dgenerate-ultralytics-headless 8.3.137__py3-none-any.whl → 8.3.224__py3-none-any.whl

ultralytics/cfg/__init__.py

@@ -1,11 +1,13 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 import shutil
 import subprocess
 import sys
 from pathlib import Path
 from types import SimpleNamespace
-from typing import Any, Dict, List, Union
+from typing import Any
 
 from ultralytics import __version__
 from ultralytics.utils import (
@@ -13,6 +15,7 @@ from ultralytics.utils import (
     DEFAULT_CFG,
     DEFAULT_CFG_DICT,
     DEFAULT_CFG_PATH,
+    FLOAT_OR_INT,
     IS_VSCODE,
     LOGGER,
     RANK,
@@ -20,6 +23,7 @@ from ultralytics.utils import (
     RUNS_DIR,
     SETTINGS,
     SETTINGS_FILE,
+    STR_OR_PATH,
     TESTS_RUNNING,
     YAML,
     IterableSimpleNamespace,
@@ -70,18 +74,17 @@ TASK2METRIC = {
     "pose": "metrics/mAP50-95(P)",
     "obb": "metrics/mAP50-95(B)",
 }
-MODELS = frozenset({TASK2MODEL[task] for task in TASKS})
 
 ARGV = sys.argv or ["", ""]  # sometimes sys.argv = []
 SOLUTIONS_HELP_MSG = f"""
-    Arguments received: {str(["yolo"] + ARGV[1:])}. Ultralytics 'yolo solutions' usage overview:
+    Arguments received: {["yolo", *ARGV[1:]]!s}. Ultralytics 'yolo solutions' usage overview:
 
         yolo solutions SOLUTION ARGS
 
         Where SOLUTION (optional) is one of {list(SOLUTION_MAP.keys())[:-1]}
-              ARGS (optional) are any number of custom 'arg=value' pairs like 'show_in=True' that override defaults 
+              ARGS (optional) are any number of custom 'arg=value' pairs like 'show_in=True' that override defaults
                   at https://docs.ultralytics.com/usage/cfg
-                
+
     1. Call object counting solution
         yolo solutions count source="path/to/video.mp4" region="[(20, 400), (1080, 400), (1080, 360), (20, 360)]"
 
@@ -96,20 +99,20 @@ SOLUTIONS_HELP_MSG = f"""
 
     5. Generate analytical graphs
         yolo solutions analytics analytics_type="pie"
-    
+
     6. Track objects within specific zones
         yolo solutions trackzone source="path/to/video.mp4" region="[(150, 150), (1130, 150), (1130, 570), (150, 570)]"
-        
+
     7. Streamlit real-time webcam inference GUI
         yolo streamlit-predict
     """
 CLI_HELP_MSG = f"""
-    Arguments received: {str(["yolo"] + ARGV[1:])}. Ultralytics 'yolo' commands use the following syntax:
+    Arguments received: {["yolo", *ARGV[1:]]!s}. Ultralytics 'yolo' commands use the following syntax:
 
         yolo TASK MODE ARGS
 
-        Where   TASK (optional) is one of {TASKS}
-                MODE (required) is one of {MODES}
+        Where   TASK (optional) is one of {list(TASKS)}
+                MODE (required) is one of {list(MODES)}
                 ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults.
                     See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg'
 
@@ -238,13 +241,12 @@ CFG_BOOL_KEYS = frozenset(
 )
 
 
-def cfg2dict(cfg: Union[str, Path, Dict, SimpleNamespace]) -> Dict:
-    """
-    Converts a configuration object to a dictionary.
+def cfg2dict(cfg: str | Path | dict | SimpleNamespace) -> dict:
+    """Convert a configuration object to a dictionary.
 
     Args:
-        cfg (str | Path | Dict | SimpleNamespace): Configuration object to be converted. Can be a file path,
-            a string, a dictionary, or a SimpleNamespace object.
+        cfg (str | Path | dict | SimpleNamespace): Configuration object to be converted. Can be a file path, a string, a
+            dictionary, or a SimpleNamespace object.
 
