ultralytics 8.3.111__tar.gz → 8.3.112__tar.gz

{ultralytics-8.3.111/ultralytics.egg-info → ultralytics-8.3.112}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.111
+Version: 8.3.112
 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-8.3.111 → ultralytics-8.3.112}/tests/test_cli.py

@@ -7,7 +7,7 @@ from PIL import Image
 
 from tests import CUDA_DEVICE_COUNT, CUDA_IS_AVAILABLE
 from ultralytics.cfg import TASK2DATA, TASK2MODEL, TASKS
-from ultralytics.utils import ASSETS, WEIGHTS_DIR, checks
+from ultralytics.utils import ARM64, ASSETS, LINUX, WEIGHTS_DIR, checks
 from ultralytics.utils.torch_utils import TORCH_1_9
 
 # Constants
@@ -64,6 +64,10 @@ def test_rtdetr(task: str = "detect", model: str = "yolov8n-rtdetr.yaml", data:
 
 
 @pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="MobileSAM with CLIP is not supported in Python 3.12")
+@pytest.mark.skipif(
+    checks.IS_PYTHON_3_8 and LINUX and ARM64,
+    reason="MobileSAM with CLIP is not supported in Python 3.8 and aarch64 Linux",
+)
 def test_fastsam(
     task: str = "segment", model: str = WEIGHTS_DIR / "FastSAM-s.pt", data: str = "coco8-seg.yaml"
 ) -> None:

{ultralytics-8.3.111 → ultralytics-8.3.112}/tests/test_integrations.py

@@ -16,7 +16,7 @@ from ultralytics.utils.checks import check_requirements
 
 @pytest.mark.slow
 def test_tensorboard():
-    """Test training with MLflow tracking enabled (see https://mlflow.org/ for details)."""
+    """Test training with TensorBoard logging enabled."""
     SETTINGS["tensorboard"] = True
     YOLO("yolo11n-cls.yaml").train(data="imagenet10", imgsz=32, epochs=3, plots=False, device="cpu")
     SETTINGS["tensorboard"] = False

{ultralytics-8.3.111 → ultralytics-8.3.112}/tests/test_python.py

@@ -18,9 +18,11 @@ from ultralytics import RTDETR, YOLO
 from ultralytics.cfg import MODELS, TASK2DATA, TASKS
 from ultralytics.data.build import load_inference_source
 from ultralytics.utils import (
+    ARM64,
     ASSETS,
     DEFAULT_CFG,
     DEFAULT_CFG_PATH,
+    LINUX,
     LOGGER,
     ONLINE,
     ROOT,
@@ -170,7 +172,7 @@ def test_youtube():
         model.predict("https://youtu.be/G17sBkb38XQ", imgsz=96, save=True)
     # 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}")
+        LOGGER.error(f"YouTube Test Error: {e}")
 
 
 @pytest.mark.skipif(not ONLINE, reason="environment is offline")
@@ -276,7 +278,7 @@ def test_results(model):
         r.to_df(decimals=3)
         r.to_csv()
         r.to_xml()
-        r.plot(pil=True)
+        r.plot(pil=True, save=True, filename=TMP / "results_plot_save.jpg")
         r.plot(conf=True, boxes=True)
         print(r, len(r), r.path)  # print after methods
 
@@ -308,7 +310,8 @@ def test_labels_and_crops():
 @pytest.mark.skipif(not ONLINE, reason="environment is offline")
 def test_data_utils():
     """Test utility functions in ultralytics/data/utils.py, including dataset stats and auto-splitting."""
-    from ultralytics.data.utils import HUBDatasetStats, autosplit
+    from ultralytics.data.split import autosplit
+    from ultralytics.data.utils import HUBDatasetStats
     from ultralytics.utils.downloads import zip_directory
 
