, img in TQDM(zip(indices, files), total=n):
-        if not annotated_only or Path(img2label_paths([str(img)])[0]).exists():  # check label
-            with open(path.parent / txt[i], "a", encoding="utf-8") as f:
-                f.write(f"./{img.relative_to(path.parent).as_posix()}" + "\n")  # add image to txt file
-
-
 def load_dataset_cache_file(path):
     """Load an Ultralytics *.cache dictionary from path."""
     import gc
@@ -788,4 +770,4 @@ def save_dataset_cache_file(prefix, path, x, version):
             np.save(file, x)
         LOGGER.info(f"{prefix}New cache created: {path}")
     else:
-        LOGGER.warning(f"{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable, cache not saved.")
+        LOGGER.warning(f"{prefix}Cache directory {path.parent} is not writeable, cache not saved.")

ultralytics/engine/exporter.py

@@ -192,7 +192,7 @@ def try_export(inner_func):
             LOGGER.info(f"{prefix} export success ✅ {dt.t:.1f}s, saved as '{f}' ({file_size(f):.1f} MB)")
             return f, model
         except Exception as e:
-            LOGGER.error(f"{prefix} export failure ❌ {dt.t:.1f}s: {e}")
+            LOGGER.error(f"{prefix} export failure {dt.t:.1f}s: {e}")
             raise e
 
     return outer_func
@@ -262,7 +262,7 @@ class Exporter:
             matches = difflib.get_close_matches(fmt, fmts, n=1, cutoff=0.6)  # 60% similarity required to match
             if not matches:
                 raise ValueError(f"Invalid export format='{fmt}'. Valid formats are {fmts}")
-            LOGGER.warning(f"WARNING ⚠️ Invalid export format='{fmt}', updating to format='{matches[0]}'")
+            LOGGER.warning(f"Invalid export format='{fmt}', updating to format='{matches[0]}'")
             fmt = matches[0]
         flags = [x == fmt for x in fmts]
         if sum(flags) != 1:
@@ -276,16 +276,14 @@ class Exporter:
         # Device
         dla = None
         if fmt == "engine" and self.args.device is None:
-            LOGGER.warning("WARNING ⚠️ TensorRT requires GPU export, automatically assigning device=0")
+            LOGGER.warning("TensorRT requires GPU export, automatically assigning device=0")
             self.args.device = "0"
         if fmt == "engine" and "dla" in str(self.args.device):  # convert int/list to str first
             dla = self.args.device.split(":")[-1]
             self.args.device = "0"  # update device to "0"
             assert dla in {"0", "1"}, f"Expected self.args.device='dla:0' or 'dla:1, but got {self.args.device}."
         if imx and self.args.device is None and torch.cuda.is_available():
-            LOGGER.warning(
-                "WARNING ⚠️ Exporting on CPU while CUDA is available, setting device=0 for faster export on GPU."
-            )
+            LOGGER.warning("Exporting on CPU while CUDA is available, setting device=0 for faster export on GPU.")
             self.args.device = "0"  # update device to "0"
         self.device = select_device("cpu" if self.args.device is None else self.args.device)
 