     Returns:
         (dict): Configuration object in dictionary format.
@@ -266,21 +268,22 @@ def cfg2dict(cfg: Union[str, Path, Dict, SimpleNamespace]) -> Dict:
         - If cfg is a SimpleNamespace object, it's converted to a dictionary using vars().
         - If cfg is already a dictionary, it's returned unchanged.
     """
-    if isinstance(cfg, (str, Path)):
+    if isinstance(cfg, STR_OR_PATH):
         cfg = YAML.load(cfg)  # load dict
     elif isinstance(cfg, SimpleNamespace):
         cfg = vars(cfg)  # convert to dict
     return cfg
 
 
-def get_cfg(cfg: Union[str, Path, Dict, SimpleNamespace] = DEFAULT_CFG_DICT, overrides: Dict = None) -> SimpleNamespace:
-    """
-    Load and merge configuration data from a file or dictionary, with optional overrides.
+def get_cfg(
+    cfg: str | Path | dict | SimpleNamespace = DEFAULT_CFG_DICT, overrides: dict | None = None
+) -> SimpleNamespace:
+    """Load and merge configuration data from a file or dictionary, with optional overrides.
 
     Args:
-        cfg (str | Path | Dict | SimpleNamespace): Configuration data source. Can be a file path, dictionary, or
+        cfg (str | Path | dict | SimpleNamespace): Configuration data source. Can be a file path, dictionary, or
             SimpleNamespace object.
-        overrides (Dict | None): Dictionary containing key-value pairs to override the base configuration.
+        overrides (dict | None): Dictionary containing key-value pairs to override the base configuration.
 
     Returns:
         (SimpleNamespace): Namespace containing the merged configuration arguments.
@@ -308,10 +311,10 @@ def get_cfg(cfg: Union[str, Path, Dict, SimpleNamespace] = DEFAULT_CFG_DICT, ove
 
     # Special handling for numeric project/name
     for k in "project", "name":
-        if k in cfg and isinstance(cfg[k], (int, float)):
+        if k in cfg and isinstance(cfg[k], FLOAT_OR_INT):
             cfg[k] = str(cfg[k])
     if cfg.get("name") == "model":  # assign model to 'name' arg
-        cfg["name"] = str(cfg.get("model", "")).split(".")[0]
+        cfg["name"] = str(cfg.get("model", "")).partition(".")[0]
         LOGGER.warning(f"'name=model' automatically updated to 'name={cfg['name']}'.")
 
     # Type and Value checks
@@ -321,12 +324,11 @@ def get_cfg(cfg: Union[str, Path, Dict, SimpleNamespace] = DEFAULT_CFG_DICT, ove
     return IterableSimpleNamespace(**cfg)
 
 
-def check_cfg(cfg: Dict, hard: bool = True) -> None:
-    """
-    Checks configuration argument types and values for the Ultralytics library.
+def check_cfg(cfg: dict, hard: bool = True) -> None:
+    """Check configuration argument types and values for the Ultralytics library.
 
-    This function validates the types and values of configuration arguments, ensuring correctness and converting
-    them if necessary. It checks for specific key types defined in global variables such as `CFG_FLOAT_KEYS`,
+    This function validates the types and values of configuration arguments, ensuring correctness and converting them if
+    necessary. It checks for specific key types defined in global variables such as `CFG_FLOAT_KEYS`,
     `CFG_FRACTION_KEYS`, `CFG_INT_KEYS`, and `CFG_BOOL_KEYS`.
 
     Args:
@@ -351,7 +353,7 @@ def check_cfg(cfg: Dict, hard: bool = True) -> None:
     """
     for k, v in cfg.items():
         if v is not None:  # None values may be from optional args
-            if k in CFG_FLOAT_KEYS and not isinstance(v, (int, float)):
+            if k in CFG_FLOAT_KEYS and not isinstance(v, FLOAT_OR_INT):
                 if hard:
                     raise TypeError(
                         f"'{k}={v}' is of invalid type {type(v).__name__}. "
@@ -359,7 +361,7 @@ def check_cfg(cfg: Dict, hard: bool = True) -> None:
                     )
                 cfg[k] = float(v)
             elif k in CFG_FRACTION_KEYS:
-                if not isinstance(v, (int, float)):
+                if not isinstance(v, FLOAT_OR_INT):
                     if hard:
                         raise TypeError(
                             f"'{k}={v}' is of invalid type {type(v).__name__}. "
@@ -383,15 +385,14 @@ def check_cfg(cfg: Dict, hard: bool = True) -> None:
                 cfg[k] = bool(v)
 
 
-def get_save_dir(args: SimpleNamespace, name: str = None) -> Path:
-    """
-    Returns the directory path for saving outputs, derived from arguments or default settings.
+def get_save_dir(args: SimpleNamespace, name: str | None = None) -> Path:
+    """Return the directory path for saving outputs, derived from arguments or default settings.
 