     # from ultralytics.utils.files import WorkingDirectory
@@ -577,6 +580,10 @@ def test_model_embeddings():
 
 
 @pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="YOLOWorld with CLIP is not supported in Python 3.12")
+@pytest.mark.skipif(
+    checks.IS_PYTHON_3_8 and LINUX and ARM64,
+    reason="YOLOWorld with CLIP is not supported in Python 3.8 and aarch64 Linux",
+)
 def test_yolo_world():
     """Test YOLO world models with CLIP support."""
     model = YOLO(WEIGHTS_DIR / "yolov8s-world.pt")  # no YOLO11n-world model yet
@@ -609,6 +616,10 @@ def test_yolo_world():
 
 
 @pytest.mark.skipif(checks.IS_PYTHON_3_12 or not TORCH_1_9, reason="YOLOE with CLIP is not supported in Python 3.12")
+@pytest.mark.skipif(
+    checks.IS_PYTHON_3_8 and LINUX and ARM64,
+    reason="YOLOE with CLIP is not supported in Python 3.8 and aarch64 Linux",
+)
 def test_yoloe():
     """Test YOLOE models with MobileClip support."""
     # Predict
@@ -672,3 +683,13 @@ def test_yolov10():
     model.val(data="coco8.yaml", imgsz=32)
     model.predict(imgsz=32, save_txt=True, save_crop=True, augment=True)
     model(SOURCE)
+
+
+def test_multichannel():
+    """Test YOLO model multi-channel training, validation, and prediction functionality."""
+    model = YOLO("yolo11n.pt")
+    model.train(data="coco8-multispectral.yaml", epochs=1, imgsz=32, close_mosaic=1, cache="disk")
+    model.val(data="coco8-multispectral.yaml")
+    im = np.zeros((32, 32, 10), dtype=np.uint8)
+    model.predict(source=im, imgsz=32, save_txt=True, save_crop=True, augment=True)
+    model.export(format="onnx")

{ultralytics-8.3.111 → ultralytics-8.3.112}/tests/test_solutions.py

@@ -164,10 +164,13 @@ def test_solution(name, solution_class, needs_frame_count, video, kwargs):
     if name == "ParkingManager":
         safe_download(url=f"{ASSETS_URL}/{PARKING_AREAS_JSON}", dir=TMP)
         safe_download(url=f"{ASSETS_URL}/{PARKING_MODEL}", dir=TMP)
-    solution = solution_class(**kwargs)
+    elif name == "StreamlitInference":
+        if checks.check_imshow():  # do not merge with elif above
+            solution_class(**kwargs).inference()  # requires interactive GUI environment
+        return
 
-    if name == "StreamlitInference":
-        if checks.check_imshow():  # requires interactive GUI environment
-            solution.inference()
-    else:
-        process_video(solution, str(TMP / video), needs_frame_count)
+    process_video(
+        solution=solution_class(**kwargs),
+        video_path=str(TMP / video),
+        needs_frame_count=needs_frame_count,
+    )

{ultralytics-8.3.111 → ultralytics-8.3.112}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.111"
+__version__ = "8.3.112"
 
 import os
 

{ultralytics-8.3.111 → ultralytics-8.3.112}/ultralytics/cfg/__init__.py

@@ -315,7 +315,7 @@ def get_cfg(cfg: Union[str, Path, Dict, SimpleNamespace] = DEFAULT_CFG_DICT, ove
             cfg[k] = str(cfg[k])
     if cfg.get("name") == "model":  # assign model to 'name' arg
         cfg["name"] = str(cfg.get("model", "")).split(".")[0]
-        LOGGER.warning(f"WARNING ⚠️ 'name=model' automatically updated to 'name={cfg['name']}'.")
+        LOGGER.warning(f"'name=model' automatically updated to 'name={cfg['name']}'.")
 
     # Type and Value checks
     check_cfg(cfg)
@@ -570,9 +570,7 @@ def handle_yolo_hub(args: List[str]) -> None:
             or 'logout'. For 'login', an optional second argument can be the API key.
 
