ultralytics-opencv-headless 8.3.246__py3-none-any.whl

ultralytics/utils/callbacks/dvc.py

@@ -0,0 +1,197 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from pathlib import Path
+
+from ultralytics.utils import LOGGER, SETTINGS, TESTS_RUNNING, checks
+
+try:
+    assert not TESTS_RUNNING  # do not log pytest
+    assert SETTINGS["dvc"] is True  # verify integration is enabled
+    import dvclive
+
+    assert checks.check_version("dvclive", "2.11.0", verbose=True)
+
+    import os
+    import re
+
+    # DVCLive logger instance
+    live = None
+    _processed_plots = {}
+
+    # `on_fit_epoch_end` is called on final validation (probably need to be fixed) for now this is the way we
+    # distinguish final evaluation of the best model vs last epoch validation
+    _training_epoch = False
+
+except (ImportError, AssertionError, TypeError):
+    dvclive = None
+
+
+def _log_images(path: Path, prefix: str = "") -> None:
+    """Log images at specified path with an optional prefix using DVCLive.
+
+    This function logs images found at the given path to DVCLive, organizing them by batch to enable slider
+    functionality in the UI. It processes image filenames to extract batch information and restructures the path
+    accordingly.
+
+    Args:
+        path (Path): Path to the image file to be logged.
+        prefix (str, optional): Optional prefix to add to the image name when logging.
+
+    Examples:
+        >>> from pathlib import Path
+        >>> _log_images(Path("runs/train/exp/val_batch0_pred.jpg"), prefix="validation")
+    """
+    if live:
+        name = path.name
+
+        # Group images by batch to enable sliders in UI
+        if m := re.search(r"_batch(\d+)", name):
+            ni = m[1]
+            new_stem = re.sub(r"_batch(\d+)", "_batch", path.stem)
+            name = (Path(new_stem) / ni).with_suffix(path.suffix)
+
+        live.log_image(os.path.join(prefix, name), path)
+
+
+def _log_plots(plots: dict, prefix: str = "") -> None:
+    """Log plot images for training progress if they have not been previously processed.
+
+    Args:
+        plots (dict): Dictionary containing plot information with timestamps.
+        prefix (str, optional): Optional prefix to add to the logged image paths.
+    """
+    for name, params in plots.items():
+        timestamp = params["timestamp"]
+        if _processed_plots.get(name) != timestamp:
+            _log_images(name, prefix)
+            _processed_plots[name] = timestamp
+
+
+def _log_confusion_matrix(validator) -> None:
+    """Log confusion matrix for a validator using DVCLive.
+
+    This function processes the confusion matrix from a validator object and logs it to DVCLive by converting the matrix
+    into lists of target and prediction labels.
+
+    Args:
+        validator (BaseValidator): The validator object containing the confusion matrix and class names. Must have
+            attributes confusion_matrix.matrix, confusion_matrix.task, and names.
+    """
+    targets = []
+    preds = []
+    matrix = validator.confusion_matrix.matrix
+    names = list(validator.names.values())
+    if validator.confusion_matrix.task == "detect":
+        names += ["background"]
+
+    for ti, pred in enumerate(matrix.T.astype(int)):
+        for pi, num in enumerate(pred):
+            targets.extend([names[ti]] * num)
+            preds.extend([names[pi]] * num)
+
+    live.log_sklearn_plot("confusion_matrix", targets, preds, name="cf.json", normalized=True)
+
+
+def on_pretrain_routine_start(trainer) -> None:
+    """Initialize DVCLive logger for training metadata during pre-training routine."""
+    try:
+        global live
+        live = dvclive.Live(save_dvc_exp=True, cache_images=True)
+        LOGGER.info("DVCLive is detected and auto logging is enabled (run 'yolo settings dvc=False' to disable).")
+    except Exception as e:
+        LOGGER.warning(f"DVCLive installed but not initialized correctly, not logging this run. {e}")
+
+
+def on_pretrain_routine_end(trainer) -> None:
+    """Log plots related to the training process at the end of the pretraining routine."""
+    _log_plots(trainer.plots, "train")
+
+
+def on_train_start(trainer) -> None:
+    """Log the training parameters if DVCLive logging is active."""
+    if live:
+        live.log_params(trainer.args)
+
+
+def on_train_epoch_start(trainer) -> None:
+    """Set the global variable _training_epoch value to True at the start of training each epoch."""
+    global _training_epoch
+    _training_epoch = True
+
+
+def on_fit_epoch_end(trainer) -> None:
+    """Log training metrics, model info, and advance to next step at the end of each fit epoch.