     Args:
-        args (SimpleNamespace): Namespace object containing configurations such as 'project', 'name', 'task',
-            'mode', and 'save_dir'.
-        name (str | None): Optional name for the output directory. If not provided, it defaults to 'args.name'
-            or the 'args.mode'.
+        args (SimpleNamespace): Namespace object containing configurations such as 'project', 'name', 'task', 'mode',
+            and 'save_dir'.
+        name (str | None): Optional name for the output directory. If not provided, it defaults to 'args.name' or the
+            'args.mode'.
 
     Returns:
         (Path): Directory path where outputs should be saved.
@@ -412,16 +413,18 @@ def get_save_dir(args: SimpleNamespace, name: str = None) -> Path:
         name = name or args.name or f"{args.mode}"
         save_dir = increment_path(Path(project) / name, exist_ok=args.exist_ok if RANK in {-1, 0} else True)
 
-    return Path(save_dir)
+    return Path(save_dir).resolve()  # resolve to display full path in console
 
 
-def _handle_deprecation(custom: Dict) -> Dict:
-    """
-    Handles deprecated configuration keys by mapping them to current equivalents with deprecation warnings.
+def _handle_deprecation(custom: dict) -> dict:
+    """Handle deprecated configuration keys by mapping them to current equivalents with deprecation warnings.
 
     Args:
         custom (dict): Configuration dictionary potentially containing deprecated keys.
 
+    Returns:
+        (dict): Updated configuration dictionary with deprecated keys replaced.
+
     Examples:
         >>> custom_config = {"boxes": True, "hide_labels": "False", "line_thickness": 2}
         >>> _handle_deprecation(custom_config)
@@ -456,9 +459,8 @@ def _handle_deprecation(custom: Dict) -> Dict:
     return custom
 
 
-def check_dict_alignment(base: Dict, custom: Dict, e: Exception = None) -> None:
-    """
-    Checks alignment between custom and base configuration dictionaries, handling deprecated keys and providing error
+def check_dict_alignment(base: dict, custom: dict, e: Exception | None = None) -> None:
+    """Check alignment between custom and base configuration dictionaries, handling deprecated keys and providing error
     messages for mismatched keys.
 
     Args:
@@ -496,9 +498,8 @@ def check_dict_alignment(base: Dict, custom: Dict, e: Exception = None) -> None:
         raise SyntaxError(string + CLI_HELP_MSG) from e
 
 
-def merge_equals_args(args: List[str]) -> List[str]:
-    """
-    Merges arguments around isolated '=' in a list of strings and joins fragments with brackets.
+def merge_equals_args(args: list[str]) -> list[str]:
+    """Merge arguments around isolated '=' in a list of strings and join fragments with brackets.
 
     This function handles the following cases:
         1. ['arg', '=', 'val'] becomes ['arg=val']
@@ -507,10 +508,11 @@ def merge_equals_args(args: List[str]) -> List[str]:
         4. Joins fragments with brackets, e.g., ['imgsz=[3,', '640,', '640]'] becomes ['imgsz=[3,640,640]']
 
     Args:
-        args (List[str]): A list of strings where each element represents an argument or fragment.
+        args (list[str]): A list of strings where each element represents an argument or fragment.
 
     Returns:
-        (List[str]): A list of strings where the arguments around isolated '=' are merged and fragments with brackets are joined.
+        (list[str]): A list of strings where the arguments around isolated '=' are merged and fragments with brackets
+            are joined.
 
     Examples:
         >>> args = ["arg1", "=", "value", "arg2=", "value2", "arg3", "=value3", "imgsz=[3,", "640,", "640]"]
@@ -555,16 +557,15 @@ def merge_equals_args(args: List[str]) -> List[str]:
     return new_args
 
 
-def handle_yolo_hub(args: List[str]) -> None:
-    """
-    Handles Ultralytics HUB command-line interface (CLI) commands for authentication.
+def handle_yolo_hub(args: list[str]) -> None:
+    """Handle Ultralytics HUB command-line interface (CLI) commands for authentication.
 