     Examples:
-        ```bash
-        yolo login YOUR_API_KEY
-        ```
+        $ yolo login YOUR_API_KEY
 
     Notes:
         - The function imports the 'hub' module from ultralytics to perform login and logout operations.
@@ -625,10 +623,10 @@ def handle_yolo_settings(args: List[str]) -> None:
                 check_dict_alignment(SETTINGS, new)
                 SETTINGS.update(new)
 
-        print(SETTINGS)  # print the current settings
+        LOGGER.info(SETTINGS)  # print the current settings
         LOGGER.info(f"💡 Learn more about Ultralytics Settings at {url}")
     except Exception as e:
-        LOGGER.warning(f"WARNING ⚠️ settings error: '{e}'. Please see {url} for help.")
+        LOGGER.warning(f"settings error: '{e}'. Please see {url} for help.")
 
 
 def handle_yolo_solutions(args: List[str]) -> None:
@@ -687,7 +685,7 @@ def handle_yolo_solutions(args: List[str]) -> None:
 
     # Get solution name
     if not args:
-        LOGGER.warning("⚠️ No solution name provided. i.e `yolo solutions count`. Defaulting to 'count'.")
+        LOGGER.warning("No solution name provided. i.e `yolo solutions count`. Defaulting to 'count'.")
         args = ["count"]
     if args[0] == "help":
         LOGGER.info(SOLUTIONS_HELP_MSG)
@@ -877,10 +875,10 @@ def entrypoint(debug: str = "") -> None:
     overrides = {}  # basic overrides, i.e. imgsz=320
     for a in merge_equals_args(args):  # merge spaces around '=' sign
         if a.startswith("--"):
-            LOGGER.warning(f"WARNING ⚠️ argument '{a}' does not require leading dashes '--', updating to '{a[2:]}'.")
+            LOGGER.warning(f"argument '{a}' does not require leading dashes '--', updating to '{a[2:]}'.")
             a = a[2:]
         if a.endswith(","):
-            LOGGER.warning(f"WARNING ⚠️ argument '{a}' does not require trailing comma ',', updating to '{a[:-1]}'.")
+            LOGGER.warning(f"argument '{a}' does not require trailing comma ',', updating to '{a[:-1]}'.")
             a = a[:-1]
         if "=" in a:
             try:
@@ -917,7 +915,7 @@ def entrypoint(debug: str = "") -> None:
     mode = overrides.get("mode")
     if mode is None:
         mode = DEFAULT_CFG.mode or "predict"
-        LOGGER.warning(f"WARNING ⚠️ 'mode' argument is missing. Valid modes are {MODES}. Using default 'mode={mode}'.")
+        LOGGER.warning(f"'mode' argument is missing. Valid modes are {MODES}. Using default 'mode={mode}'.")
     elif mode not in MODES:
         raise ValueError(f"Invalid 'mode={mode}'. Valid modes are {MODES}.\n{CLI_HELP_MSG}")
 