+
+    This function is called at the end of each fit epoch during training. It logs various metrics including training
+    loss items, validation metrics, and learning rates. On the first epoch, it also logs model
+    information. Additionally, it logs training and validation plots and advances the DVCLive step counter.
+
+    Args:
+        trainer (BaseTrainer): The trainer object containing training state, metrics, and plots.
+
+    Notes:
+        This function only performs logging operations when DVCLive logging is active and during a training epoch.
+        The global variable _training_epoch is used to track whether the current epoch is a training epoch.
+    """
+    global _training_epoch
+    if live and _training_epoch:
+        all_metrics = {**trainer.label_loss_items(trainer.tloss, prefix="train"), **trainer.metrics, **trainer.lr}
+        for metric, value in all_metrics.items():
+            live.log_metric(metric, value)
+
+        if trainer.epoch == 0:
+            from ultralytics.utils.torch_utils import model_info_for_loggers
+
+            for metric, value in model_info_for_loggers(trainer).items():
+                live.log_metric(metric, value, plot=False)
+
+        _log_plots(trainer.plots, "train")
+        _log_plots(trainer.validator.plots, "val")
+
+        live.next_step()
+        _training_epoch = False
+
+
+def on_train_end(trainer) -> None:
+    """Log best metrics, plots, and confusion matrix at the end of training.
+
+    This function is called at the conclusion of the training process to log final metrics, visualizations, and model
+    artifacts if DVCLive logging is active. It captures the best model performance metrics, training plots, validation
+    plots, and confusion matrix for later analysis.
+
+    Args:
+        trainer (BaseTrainer): The trainer object containing training state, metrics, and validation results.
+
+    Examples:
+        >>> # Inside a custom training loop
+        >>> from ultralytics.utils.callbacks.dvc import on_train_end
+        >>> on_train_end(trainer)  # Log final metrics and artifacts
+    """
+    if live:
+        # At the end log the best metrics. It runs validator on the best model internally.
+        all_metrics = {**trainer.label_loss_items(trainer.tloss, prefix="train"), **trainer.metrics, **trainer.lr}
+        for metric, value in all_metrics.items():
+            live.log_metric(metric, value, plot=False)
+
+        _log_plots(trainer.plots, "val")
+        _log_plots(trainer.validator.plots, "val")
+        _log_confusion_matrix(trainer.validator)
+
+        if trainer.best.exists():
+            live.log_artifact(trainer.best, copy=True, type="model")
+
+        live.end()
+
+
+callbacks = (
+    {
+        "on_pretrain_routine_start": on_pretrain_routine_start,
+        "on_pretrain_routine_end": on_pretrain_routine_end,
+        "on_train_start": on_train_start,
+        "on_train_epoch_start": on_train_epoch_start,
+        "on_fit_epoch_end": on_fit_epoch_end,
+        "on_train_end": on_train_end,
+    }
+    if dvclive
+    else {}
+)

ultralytics/utils/callbacks/hub.py

@@ -0,0 +1,110 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+import json
+from time import time
+
+from ultralytics.hub import HUB_WEB_ROOT, PREFIX, HUBTrainingSession
+from ultralytics.utils import LOGGER, RANK, SETTINGS
+from ultralytics.utils.events import events
+
+
+def on_pretrain_routine_start(trainer):
+    """Create a remote Ultralytics HUB session to log local model training."""
+    if RANK in {-1, 0} and SETTINGS["hub"] is True and SETTINGS["api_key"] and trainer.hub_session is None:
+        trainer.hub_session = HUBTrainingSession.create_session(trainer.args.model, trainer.args)
+
+
+def on_pretrain_routine_end(trainer):
+    """Initialize timers for upload rate limiting before training begins."""
+    if session := getattr(trainer, "hub_session", None):
+        # Start timer for upload rate limit
+        session.timers = {"metrics": time(), "ckpt": time()}  # start timer for session rate limiting
+
+
+def on_fit_epoch_end(trainer):
+    """Upload training progress metrics to Ultralytics HUB at the end of each epoch."""
+    if session := getattr(trainer, "hub_session", None):
+        # Upload metrics after validation ends
+        all_plots = {
+            **trainer.label_loss_items(trainer.tloss, prefix="train"),
+            **trainer.metrics,
+        }
+        if trainer.epoch == 0:
+            from ultralytics.utils.torch_utils import model_info_for_loggers
+
+            all_plots = {**all_plots, **model_info_for_loggers(trainer)}
+
+        session.metrics_queue[trainer.epoch] = json.dumps(all_plots)
+
+        # If any metrics failed to upload previously, add them to the queue to attempt uploading again
+        if session.metrics_upload_failed_queue:
+            session.metrics_queue.update(session.metrics_upload_failed_queue)
+
+        if time() - session.timers["metrics"] > session.rate_limits["metrics"]:
+            session.upload_metrics()
+            session.timers["metrics"] = time()  # reset timer
+            session.metrics_queue = {}  # reset queue
+
+
+def on_model_save(trainer):
+    """Upload model checkpoints to Ultralytics HUB with rate limiting."""