     This function processes Ultralytics HUB CLI commands such as login and logout. It should be called when executing a
     script with arguments related to HUB authentication.
 
     Args:
-        args (List[str]): A list of command line arguments. The first argument should be either 'login'
-            or 'logout'. For 'login', an optional second argument can be the API key.
+        args (list[str]): A list of command line arguments. The first argument should be either 'login' or 'logout'. For
+            'login', an optional second argument can be the API key.
 
     Examples:
         $ yolo login YOUR_API_KEY
@@ -585,15 +586,14 @@ def handle_yolo_hub(args: List[str]) -> None:
         hub.logout()
 
 
-def handle_yolo_settings(args: List[str]) -> None:
-    """
-    Handles YOLO settings command-line interface (CLI) commands.
+def handle_yolo_settings(args: list[str]) -> None:
+    """Handle YOLO settings command-line interface (CLI) commands.
 
     This function processes YOLO settings CLI commands such as reset and updating individual settings. It should be
     called when executing a script with arguments related to YOLO settings management.
 
     Args:
-        args (List[str]): A list of command line arguments for YOLO settings management.
+        args (list[str]): A list of command line arguments for YOLO settings management.
 
     Examples:
         >>> handle_yolo_settings(["reset"])  # Reset YOLO settings
@@ -619,6 +619,8 @@ def handle_yolo_settings(args: List[str]) -> None:
                 new = dict(parse_key_value_pair(a) for a in args)
                 check_dict_alignment(SETTINGS, new)
                 SETTINGS.update(new)
+                for k, v in new.items():
+                    LOGGER.info(f"✅ Updated '{k}={v}'")
 
         LOGGER.info(SETTINGS)  # print the current settings
         LOGGER.info(f"💡 Learn more about Ultralytics Settings at {url}")
@@ -626,14 +628,11 @@ def handle_yolo_settings(args: List[str]) -> None:
         LOGGER.warning(f"settings error: '{e}'. Please see {url} for help.")
 
 
-def handle_yolo_solutions(args: List[str]) -> None:
-    """
-    Processes YOLO solutions arguments and runs the specified computer vision solutions pipeline.
+def handle_yolo_solutions(args: list[str]) -> None:
+    """Process YOLO solutions arguments and run the specified computer vision solutions pipeline.
 
     Args:
-        args (List[str]): Command-line arguments for configuring and running the Ultralytics YOLO
-            solutions: https://docs.ultralytics.com/solutions/, It can include solution name, source,
-            and other configuration parameters.
+        args (list[str]): Command-line arguments for configuring and running the Ultralytics YOLO solutions.
 
     Examples:
         Run people counting solution with default settings:
@@ -739,8 +738,7 @@ def handle_yolo_solutions(args: List[str]) -> None:
 
 
 def parse_key_value_pair(pair: str = "key=value") -> tuple:
-    """
-    Parses a key-value pair string into separate key and value components.
+    """Parse a key-value pair string into separate key and value components.
 
     Args:
         pair (str): A string containing a key-value pair in the format "key=value".
@@ -773,8 +771,7 @@ def parse_key_value_pair(pair: str = "key=value") -> tuple:
 
 
 def smart_value(v: str) -> Any:
-    """
-    Converts a string representation of a value to its appropriate Python type.
+    """Convert a string representation of a value to its appropriate Python type.
 
     This function attempts to convert a given string into a Python object of the most appropriate type. It handles
     conversions to None, bool, int, float, and other types that can be evaluated safely.
@@ -783,8 +780,8 @@ def smart_value(v: str) -> Any:
         v (str): The string representation of the value to be converted.
 
     Returns:
-        (Any): The converted value. The type can be None, bool, int, float, or the original string if no conversion
-            is applicable.
+        (Any): The converted value. The type can be None, bool, int, float, or the original string if no conversion is
+            applicable.
 
     Examples:
         >>> smart_value("42")
@@ -818,11 +815,10 @@ def smart_value(v: str) -> Any:
 
 
 def entrypoint(debug: str = "") -> None:
-    """
-    Ultralytics entrypoint function for parsing and executing command-line arguments.
+    """Ultralytics entrypoint function for parsing and executing command-line arguments.
 