@@ -927,7 +925,7 @@ def entrypoint(debug: str = "") -> None:
         if task not in TASKS:
             if task == "track":
                 LOGGER.warning(
-                    "WARNING ⚠️ invalid 'task=track', setting 'task=detect' and 'mode=track'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}."
+                    "invalid 'task=track', setting 'task=detect' and 'mode=track'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}."
                 )
                 task, mode = "detect", "track"
             else:
@@ -939,7 +937,7 @@ def entrypoint(debug: str = "") -> None:
     model = overrides.pop("model", DEFAULT_CFG.model)
     if model is None:
         model = "yolo11n.pt"
-        LOGGER.warning(f"WARNING ⚠️ 'model' argument is missing. Using default 'model={model}'.")
+        LOGGER.warning(f"'model' argument is missing. Using default 'model={model}'.")
     overrides["model"] = model
     stem = Path(model).stem.lower()
     if "rtdetr" in stem:  # guess architecture
@@ -965,7 +963,7 @@ def entrypoint(debug: str = "") -> None:
     if task != model.task:
         if task:
             LOGGER.warning(
-                f"WARNING ⚠️ conflicting 'task={task}' passed with 'task={model.task}' model. "
+                f"conflicting 'task={task}' passed with 'task={model.task}' model. "
                 f"Ignoring 'task={task}' and updating to 'task={model.task}' to match model."
             )
         task = model.task
@@ -975,15 +973,15 @@ def entrypoint(debug: str = "") -> None:
         overrides["source"] = (
             "https://ultralytics.com/images/boats.jpg" if task == "obb" else DEFAULT_CFG.source or ASSETS
         )
-        LOGGER.warning(f"WARNING ⚠️ 'source' argument is missing. Using default 'source={overrides['source']}'.")
+        LOGGER.warning(f"'source' argument is missing. Using default 'source={overrides['source']}'.")
     elif mode in {"train", "val"}:
         if "data" not in overrides and "resume" not in overrides:
             overrides["data"] = DEFAULT_CFG.data or TASK2DATA.get(task or DEFAULT_CFG.task, DEFAULT_CFG.data)
-            LOGGER.warning(f"WARNING ⚠️ 'data' argument is missing. Using default 'data={overrides['data']}'.")
+            LOGGER.warning(f"'data' argument is missing. Using default 'data={overrides['data']}'.")
     elif mode == "export":
         if "format" not in overrides:
             overrides["format"] = DEFAULT_CFG.format or "torchscript"
-            LOGGER.warning(f"WARNING ⚠️ 'format' argument is missing. Using default 'format={overrides['format']}'.")
+            LOGGER.warning(f"'format' argument is missing. Using default 'format={overrides['format']}'.")
 
     # Run command in python
     getattr(model, mode)(**overrides)  # default args from model

ultralytics-8.3.112/ultralytics/cfg/datasets/coco8-multispectral.yaml

@@ -0,0 +1,104 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# COCO8-Multispectral dataset (COCO8 images interpolated across 10 channels in the visual spectrum) by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/coco8-multispectral/
+# Example usage: yolo train data=coco8-multispectral.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco8-multispectral  ← downloads here (20.2 MB)
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/coco8-multispectral # dataset root dir
+train: images/train # train images (relative to 'path') 4 images
+val: images/val # val images (relative to 'path') 4 images
+test: # test images (optional)
+
+# Number of multispectral image channels
+channels: 10
+
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-multispectral.zip

{ultralytics-8.3.111 → ultralytics-8.3.112}/ultralytics/data/augment.py

@@ -1364,8 +1364,10 @@ class RandomHSV:
             >>> hsv_augmenter(labels)
             >>> augmented_img = labels["img"]
         """
+        img = labels["img"]
+        if img.shape[-1] != 3:  # only apply to RGB images
+            return labels
         if self.hgain or self.sgain or self.vgain:
-            img = labels["img"]
             dtype = img.dtype  # uint8
 
             r = np.random.uniform(-1, 1, 3) * [self.hgain, self.sgain, self.vgain]  # random gains
@@ -1588,9 +1590,14 @@ class LetterBox:
             img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
         top, bottom = int(round(dh - 0.1)) if self.center else 0, int(round(dh + 0.1))
         left, right = int(round(dw - 0.1)) if self.center else 0, int(round(dw + 0.1))
-        img = cv2.copyMakeBorder(
-            img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114)
-        )  # add border
+        h, w, c = img.shape
+        if c == 3:
+            img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114))
+        else:  # multispectral
+            pad_img = np.full((h + top + bottom, w + left + right, c), fill_value=114, dtype=img.dtype)
+            pad_img[top : top + h, left : left + w] = img
+            img = pad_img
+
         if labels.get("ratio_pad"):
             labels["ratio_pad"] = (labels["ratio_pad"], (left, top))  # for evaluation
 
@@ -1908,10 +1915,13 @@ class Albumentations:
         if self.transform is None or random.random() > self.p:
             return labels
 
