Reference for ultralytics/models/yolo/detect/val.py

def build_dataset(self, img_path: str, mode: str = "val", batch: Optional[int] = None) -> torch.utils.data.Dataset:
    """
    Build YOLO Dataset.

    Args:
        img_path (str): Path to the folder containing images.
        mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode.
        batch (int, optional): Size of batches, this is for `rect`.

    Returns:
        (Dataset): YOLO dataset.
    """
    return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, stride=self.stride)

def coco_evaluate(
    self,
    stats: Dict[str, Any],
    pred_json: str,
    anno_json: str,
    iou_types: Union[str, List[str]] = "bbox",
    suffix: Union[str, List[str]] = "Box",
) -> Dict[str, Any]:
    """
    Evaluate COCO/LVIS metrics using faster-coco-eval library.

    Performs evaluation using the faster-coco-eval library to compute mAP metrics
    for object detection. Updates the provided stats dictionary with computed metrics
    including mAP50, mAP50-95, and LVIS-specific metrics if applicable.

    Args:
        stats (Dict[str, Any]): Dictionary to store computed metrics and statistics.
        pred_json (str | Path]): Path to JSON file containing predictions in COCO format.
        anno_json (str | Path]): Path to JSON file containing ground truth annotations in COCO format.
        iou_types (str | List[str]]): IoU type(s) for evaluation. Can be single string or list of strings.
            Common values include "bbox", "segm", "keypoints". Defaults to "bbox".
        suffix (str | List[str]]): Suffix to append to metric names in stats dictionary. Should correspond
            to iou_types if multiple types provided. Defaults to "Box".

    Returns:
        (Dict[str, Any]): Updated stats dictionary containing the computed COCO/LVIS evaluation metrics.
    """
    if self.args.save_json and (self.is_coco or self.is_lvis) and len(self.jdict):
        LOGGER.info(f"\nEvaluating faster-coco-eval mAP using {pred_json} and {anno_json}...")
        try:
            for x in pred_json, anno_json:
                assert x.is_file(), f"{x} file not found"
            iou_types = [iou_types] if isinstance(iou_types, str) else iou_types
            suffix = [suffix] if isinstance(suffix, str) else suffix
            check_requirements("faster-coco-eval>=1.6.7")
            from faster_coco_eval import COCO, COCOeval_faster

            anno = COCO(anno_json)
            pred = anno.loadRes(pred_json)
            for i, iou_type in enumerate(iou_types):
                val = COCOeval_faster(
                    anno, pred, iouType=iou_type, lvis_style=self.is_lvis, print_function=LOGGER.info
                )
                val.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # images to eval
                val.evaluate()
                val.accumulate()
                val.summarize()

                # update mAP50-95 and mAP50
                stats[f"metrics/mAP50({suffix[i][0]})"] = val.stats_as_dict["AP_50"]
                stats[f"metrics/mAP50-95({suffix[i][0]})"] = val.stats_as_dict["AP_all"]

                if self.is_lvis:
                    stats[f"metrics/APr({suffix[i][0]})"] = val.stats_as_dict["APr"]
                    stats[f"metrics/APc({suffix[i][0]})"] = val.stats_as_dict["APc"]
                    stats[f"metrics/APf({suffix[i][0]})"] = val.stats_as_dict["APf"]

            if self.is_lvis:
                stats["fitness"] = stats["metrics/mAP50-95(B)"]  # always use box mAP50-95 for fitness
        except Exception as e:
            LOGGER.warning(f"faster-coco-eval unable to run: {e}")
    return stats

def eval_json(self, stats: Dict[str, Any]) -> Dict[str, Any]:
    """
    Evaluate YOLO output in JSON format and return performance statistics.

    Args:
        stats (Dict[str, Any]): Current statistics dictionary.

    Returns:
        (Dict[str, Any]): Updated statistics dictionary with COCO/LVIS evaluation results.
    """
    pred_json = self.save_dir / "predictions.json"  # predictions
    anno_json = (
        self.data["path"]
        / "annotations"
        / ("instances_val2017.json" if self.is_coco else f"lvis_v1_{self.args.split}.json")
    )  # annotations
    return self.coco_evaluate(stats, pred_json, anno_json)

def finalize_metrics(self) -> None:
    """Set final values for metrics speed and confusion matrix."""
    if self.args.plots:
        for normalize in True, False:
            self.confusion_matrix.plot(save_dir=self.save_dir, normalize=normalize, on_plot=self.on_plot)
    self.metrics.speed = self.speed
    self.metrics.confusion_matrix = self.confusion_matrix
    self.metrics.save_dir = self.save_dir

def get_dataloader(self, dataset_path: str, batch_size: int) -> torch.utils.data.DataLoader:
    """
    Construct and return dataloader.

    Args:
        dataset_path (str): Path to the dataset.
        batch_size (int): Size of each batch.

    Returns:
        (torch.utils.data.DataLoader): Dataloader for validation.
    """
    dataset = self.build_dataset(dataset_path, batch=batch_size, mode="val")
    return build_dataloader(dataset, batch_size, self.args.workers, shuffle=False, rank=-1)  # return dataloader

def get_desc(self) -> str:
    """Return a formatted string summarizing class metrics of YOLO model."""
    return ("%22s" + "%11s" * 6) % ("Class", "Images", "Instances", "Box(P", "R", "mAP50", "mAP50-95)")

def get_stats(self) -> Dict[str, Any]:
    """
    Calculate and return metrics statistics.