-    This function serves as the main entry point for the Ultralytics CLI, parsing command-line arguments and
-    executing the corresponding tasks such as training, validation, prediction, exporting models, and more.
+    This function serves as the main entry point for the Ultralytics CLI, parsing command-line arguments and executing
+    the corresponding tasks such as training, validation, prediction, exporting models, and more.
 
     Args:
         debug (str): Space-separated string of command-line arguments for debugging purposes.
@@ -848,7 +844,6 @@ def entrypoint(debug: str = "") -> None:
         return
 
     special = {
-        "help": lambda: LOGGER.info(CLI_HELP_MSG),
         "checks": checks.collect_system_info,
         "version": lambda: LOGGER.info(__version__),
         "settings": lambda: handle_yolo_settings(args[1:]),
@@ -858,6 +853,7 @@ def entrypoint(debug: str = "") -> None:
         "logout": lambda: handle_yolo_hub(args),
         "copy-cfg": copy_default_cfg,
         "solutions": lambda: handle_yolo_solutions(args[1:]),
+        "help": lambda: LOGGER.info(CLI_HELP_MSG),  # help below hub for -h flag precedence
     }
     full_args_dict = {**DEFAULT_CFG_DICT, **{k: None for k in TASKS}, **{k: None for k in MODES}, **special}
 
@@ -909,9 +905,9 @@ def entrypoint(debug: str = "") -> None:
     mode = overrides.get("mode")
     if mode is None:
         mode = DEFAULT_CFG.mode or "predict"
-        LOGGER.warning(f"'mode' argument is missing. Valid modes are {MODES}. Using default 'mode={mode}'.")
+        LOGGER.warning(f"'mode' argument is missing. Valid modes are {list(MODES)}. Using default 'mode={mode}'.")
     elif mode not in MODES:
-        raise ValueError(f"Invalid 'mode={mode}'. Valid modes are {MODES}.\n{CLI_HELP_MSG}")
+        raise ValueError(f"Invalid 'mode={mode}'. Valid modes are {list(MODES)}.\n{CLI_HELP_MSG}")
 
     # Task
     task = overrides.pop("task", None)
@@ -919,11 +915,11 @@ def entrypoint(debug: str = "") -> None:
         if task not in TASKS:
             if task == "track":
                 LOGGER.warning(
-                    f"invalid 'task=track', setting 'task=detect' and 'mode=track'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}."
+                    f"invalid 'task=track', setting 'task=detect' and 'mode=track'. Valid tasks are {list(TASKS)}.\n{CLI_HELP_MSG}."
                 )
                 task, mode = "detect", "track"
             else:
-                raise ValueError(f"Invalid 'task={task}'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}")
+                raise ValueError(f"Invalid 'task={task}'. Valid tasks are {list(TASKS)}.\n{CLI_HELP_MSG}")
         if "model" not in overrides:
             overrides["model"] = TASK2MODEL[task]
 
@@ -950,9 +946,10 @@ def entrypoint(debug: str = "") -> None:
         from ultralytics import YOLO
 
         model = YOLO(model, task=task)
-    if isinstance(overrides.get("pretrained"), str):
-        model.load(overrides["pretrained"])
-
+        if "yoloe" in stem or "world" in stem:
+            cls_list = overrides.pop("classes", DEFAULT_CFG.classes)
+            if cls_list is not None and isinstance(cls_list, str):
+                model.set_classes(cls_list.split(","))  # convert "person, bus" -> ['person', ' bus'].
     # Task Update
     if task != model.task:
         if task:
@@ -990,12 +987,11 @@ def entrypoint(debug: str = "") -> None:
 
 # Special modes --------------------------------------------------------------------------------------------------------
 def copy_default_cfg() -> None:
-    """
-    Copies the default configuration file and creates a new one with '_copy' appended to its name.
+    """Copy the default configuration file and create a new one with '_copy' appended to its name.
 
-    This function duplicates the existing default configuration file (DEFAULT_CFG_PATH) and saves it
-    with '_copy' appended to its name in the current working directory. It provides a convenient way
-    to create a custom configuration file based on the default settings.
+    This function duplicates the existing default configuration file (DEFAULT_CFG_PATH) and saves it with '_copy'
+    appended to its name in the current working directory. It provides a convenient way to create a custom configuration
+    file based on the default settings.
 