@@ -294,7 +292,7 @@ class Exporter:
         validate_args(fmt, self.args, fmt_keys)
         if imx:
             if not self.args.int8:
-                LOGGER.warning("WARNING ⚠️ IMX export requires int8=True, setting int8=True.")
+                LOGGER.warning("IMX export requires int8=True, setting int8=True.")
                 self.args.int8 = True
             if model.task != "detect":
                 raise ValueError("IMX export only supported for detection models.")
@@ -302,10 +300,10 @@ class Exporter:
             model.names = default_class_names()
         model.names = check_class_names(model.names)
         if self.args.half and self.args.int8:
-            LOGGER.warning("WARNING ⚠️ half=True and int8=True are mutually exclusive, setting half=False.")
+            LOGGER.warning("half=True and int8=True are mutually exclusive, setting half=False.")
             self.args.half = False
         if self.args.half and onnx and self.device.type == "cpu":
-            LOGGER.warning("WARNING ⚠️ half=True only compatible with GPU export, i.e. use device=0")
+            LOGGER.warning("half=True only compatible with GPU export, i.e. use device=0")
             self.args.half = False
         self.imgsz = check_imgsz(self.args.imgsz, stride=model.stride, min_dim=2)  # check image size
         if self.args.int8 and engine:
@@ -316,7 +314,7 @@ class Exporter:
         if rknn:
             if not self.args.name:
                 LOGGER.warning(
-                    "WARNING ⚠️ Rockchip RKNN export requires a missing 'name' arg for processor type. "
+                    "Rockchip RKNN export requires a missing 'name' arg for processor type. "
                     "Using default name='rk3588'."
                 )
                 self.args.name = "rk3588"
@@ -330,7 +328,7 @@ class Exporter:
             assert not isinstance(model, ClassificationModel), "'nms=True' is not valid for classification models."
             assert not (tflite and ARM64 and LINUX), "TFLite export with NMS unsupported on ARM64 Linux"
             if getattr(model, "end2end", False):
-                LOGGER.warning("WARNING ⚠️ 'nms=True' is not available for end2end models. Forcing 'nms=False'.")
+                LOGGER.warning("'nms=True' is not available for end2end models. Forcing 'nms=False'.")
                 self.args.nms = False
             self.args.conf = self.args.conf or 0.25  # set conf default value for nms export
         if edgetpu:
@@ -339,12 +337,12 @@ class Exporter:
                     "Edge TPU export only supported on non-aarch64 Linux. See https://coral.ai/docs/edgetpu/compiler"
                 )
             elif self.args.batch != 1:  # see github.com/ultralytics/ultralytics/pull/13420
-                LOGGER.warning("WARNING ⚠️ Edge TPU export requires batch size 1, setting batch=1.")
+                LOGGER.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"
-                "WARNING ⚠️ YOLOWorldv2 models (i.e. 'yolov8s-worldv2.pt') only support export to "
+                "YOLOWorld (original version) export is not supported to any format. "
+                "YOLOWorldv2 models (i.e. 'yolov8s-worldv2.pt') only support export to "
                 "(torchscript, onnx, openvino, engine, coreml) formats. "
                 "See https://docs.ultralytics.com/models/yolo-world for details."
             )
@@ -353,14 +351,13 @@ class Exporter:
         if self.args.int8 and not self.args.data:
             self.args.data = DEFAULT_CFG.data or TASK2DATA[getattr(model, "task", "detect")]  # assign default data
             LOGGER.warning(
-                "WARNING ⚠️ INT8 export requires a missing 'data' arg for calibration. "
-                f"Using default 'data={self.args.data}'."
+                "INT8 export requires a missing 'data' arg for calibration. Using default 'data={self.args.data}'."
             )
         if tfjs and (ARM64 and LINUX):
             raise SystemError("TF.js exports are not currently supported on ARM64 Linux")
 
         # Input
-        im = torch.zeros(self.args.batch, 3, *self.imgsz).to(self.device)
+        im = torch.zeros(self.args.batch, model.yaml.get("channels", 3), *self.imgsz).to(self.device)
         file = Path(
             getattr(model, "pt_path", None) or getattr(model, "yaml_file", None) or model.yaml.get("yaml_file", "")
         )
@@ -436,6 +433,7 @@ class Exporter:
             "imgsz": self.imgsz,
             "names": model.names,
             "args": {k: v for k, v in self.args if k in fmt_keys},
+            "channels": model.yaml.get("channels", 3),
         }  # model metadata
         if dla is not None:
             self.metadata["dla"] = dla  # make sure `AutoBackend` uses correct dla device if it has one
@@ -528,7 +526,7 @@ class Exporter:
                 f"('batch={self.args.batch}')."
             )
         elif n < 300:
-            LOGGER.warning(f"{prefix} WARNING ⚠️ >300 images recommended for INT8 calibration, found {n} images.")
+            LOGGER.warning(f"{prefix} >300 images recommended for INT8 calibration, found {n} images.")
         return build_dataloader(dataset, batch=batch, workers=0)  # required for batch loading
 