+        im = labels["img"]
+        if im.shape[2] != 3:  # Only apply Albumentation on 3-channel images
+            return labels
+
         if self.contains_spatial:
             cls = labels["cls"]
             if len(cls):
-                im = labels["img"]
                 labels["instances"].convert_bbox("xywh")
                 labels["instances"].normalize(*im.shape[:2][::-1])
                 bboxes = labels["instances"].bboxes
@@ -2426,7 +2436,7 @@ def v8_transforms(dataset, imgsz, hyp, stretch=False):
         kpt_shape = dataset.data.get("kpt_shape", None)
         if len(flip_idx) == 0 and hyp.fliplr > 0.0:
             hyp.fliplr = 0.0
-            LOGGER.warning("WARNING ⚠️ No 'flip_idx' array defined in data.yaml, setting augmentation 'fliplr=0.0'")
+            LOGGER.warning("No 'flip_idx' array defined in data.yaml, setting augmentation 'fliplr=0.0'")
         elif flip_idx and (len(flip_idx) != kpt_shape[0]):
             raise ValueError(f"data.yaml flip_idx={flip_idx} length must be equal to kpt_shape[0]={kpt_shape[0]}")
 

{ultralytics-8.3.111 → ultralytics-8.3.112}/ultralytics/data/base.py

@@ -15,7 +15,7 @@ import psutil
 from torch.utils.data import Dataset
 
 from ultralytics.data.utils import FORMATS_HELP_MSG, HELP_URL, IMG_FORMATS, check_file_speeds
-from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM
+from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM, imread
 
 
 class BaseDataset(Dataset):
@@ -127,7 +127,7 @@ class BaseDataset(Dataset):
         if self.cache == "ram" and self.check_cache_ram():
             if hyp.deterministic:
                 LOGGER.warning(
-                    "WARNING ⚠️ cache='ram' may produce non-deterministic training results. "
+                    "cache='ram' may produce non-deterministic training results. "
                     "Consider cache='disk' as a deterministic alternative if your disk space allows."
                 )
             self.cache_images()
@@ -221,11 +221,11 @@ class BaseDataset(Dataset):
                 try:
                     im = np.load(fn)
                 except Exception as e:
-                    LOGGER.warning(f"{self.prefix}WARNING ⚠️ Removing corrupt *.npy image file {fn} due to: {e}")
+                    LOGGER.warning(f"{self.prefix}Removing corrupt *.npy image file {fn} due to: {e}")
                     Path(fn).unlink(missing_ok=True)
-                    im = cv2.imread(f)  # BGR
+                    im = imread(f)  # BGR
             else:  # read image
-                im = cv2.imread(f)  # BGR
+                im = imread(f)  # BGR
             if im is None:
                 raise FileNotFoundError(f"Image Not Found {f}")
 
@@ -271,7 +271,7 @@ class BaseDataset(Dataset):
         """Save an image as an *.npy file for faster loading."""
         f = self.npy_files[i]
         if not f.exists():
-            np.save(f.as_posix(), cv2.imread(self.im_files[i]), allow_pickle=False)
+            np.save(f.as_posix(), imread(self.im_files[i]), allow_pickle=False)
 