+    if session := getattr(trainer, "hub_session", None):
+        # Upload checkpoints with rate limiting
+        is_best = trainer.best_fitness == trainer.fitness
+        if time() - session.timers["ckpt"] > session.rate_limits["ckpt"]:
+            LOGGER.info(f"{PREFIX}Uploading checkpoint {HUB_WEB_ROOT}/models/{session.model.id}")
+            session.upload_model(trainer.epoch, trainer.last, is_best)
+            session.timers["ckpt"] = time()  # reset timer
+
+
+def on_train_end(trainer):
+    """Upload final model and metrics to Ultralytics HUB at the end of training."""
+    if session := getattr(trainer, "hub_session", None):
+        # Upload final model and metrics with exponential standoff
+        LOGGER.info(f"{PREFIX}Syncing final model...")
+        session.upload_model(
+            trainer.epoch,
+            trainer.best,
+            map=trainer.metrics.get("metrics/mAP50-95(B)", 0),
+            final=True,
+        )
+        session.alive = False  # stop heartbeats
+        LOGGER.info(f"{PREFIX}Done ✅\n{PREFIX}View model at {session.model_url} 🚀")
+
+
+def on_train_start(trainer):
+    """Run events on train start."""
+    events(trainer.args, trainer.device)
+
+
+def on_val_start(validator):
+    """Run events on validation start."""
+    if not validator.training:
+        events(validator.args, validator.device)
+
+
+def on_predict_start(predictor):
+    """Run events on predict start."""
+    events(predictor.args, predictor.device)
+
+
+def on_export_start(exporter):
+    """Run events on export start."""
+    events(exporter.args, exporter.device)
+
+
+callbacks = (
+    {
+        "on_pretrain_routine_start": on_pretrain_routine_start,
+        "on_pretrain_routine_end": on_pretrain_routine_end,
+        "on_fit_epoch_end": on_fit_epoch_end,
+        "on_model_save": on_model_save,
+        "on_train_end": on_train_end,
+        "on_train_start": on_train_start,
+        "on_val_start": on_val_start,
+        "on_predict_start": on_predict_start,
+        "on_export_start": on_export_start,
+    }
+    if SETTINGS["hub"] is True
+    else {}
+)

ultralytics/utils/callbacks/mlflow.py

@@ -0,0 +1,134 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+"""
+MLflow Logging for Ultralytics YOLO.
+
+This module enables MLflow logging for Ultralytics YOLO. It logs metrics, parameters, and model artifacts.
+For setting up, a tracking URI should be specified. The logging can be customized using environment variables.
+
+Commands:
+    1. To set a project name:
+        `export MLFLOW_EXPERIMENT_NAME=<your_experiment_name>` or use the project=<project> argument
+
+    2. To set a run name:
+        `export MLFLOW_RUN=<your_run_name>` or use the name=<name> argument
+
+    3. To start a local MLflow server:
+        mlflow server --backend-store-uri runs/mlflow
+       It will by default start a local server at http://127.0.0.1:5000.
+       To specify a different URI, set the MLFLOW_TRACKING_URI environment variable.
+
+    4. To kill all running MLflow server instances:
+        ps aux | grep 'mlflow' | grep -v 'grep' | awk '{print $2}' | xargs kill -9
+"""
+
+from ultralytics.utils import LOGGER, RUNS_DIR, SETTINGS, TESTS_RUNNING, colorstr
+
+try:
+    import os
+
+    assert not TESTS_RUNNING or "test_mlflow" in os.environ.get("PYTEST_CURRENT_TEST", "")  # do not log pytest
+    assert SETTINGS["mlflow"] is True  # verify integration is enabled
+    import mlflow
+
+    assert hasattr(mlflow, "__version__")  # verify package is not directory
+    from pathlib import Path
+
+    PREFIX = colorstr("MLflow: ")
+
+except (ImportError, AssertionError):
+    mlflow = None
+
+
+def sanitize_dict(x: dict) -> dict:
+    """Sanitize dictionary keys by removing parentheses and converting values to floats."""
+    return {k.replace("(", "").replace(")", ""): float(v) for k, v in x.items()}
+
+
+def on_pretrain_routine_end(trainer):
+    """Log training parameters to MLflow at the end of the pretraining routine.