     @try_export
@@ -741,7 +739,7 @@ class Exporter:
         pnnx = name if name.is_file() else (ROOT / name)
         if not pnnx.is_file():
             LOGGER.warning(
-                f"{prefix} WARNING ⚠️ PNNX not found. Attempting to download binary file from "
+                f"{prefix} PNNX not found. Attempting to download binary file from "
                 "https://github.com/pnnx/pnnx/.\nNote PNNX Binary file must be placed in current working directory "
                 f"or in {ROOT}. See PNNX repo for full installation instructions."
             )
@@ -754,7 +752,7 @@ class Exporter:
             except Exception as e:
                 release = "20240410"
                 asset = f"pnnx-{release}-{system}.zip"
-                LOGGER.warning(f"{prefix} WARNING ⚠️ PNNX GitHub assets not found: {e}, using default {asset}")
+                LOGGER.warning(f"{prefix} PNNX GitHub assets not found: {e}, using default {asset}")
             unzip_dir = safe_download(f"https://github.com/pnnx/pnnx/releases/download/{release}/{asset}", delete=True)
             if check_is_path_safe(Path.cwd(), unzip_dir):  # avoid path traversal security vulnerability
                 shutil.move(src=unzip_dir / name, dst=pnnx)  # move binary to ROOT
@@ -819,7 +817,7 @@ class Exporter:
             model = IOSDetectModel(self.model, self.im) if self.args.nms else self.model
         else:
             if self.args.nms:
-                LOGGER.warning(f"{prefix} WARNING ⚠️ 'nms=True' is only available for Detect models like 'yolo11n.pt'.")
+                LOGGER.warning(f"{prefix} 'nms=True' is only available for Detect models like 'yolo11n.pt'.")
                 # TODO CoreML Segment and Pose model pipelining
             model = self.model
         ts = torch.jit.trace(model.eval(), self.im, strict=False)  # TorchScript model
@@ -864,7 +862,7 @@ class Exporter:
             ct_model.save(str(f))  # save *.mlpackage
         except Exception as e:
             LOGGER.warning(
-                f"{prefix} WARNING ⚠️ CoreML export to *.mlpackage failed ({e}), reverting to *.mlmodel export. "
+                f"{prefix} CoreML export to *.mlpackage failed ({e}), reverting to *.mlmodel export. "
                 f"Known coremltools Python 3.11 and Windows bugs https://github.com/apple/coremltools/issues/1928."
             )
             f = f.with_suffix(".mlmodel")
@@ -1033,7 +1031,7 @@ class Exporter:
     @try_export
     def export_edgetpu(self, tflite_model="", prefix=colorstr("Edge TPU:")):
         """YOLO Edge TPU export https://coral.ai/docs/edgetpu/models-intro/."""
-        LOGGER.warning(f"{prefix} WARNING ⚠️ Edge TPU known bug https://github.com/ultralytics/ultralytics/issues/1185")
+        LOGGER.warning(f"{prefix} Edge TPU known bug https://github.com/ultralytics/ultralytics/issues/1185")
 
         cmd = "edgetpu_compiler --version"
         help_url = "https://coral.ai/docs/edgetpu/compiler/"
@@ -1094,7 +1092,7 @@ class Exporter:
             subprocess.run(cmd, shell=True)
 
         if " " in f:
-            LOGGER.warning(f"{prefix} WARNING ⚠️ your model may not work correctly with spaces in path '{f}'.")
+            LOGGER.warning(f"{prefix} your model may not work correctly with spaces in path '{f}'.")
 
         # Add metadata
         yaml_save(Path(f) / "metadata.yaml", self.metadata)  # add metadata.yaml

ultralytics/engine/model.py

@@ -21,7 +21,6 @@ from ultralytics.utils import (
     SETTINGS,
     callbacks,
     checks,
-    emojis,
     yaml_load,
 )
 
@@ -528,7 +527,7 @@ class Model(torch.nn.Module):
         """
         if source is None:
             source = ASSETS
-            LOGGER.warning(f"WARNING ⚠️ 'source' is missing. Using 'source={source}'.")
+            LOGGER.warning(f"'source' is missing. Using 'source={source}'.")
 
         is_cli = (ARGV[0].endswith("yolo") or ARGV[0].endswith("ultralytics")) and any(
             x in ARGV for x in ("predict", "track", "mode=predict", "mode=track")
@@ -766,7 +765,7 @@ class Model(torch.nn.Module):
         self._check_is_pytorch_model()
         if hasattr(self.session, "model") and self.session.model.id:  # Ultralytics HUB session with loaded model
             if any(kwargs):
-                LOGGER.warning("WARNING ⚠️ using HUB training arguments, ignoring local training arguments.")
+                LOGGER.warning("using HUB training arguments, ignoring local training arguments.")
             kwargs = self.session.train_args  # overwrite kwargs
 
         checks.check_pip_update_available()
@@ -1082,9 +1081,7 @@ class Model(torch.nn.Module):
         except Exception as e:
             name = self.__class__.__name__
             mode = inspect.stack()[1][3]  # get the function name.
-            raise NotImplementedError(
-                emojis(f"WARNING ⚠️ '{name}' model does not support '{mode}' mode for '{self.task}' task yet.")
-            ) from e
+            raise NotImplementedError(f"'{name}' model does not support '{mode}' mode for '{self.task}' task.") from e
 
     @property
     def task_map(self) -> dict:

ultralytics/engine/predictor.py

@@ -51,7 +51,7 @@ from ultralytics.utils.files import increment_path
 from ultralytics.utils.torch_utils import select_device, smart_inference_mode
 
 STREAM_WARNING = """
-WARNING ⚠️ inference results will accumulate in RAM unless `stream=True` is passed, causing potential out-of-memory
+inference results will accumulate in RAM unless `stream=True` is passed, causing potential out-of-memory
 errors for large sources or long-running streams and videos. See https://docs.ultralytics.com/modes/predict/ for help.
 