     Examples:
         >>> copy_default_cfg()

ultralytics/cfg/datasets/Argoverse.yaml

@@ -6,10 +6,10 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── Argoverse  ← downloads here (31.5 GB)
+#     └── Argoverse ← downloads here (31.5 GB)
 
 # 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/Argoverse # dataset root dir
+path: Argoverse # dataset root dir
 train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images
 val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images
 test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
@@ -30,14 +30,14 @@ download: |
   import json
   from pathlib import Path
 
-  from tqdm import tqdm
+  from ultralytics.utils import TQDM
   from ultralytics.utils.downloads import download
 
   def argoverse2yolo(set):
       """Convert Argoverse dataset annotations to YOLO format for object detection tasks."""
       labels = {}
       a = json.load(open(set, "rb"))
-      for annot in tqdm(a["annotations"], desc=f"Converting {set} to YOLOv5 format..."):
+      for annot in TQDM(a["annotations"], desc=f"Converting {set} to YOLOv5 format..."):
           img_id = annot["image_id"]
           img_name = a["images"][img_id]["name"]
           img_label_name = f"{img_name[:-3]}txt"

ultralytics/cfg/datasets/DOTAv1.5.yaml

@@ -6,10 +6,10 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── dota1.5  ← downloads here (2GB)
+#     └── dota1.5 ← downloads here (2GB)
 
 # 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/DOTAv1.5 # dataset root dir
+path: DOTAv1.5 # dataset root dir
 train: images/train # train images (relative to 'path') 1411 images
 val: images/val # val images (relative to 'path') 458 images
 test: images/test # test images (optional) 937 images

ultralytics/cfg/datasets/DOTAv1.yaml

@@ -6,10 +6,10 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── dota1  ← downloads here (2GB)
+#     └── dota1 ← downloads here (2GB)
 
 # 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/DOTAv1 # dataset root dir
+path: DOTAv1 # dataset root dir
 train: images/train # train images (relative to 'path') 1411 images
 val: images/val # val images (relative to 'path') 458 images
 test: images/test # test images (optional) 937 images

ultralytics/cfg/datasets/GlobalWheat2020.yaml

@@ -6,10 +6,10 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── GlobalWheat2020  ← downloads here (7.0 GB)
+#     └── GlobalWheat2020 ← downloads here (7.0 GB)
 
 # 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/GlobalWheat2020 # dataset root dir
+path: GlobalWheat2020 # dataset root dir
 train: # train images (relative to 'path') 3422 images
   - images/arvalis_1
   - images/arvalis_2

ultralytics/cfg/datasets/HomeObjects-3K.yaml

@@ -6,13 +6,12 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── homeobjects-3K  ← downloads here (390 MB)
+#     └── homeobjects-3K ← downloads here (390 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/homeobjects-3K # dataset root dir
-train: train/images # train images (relative to 'path') 2285 images
-val: valid/images # val images (relative to 'path') 404 images
-test: # test images (relative to 'path')
+path: homeobjects-3K # dataset root dir
+train: images/train # train images (relative to 'path') 2285 images
+val: images/val # val images (relative to 'path') 404 images
 
 # Classes
 names:

ultralytics/cfg/datasets/ImageNet.yaml

@@ -7,10 +7,10 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── imagenet  ← downloads here (144 GB)
+#     └── imagenet ← downloads here (144 GB)
 
 # 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/imagenet # dataset root dir
+path: imagenet # dataset root dir
 train: train # train images (relative to 'path') 1281167 images
 val: val # val images (relative to 'path') 50000 images
 test: # test images (optional)
@@ -342,7 +342,7 @@ names:
   322: ringlet
   323: monarch butterfly
   324: small white
-  325: sulphur butterfly
+  325: sulfur butterfly
   326: gossamer-winged butterfly
   327: starfish
   328: sea urchin

ultralytics/cfg/datasets/Objects365.yaml

@@ -6,10 +6,10 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── Objects365  ← downloads here (712 GB = 367G data + 345G zips)
+#     └── Objects365 ← downloads here (712 GB = 367G data + 345G zips)
 