+
+    This function sets up MLflow logging based on environment variables and trainer arguments. It sets the tracking URI,
+    experiment name, and run name, then starts the MLflow run if not already active. It finally logs the parameters from
+    the trainer.
+
+    Args:
+        trainer (ultralytics.engine.trainer.BaseTrainer): The training object with arguments and parameters to log.
+
+    Notes:
+        MLFLOW_TRACKING_URI: The URI for MLflow tracking. If not set, defaults to 'runs/mlflow'.
+        MLFLOW_EXPERIMENT_NAME: The name of the MLflow experiment. If not set, defaults to trainer.args.project.
+        MLFLOW_RUN: The name of the MLflow run. If not set, defaults to trainer.args.name.
+        MLFLOW_KEEP_RUN_ACTIVE: Boolean indicating whether to keep the MLflow run active after training ends.
+    """
+    global mlflow
+
+    uri = os.environ.get("MLFLOW_TRACKING_URI") or str(RUNS_DIR / "mlflow")
+    LOGGER.debug(f"{PREFIX} tracking uri: {uri}")
+    mlflow.set_tracking_uri(uri)
+
+    # Set experiment and run names
+    experiment_name = os.environ.get("MLFLOW_EXPERIMENT_NAME") or trainer.args.project or "/Shared/Ultralytics"
+    run_name = os.environ.get("MLFLOW_RUN") or trainer.args.name
+    mlflow.set_experiment(experiment_name)
+
+    mlflow.autolog()
+    try:
+        active_run = mlflow.active_run() or mlflow.start_run(run_name=run_name)
+        LOGGER.info(f"{PREFIX}logging run_id({active_run.info.run_id}) to {uri}")
+        if Path(uri).is_dir():
+            LOGGER.info(f"{PREFIX}view at http://127.0.0.1:5000 with 'mlflow server --backend-store-uri {uri}'")
+        LOGGER.info(f"{PREFIX}disable with 'yolo settings mlflow=False'")
+        mlflow.log_params(dict(trainer.args))
+    except Exception as e:
+        LOGGER.warning(f"{PREFIX}Failed to initialize: {e}")
+        LOGGER.warning(f"{PREFIX}Not tracking this run")
+
+
+def on_train_epoch_end(trainer):
+    """Log training metrics at the end of each train epoch to MLflow."""
+    if mlflow:
+        mlflow.log_metrics(
+            metrics={
+                **sanitize_dict(trainer.lr),
+                **sanitize_dict(trainer.label_loss_items(trainer.tloss, prefix="train")),
+            },
+            step=trainer.epoch,
+        )
+
+
+def on_fit_epoch_end(trainer):
+    """Log training metrics at the end of each fit epoch to MLflow."""
+    if mlflow:
+        mlflow.log_metrics(metrics=sanitize_dict(trainer.metrics), step=trainer.epoch)
+
+
+def on_train_end(trainer):
+    """Log model artifacts at the end of training."""
+    if not mlflow:
+        return
+    mlflow.log_artifact(str(trainer.best.parent))  # log save_dir/weights directory with best.pt and last.pt
+    for f in trainer.save_dir.glob("*"):  # log all other files in save_dir
+        if f.suffix in {".png", ".jpg", ".csv", ".pt", ".yaml"}:
+            mlflow.log_artifact(str(f))
+    keep_run_active = os.environ.get("MLFLOW_KEEP_RUN_ACTIVE", "False").lower() == "true"
+    if keep_run_active:
+        LOGGER.info(f"{PREFIX}mlflow run still alive, remember to close it using mlflow.end_run()")
+    else:
+        mlflow.end_run()
+        LOGGER.debug(f"{PREFIX}mlflow run ended")
+
+    LOGGER.info(
+        f"{PREFIX}results logged to {mlflow.get_tracking_uri()}\n{PREFIX}disable with 'yolo settings mlflow=False'"
+    )
+
+
+callbacks = (
+    {
+        "on_pretrain_routine_end": on_pretrain_routine_end,
+        "on_train_epoch_end": on_train_epoch_end,
+        "on_fit_epoch_end": on_fit_epoch_end,
+        "on_train_end": on_train_end,
+    }
+    if mlflow
+    else {}
+)

ultralytics/utils/callbacks/neptune.py

@@ -0,0 +1,126 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from ultralytics.utils import LOGGER, SETTINGS, TESTS_RUNNING
+
+try:
+    assert not TESTS_RUNNING  # do not log pytest
+    assert SETTINGS["neptune"] is True  # verify integration is enabled
+
+    import neptune
+    from neptune.types import File
+
+    assert hasattr(neptune, "__version__")
+
+    run = None  # NeptuneAI experiment logger instance
+
+except (ImportError, AssertionError):
+    neptune = None
+
+
+def _log_scalars(scalars: dict, step: int = 0) -> None:
+    """Log scalars to the NeptuneAI experiment logger.