     def check_cache_disk(self, safety_margin=0.5):
         """
@@ -289,22 +289,22 @@ class BaseDataset(Dataset):
         n = min(self.ni, 30)  # extrapolate from 30 random images
         for _ in range(n):
             im_file = random.choice(self.im_files)
-            im = cv2.imread(im_file)
+            im = imread(im_file)
             if im is None:
                 continue
             b += im.nbytes
             if not os.access(Path(im_file).parent, os.W_OK):
                 self.cache = None
-                LOGGER.info(f"{self.prefix}Skipping caching images to disk, directory not writeable ⚠️")
+                LOGGER.warning(f"{self.prefix}Skipping caching images to disk, directory not writeable")
                 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)
         if disk_required > free:
             self.cache = None
-            LOGGER.info(
+            LOGGER.warning(
                 f"{self.prefix}{disk_required / gb:.1f}GB disk space required, "
                 f"with {int(safety_margin * 100)}% safety margin but only "
-                f"{free / gb:.1f}/{total / gb:.1f}GB free, not caching images to disk ⚠️"
+                f"{free / gb:.1f}/{total / gb:.1f}GB free, not caching images to disk"
             )
             return False
         return True
@@ -322,7 +322,7 @@ class BaseDataset(Dataset):
         b, gb = 0, 1 << 30  # bytes of cached images, bytes per gigabytes
         n = min(self.ni, 30)  # extrapolate from 30 random images
         for _ in range(n):
-            im = cv2.imread(random.choice(self.im_files))  # sample image
+            im = imread(random.choice(self.im_files))  # sample image
             if im is None:
                 continue
             ratio = self.imgsz / max(im.shape[0], im.shape[1])  # max(h, w)  # ratio
@@ -331,10 +331,10 @@ class BaseDataset(Dataset):
         mem = psutil.virtual_memory()
         if mem_required > mem.available:
             self.cache = None
-            LOGGER.info(
+            LOGGER.warning(
                 f"{self.prefix}{mem_required / gb:.1f}GB RAM required to cache images "
                 f"with {int(safety_margin * 100)}% safety margin but only "
-                f"{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, not caching images ⚠️"
+                f"{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, not caching images"
             )
             return False
         return True
@@ -415,19 +415,17 @@ class BaseDataset(Dataset):
         """
         Users can customize their own format here.
 
-        Note:
+        Examples:
             Ensure output is a dictionary with the following keys:
-            ```python
-            dict(
-                im_file=im_file,
-                shape=shape,  # format: (height, width)
-                cls=cls,
-                bboxes=bboxes,  # xywh
-                segments=segments,  # xy
-                keypoints=keypoints,  # xy
-                normalized=True,  # or False
-                bbox_format="xyxy",  # or xywh, ltwh
-            )
-            ```
+            >>> dict(
+            ...     im_file=im_file,
+            ...     shape=shape,  # format: (height, width)
+            ...     cls=cls,
+            ...     bboxes=bboxes,  # xywh
+            ...     segments=segments,  # xy
+            ...     keypoints=keypoints,  # xy
+            ...     normalized=True,  # or False
+            ...     bbox_format="xyxy",  # or xywh, ltwh
+            ... )
         """
         raise NotImplementedError

{ultralytics-8.3.111 → ultralytics-8.3.112}/ultralytics/data/converter.py

@@ -12,7 +12,7 @@ import numpy as np
 from PIL import Image
 
 from ultralytics.utils import DATASETS_DIR, LOGGER, NUM_THREADS, TQDM
-from ultralytics.utils.downloads import download
+from ultralytics.utils.downloads import download, zip_directory
 from ultralytics.utils.files import increment_path
 
 
@@ -698,6 +698,55 @@ def create_synthetic_coco_dataset():
                 for _ in TQDM(as_completed(futures), total=len(futures), desc=f"Generating images for {subset}"):
                     pass  # The actual work is done in the background
             else:
-                print(f"Warning: Labels file {label_list_file} does not exist. Skipping image creation for {subset}.")
+                LOGGER.warning(f"Labels file {label_list_file} does not exist. Skipping image creation for {subset}.")
 