 # 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/Objects365 # dataset root dir
+path: Objects365 # dataset root dir
 train: images/train # train images (relative to 'path') 1742289 images
 val: images/val # val images (relative to 'path') 80000 images
 test: # test images (optional)
@@ -384,43 +384,41 @@ names:
 
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
+  from concurrent.futures import ThreadPoolExecutor
   from pathlib import Path
 
   import numpy as np
-  from tqdm import tqdm
 
+  from ultralytics.utils import TQDM
   from ultralytics.utils.checks import check_requirements
   from ultralytics.utils.downloads import download
   from ultralytics.utils.ops import xyxy2xywhn
 
-  check_requirements(("pycocotools>=2.0",))
-  from pycocotools.coco import COCO
-
-  # Make Directories
-  dir = Path(yaml["path"])  # dataset root dir
-  for p in "images", "labels":
-      (dir / p).mkdir(parents=True, exist_ok=True)
-      for q in "train", "val":
-          (dir / p / q).mkdir(parents=True, exist_ok=True)
+  check_requirements("faster-coco-eval")
+  from faster_coco_eval import COCO
 
   # Train, Val Splits
+  dir = Path(yaml["path"])
   for split, patches in [("train", 50 + 1), ("val", 43 + 1)]:
       print(f"Processing {split} in {patches} patches ...")
       images, labels = dir / "images" / split, dir / "labels" / split
+      images.mkdir(parents=True, exist_ok=True)
+      labels.mkdir(parents=True, exist_ok=True)
 
       # Download
       url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/"
       if split == "train":
           download([f"{url}zhiyuan_objv2_{split}.tar.gz"], dir=dir)  # annotations json
-          download([f"{url}patch{i}.tar.gz" for i in range(patches)], dir=images, curl=True, threads=8)
+          download([f"{url}patch{i}.tar.gz" for i in range(patches)], dir=images, threads=17)  # 51 patches / 17 threads = 3
       elif split == "val":
           download([f"{url}zhiyuan_objv2_{split}.json"], dir=dir)  # annotations json
-          download([f"{url}images/v1/patch{i}.tar.gz" for i in range(15 + 1)], dir=images, curl=True, threads=8)
-          download([f"{url}images/v2/patch{i}.tar.gz" for i in range(16, patches)], dir=images, curl=True, threads=8)
+          download([f"{url}images/v1/patch{i}.tar.gz" for i in range(15 + 1)], dir=images, threads=16)
+          download([f"{url}images/v2/patch{i}.tar.gz" for i in range(16, patches)], dir=images, threads=16)
 
       # Move
-      for f in tqdm(images.rglob("*.jpg"), desc=f"Moving {split} images"):
-          f.rename(images / f.name)  # move to /images/{split}
+      files = list(images.rglob("*.jpg"))
+      with ThreadPoolExecutor(max_workers=16) as executor:
+          list(TQDM(executor.map(lambda f: f.rename(images / f.name), files), total=len(files), desc=f"Moving {split} images"))
 
       # Labels
       coco = COCO(dir / f"zhiyuan_objv2_{split}.json")
@@ -428,10 +426,12 @@ download: |
       for cid, cat in enumerate(names):
           catIds = coco.getCatIds(catNms=[cat])
           imgIds = coco.getImgIds(catIds=catIds)
-          for im in tqdm(coco.loadImgs(imgIds), desc=f"Class {cid + 1}/{len(names)} {cat}"):
-              width, height = im["width"], im["height"]
-              path = Path(im["file_name"])  # image filename
+
+          def process_annotation(im):
+              """Process and write annotations for a single image."""
               try:
+                  width, height = im["width"], im["height"]
+                  path = Path(im["file_name"])
                   with open(labels / path.with_suffix(".txt").name, "a", encoding="utf-8") as file:
                       annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
                       for a in coco.loadAnns(annIds):
@@ -441,3 +441,7 @@ download: |
                           file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n")
               except Exception as e:
                   print(e)
+
+          images_list = coco.loadImgs(imgIds)
+          with ThreadPoolExecutor(max_workers=16) as executor:
+              list(TQDM(executor.map(process_annotation, images_list), total=len(images_list), desc=f"Class {cid + 1}/{len(names)} {cat}"))