+
+    Args:
+        scalars (dict): Dictionary of scalar values to log to NeptuneAI.
+        step (int, optional): The current step or iteration number for logging.
+
+    Examples:
+        >>> metrics = {"mAP": 0.85, "loss": 0.32}
+        >>> _log_scalars(metrics, step=100)
+    """
+    if run:
+        for k, v in scalars.items():
+            run[k].append(value=v, step=step)
+
+
+def _log_images(imgs_dict: dict, group: str = "") -> None:
+    """Log images to the NeptuneAI experiment logger.
+
+    This function logs image data to Neptune.ai when a valid Neptune run is active. Images are organized under the
+    specified group name.
+
+    Args:
+        imgs_dict (dict): Dictionary of images to log, with keys as image names and values as image data.
+        group (str, optional): Group name to organize images under in the Neptune UI.
+
+    Examples:
+        >>> # Log validation images
+        >>> _log_images({"val_batch": img_tensor}, group="validation")
+    """
+    if run:
+        for k, v in imgs_dict.items():
+            run[f"{group}/{k}"].upload(File(v))
+
+
+def _log_plot(title: str, plot_path: str) -> None:
+    """Log plots to the NeptuneAI experiment logger."""
+    import matplotlib.image as mpimg
+    import matplotlib.pyplot as plt
+
+    img = mpimg.imread(plot_path)
+    fig = plt.figure()
+    ax = fig.add_axes([0, 0, 1, 1], frameon=False, aspect="auto", xticks=[], yticks=[])  # no ticks
+    ax.imshow(img)
+    run[f"Plots/{title}"].upload(fig)
+
+
+def on_pretrain_routine_start(trainer) -> None:
+    """Initialize NeptuneAI run and log hyperparameters before training starts."""
+    try:
+        global run
+        run = neptune.init_run(
+            project=trainer.args.project or "Ultralytics",
+            name=trainer.args.name,
+            tags=["Ultralytics"],
+        )
+        run["Configuration/Hyperparameters"] = {k: "" if v is None else v for k, v in vars(trainer.args).items()}
+    except Exception as e:
+        LOGGER.warning(f"NeptuneAI installed but not initialized correctly, not logging this run. {e}")
+
+
+def on_train_epoch_end(trainer) -> None:
+    """Log training metrics and learning rate at the end of each training epoch."""
+    _log_scalars(trainer.label_loss_items(trainer.tloss, prefix="train"), trainer.epoch + 1)
+    _log_scalars(trainer.lr, trainer.epoch + 1)
+    if trainer.epoch == 1:
+        _log_images({f.stem: str(f) for f in trainer.save_dir.glob("train_batch*.jpg")}, "Mosaic")
+
+
+def on_fit_epoch_end(trainer) -> None:
+    """Log model info and validation metrics at the end of each fit epoch."""
+    if run and trainer.epoch == 0:
+        from ultralytics.utils.torch_utils import model_info_for_loggers
+
+        run["Configuration/Model"] = model_info_for_loggers(trainer)
+    _log_scalars(trainer.metrics, trainer.epoch + 1)
+
+
+def on_val_end(validator) -> None:
+    """Log validation images at the end of validation."""
+    if run:
+        # Log val_labels and val_pred
+        _log_images({f.stem: str(f) for f in validator.save_dir.glob("val*.jpg")}, "Validation")
+
+
+def on_train_end(trainer) -> None:
+    """Log final results, plots, and model weights at the end of training."""
+    if run:
+        # Log final results, CM matrix + PR plots
+        for f in [*trainer.plots.keys(), *trainer.validator.plots.keys()]:
+            if "batch" not in f.name:
+                _log_plot(title=f.stem, plot_path=f)
+        # Log the final model
+        run[f"weights/{trainer.args.name or trainer.args.task}/{trainer.best.name}"].upload(File(str(trainer.best)))
+
+
+callbacks = (
+    {
+        "on_pretrain_routine_start": on_pretrain_routine_start,
+        "on_train_epoch_end": on_train_epoch_end,
+        "on_fit_epoch_end": on_fit_epoch_end,
+        "on_val_end": on_val_end,
+        "on_train_end": on_train_end,
+    }
+    if neptune
+    else {}
+)