 Example:
@@ -151,7 +151,9 @@ class BasePredictor:
         not_tensor = not isinstance(im, torch.Tensor)
         if not_tensor:
             im = np.stack(self.pre_transform(im))
-            im = im[..., ::-1].transpose((0, 3, 1, 2))  # BGR to RGB, BHWC to BCHW, (n, 3, h, w)
+            if im.shape[-1] == 3:
+                im = im[..., ::-1]  # BGR to RGB
+            im = im.transpose((0, 3, 1, 2))  # BHWC to BCHW, (n, 3, h, w)
             im = np.ascontiguousarray(im)  # contiguous
             im = torch.from_numpy(im)
 
@@ -302,7 +304,9 @@ class BasePredictor:
 
             # Warmup model
             if not self.done_warmup:
-                self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz))
+                self.model.warmup(
+                    imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, self.model.ch, *self.imgsz)
+                )
                 self.done_warmup = True
 
             self.seen, self.windows, self.batch = 0, [], None
@@ -361,7 +365,7 @@ class BasePredictor:
             t = tuple(x.t / self.seen * 1e3 for x in profilers)  # speeds per image
             LOGGER.info(
                 f"Speed: %.1fms preprocess, %.1fms inference, %.1fms postprocess per image at shape "
-                f"{(min(self.args.batch, self.seen), 3, *im.shape[2:])}" % t
+                f"{(min(self.args.batch, self.seen), getattr(self.model, 'ch', 3), *im.shape[2:])}" % t
             )
         if self.args.save or self.args.save_txt or self.args.save_crop:
             nl = len(list(self.save_dir.glob("labels/*.txt")))  # number of labels

ultralytics/engine/results.py

@@ -569,9 +569,9 @@ class Results(SimpleClass):
 
         # Plot Classify results
         if pred_probs is not None and show_probs:
-            text = ",\n".join(f"{names[j] if names else j} {pred_probs.data[j]:.2f}" for j in pred_probs.top5)
+            text = "\n".join(f"{names[j] if names else j} {pred_probs.data[j]:.2f}" for j in pred_probs.top5)
             x = round(self.orig_shape[0] * 0.03)
-            annotator.text([x, x], text, txt_color=txt_color)
+            annotator.text([x, x], text, txt_color=txt_color, box_color=(64, 64, 64, 128))  # RGBA box
 
         # Plot Pose results
         if self.keypoints is not None:
@@ -590,7 +590,7 @@ class Results(SimpleClass):
 
         # Save results
         if save:
-            annotator.save(filename)
+            annotator.save(filename or f"results_{Path(self.path).name}")
 
         return annotator.im if pil else annotator.result()
 
@@ -752,10 +752,10 @@ class Results(SimpleClass):
             >>>     result.save_crop(save_dir="path/to/crops", file_name="detection")
         """
         if self.probs is not None:
-            LOGGER.warning("WARNING ⚠️ Classify task do not support `save_crop`.")
+            LOGGER.warning("Classify task do not support `save_crop`.")
             return
         if self.obb is not None:
-            LOGGER.warning("WARNING ⚠️ OBB task do not support `save_crop`.")
+            LOGGER.warning("OBB task do not support `save_crop`.")
             return
         for d in self.boxes:
             save_one_box(
@@ -942,7 +942,7 @@ class Results(SimpleClass):
 
     def tojson(self, normalize=False, decimals=5):
         """Deprecated version of to_json()."""
-        LOGGER.warning("WARNING ⚠️ 'result.tojson()' is deprecated, replace with 'result.to_json()'.")
+        LOGGER.warning("'result.tojson()' is deprecated, replace with 'result.to_json()'.")
         return self.to_json(normalize, decimals)
 
     def to_json(self, normalize=False, decimals=5):
@@ -1005,7 +1005,7 @@ class Results(SimpleClass):
         # Convert results to a list of dictionaries
         data = self.summary(normalize=normalize, decimals=decimals)
         if len(data) == 0:
-            LOGGER.warning("⚠️ No results to save to SQL. Results dict is empty")
+            LOGGER.warning("No results to save to SQL. Results dict is empty.")
             return
 
         # Connect to the SQLite database