-    print("Synthetic COCO dataset created successfully.")
+    LOGGER.info("Synthetic COCO dataset created successfully.")
+
+
+def convert_to_multispectral(path, n_channels=10, replace=False, zip=False):
+    """
+    Convert RGB images to multispectral images by interpolating across wavelength bands.
+
+    This function takes RGB images and interpolates them to create multispectral images with a specified number
+    of channels. It can process either a single image or a directory of images.
+
+    Args:
+        path (str | Path): Path to an image file or directory containing images to convert.
+        n_channels (int): Number of spectral channels to generate in the output image.
+        replace (bool): Whether to replace the original image file with the converted one.
+        zip (bool): Whether to zip the converted images into a zip file.
+
+    Examples:
+        >>> # Convert a single image
+        >>> convert_to_multispectral("path/to/image.jpg", n_channels=12)
+    """
+    from scipy.interpolate import interp1d
+
+    from ultralytics.data.utils import IMG_FORMATS
+
+    path = Path(path)
+    if path.is_dir():
+        # Process directory
+        im_files = sum([list(path.rglob(f"*.{ext}")) for ext in (IMG_FORMATS - {"tif", "tiff"})], [])
+        for im_path in im_files:
+            try:
+                convert_to_multispectral(im_path, n_channels)
+                if replace:
+                    im_path.unlink()
+            except Exception as e:
+                LOGGER.info(f"Error converting {im_path}: {e}")
+
+        if zip:
+            zip_directory(path)
+    else:
+        # Process a single image
+        output_path = path.with_suffix(".tiff")
+        img = cv2.cvtColor(cv2.imread(str(path)), cv2.COLOR_BGR2RGB)
+
+        # Interpolate all pixels at once
+        rgb_wavelengths = np.array([650, 510, 475])  # R, G, B wavelengths (nm)
+        target_wavelengths = np.linspace(450, 700, n_channels)
+        f = interp1d(rgb_wavelengths.T, img, kind="linear", bounds_error=False, fill_value="extrapolate")
+        multispectral = f(target_wavelengths)
+        cv2.imwritemulti(str(output_path), np.clip(multispectral, 0, 255).astype(np.uint8).transpose(2, 0, 1))
+        LOGGER.info(f"Converted {output_path}")

{ultralytics-8.3.111 → ultralytics-8.3.112}/ultralytics/data/dataset.py

@@ -148,7 +148,7 @@ class YOLODataset(BaseDataset):
         if msgs:
             LOGGER.info("\n".join(msgs))
         if nf == 0:
-            LOGGER.warning(f"{self.prefix}WARNING ⚠️ No labels found in {path}. {HELP_URL}")
+            LOGGER.warning(f"{self.prefix}No labels found in {path}. {HELP_URL}")
         x["hash"] = get_hash(self.label_files + self.im_files)
         x["results"] = nf, nm, ne, nc, len(self.im_files)
         x["msgs"] = msgs  # warnings
@@ -185,7 +185,7 @@ class YOLODataset(BaseDataset):
         [cache.pop(k) for k in ("hash", "version", "msgs")]  # remove items
         labels = cache["labels"]
         if not labels:
-            LOGGER.warning(f"WARNING ⚠️ No images found in {cache_path}, training may not work correctly. {HELP_URL}")
+            LOGGER.warning(f"No images found in {cache_path}, training may not work correctly. {HELP_URL}")
         self.im_files = [lb["im_file"] for lb in labels]  # update im_files
 
         # Check if the dataset is all boxes or all segments
@@ -193,14 +193,14 @@ class YOLODataset(BaseDataset):
         len_cls, len_boxes, len_segments = (sum(x) for x in zip(*lengths))
         if len_segments and len_boxes != len_segments:
             LOGGER.warning(
-                f"WARNING ⚠️ Box and segment counts should be equal, but got len(segments) = {len_segments}, "
+                f"Box and segment counts should be equal, but got len(segments) = {len_segments}, "
                 f"len(boxes) = {len_boxes}. To resolve this only boxes will be used and all segments will be removed. "
                 "To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset."
             )
             for lb in labels:
                 lb["segments"] = []
         if len_cls == 0:
-            LOGGER.warning(f"WARNING ⚠️ No labels found in {cache_path}, training may not work correctly. {HELP_URL}")
+            LOGGER.warning(f"No labels found in {cache_path}, training may not work correctly. {HELP_URL}")
         return labels
 
     def build_transforms(self, hyp=None):
@@ -731,7 +731,7 @@ class ClassificationDataset:
         self.cache_ram = args.cache is True or str(args.cache).lower() == "ram"  # cache images into RAM
         if self.cache_ram:
             LOGGER.warning(
-                "WARNING ⚠️ Classification `cache_ram` training has known memory leak in "
+                "Classification `cache_ram` training has known memory leak in "
                 "https://github.com/ultralytics/ultralytics/issues/9824, setting `cache_ram=False`."
             )
             self.cache_ram = False