    Returns:
        (Dict[str, Any]): Dictionary containing metrics results.
    """
    self.metrics.process(save_dir=self.save_dir, plot=self.args.plots, on_plot=self.on_plot)
    self.metrics.clear_stats()
    return self.metrics.results_dict

def init_metrics(self, model: torch.nn.Module) -> None:
    """
    Initialize evaluation metrics for YOLO detection validation.

    Args:
        model (torch.nn.Module): Model to validate.
    """
    val = self.data.get(self.args.split, "")  # validation path
    self.is_coco = (
        isinstance(val, str)
        and "coco" in val
        and (val.endswith(f"{os.sep}val2017.txt") or val.endswith(f"{os.sep}test-dev2017.txt"))
    )  # is COCO
    self.is_lvis = isinstance(val, str) and "lvis" in val and not self.is_coco  # is LVIS
    self.class_map = converter.coco80_to_coco91_class() if self.is_coco else list(range(1, len(model.names) + 1))
    self.args.save_json |= self.args.val and (self.is_coco or self.is_lvis) and not self.training  # run final val
    self.names = model.names
    self.nc = len(model.names)
    self.end2end = getattr(model, "end2end", False)
    self.seen = 0
    self.jdict = []
    self.metrics.names = self.names
    self.confusion_matrix = ConfusionMatrix(names=list(model.names.values()))

def plot_predictions(
    self, batch: Dict[str, Any], preds: List[Dict[str, torch.Tensor]], ni: int, max_det: Optional[int] = None
) -> None:
    """
    Plot predicted bounding boxes on input images and save the result.

    Args:
        batch (Dict[str, Any]): Batch containing images and annotations.
        preds (List[Dict[str, torch.Tensor]]): List of predictions from the model.
        ni (int): Batch index.
        max_det (Optional[int]): Maximum number of detections to plot.
    """
    # TODO: optimize this
    for i, pred in enumerate(preds):
        pred["batch_idx"] = torch.ones_like(pred["conf"]) * i  # add batch index to predictions
    keys = preds[0].keys()
    max_det = max_det or self.args.max_det
    batched_preds = {k: torch.cat([x[k][:max_det] for x in preds], dim=0) for k in keys}
    # TODO: fix this
    batched_preds["bboxes"][:, :4] = ops.xyxy2xywh(batched_preds["bboxes"][:, :4])  # convert to xywh format
    plot_images(
        images=batch["img"],
        labels=batched_preds,
        paths=batch["im_file"],
        fname=self.save_dir / f"val_batch{ni}_pred.jpg",
        names=self.names,
        on_plot=self.on_plot,
    )  # pred

def plot_val_samples(self, batch: Dict[str, Any], ni: int) -> None:
    """
    Plot validation image samples.

    Args:
        batch (Dict[str, Any]): Batch containing images and annotations.
        ni (int): Batch index.
    """
    plot_images(
        labels=batch,
        paths=batch["im_file"],
        fname=self.save_dir / f"val_batch{ni}_labels.jpg",
        names=self.names,
        on_plot=self.on_plot,
    )

def postprocess(self, preds: torch.Tensor) -> List[Dict[str, torch.Tensor]]:
    """
    Apply Non-maximum suppression to prediction outputs.

    Args:
        preds (torch.Tensor): Raw predictions from the model.

    Returns:
        (List[Dict[str, torch.Tensor]]): Processed predictions after NMS, where each dict contains
            'bboxes', 'conf', 'cls', and 'extra' tensors.
    """
    outputs = ops.non_max_suppression(
        preds,
        self.args.conf,
        self.args.iou,
        nc=0 if self.args.task == "detect" else self.nc,
        multi_label=True,
        agnostic=self.args.single_cls or self.args.agnostic_nms,
        max_det=self.args.max_det,
        end2end=self.end2end,
        rotated=self.args.task == "obb",
    )
    return [{"bboxes": x[:, :4], "conf": x[:, 4], "cls": x[:, 5], "extra": x[:, 6:]} for x in outputs]

def pred_to_json(self, predn: Dict[str, torch.Tensor], filename: str) -> None:
    """
    Serialize YOLO predictions to COCO json format.

    Args:
        predn (Dict[str, torch.Tensor]): Predictions dictionary containing 'bboxes', 'conf', and 'cls' keys
            with bounding box coordinates, confidence scores, and class predictions.
        filename (str): Image filename.
    """
    stem = Path(filename).stem
    image_id = int(stem) if stem.isnumeric() else stem
    box = ops.xyxy2xywh(predn["bboxes"])  # xywh
    box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
    for b, s, c in zip(box.tolist(), predn["conf"].tolist(), predn["cls"].tolist()):
        self.jdict.append(
            {
                "image_id": image_id,
                "category_id": self.class_map[int(c)],
                "bbox": [round(x, 3) for x in b],
                "score": round(s, 5),
            }
        )

def preprocess(self, batch: Dict[str, Any]) -> Dict[str, Any]:
    """
    Preprocess batch of images for YOLO validation.

    Args:
        batch (Dict[str, Any]): Batch containing images and annotations.

    Returns:
        (Dict[str, Any]): Preprocessed batch.
    """
    batch["img"] = batch["img"].to(self.device, non_blocking=True)
    batch["img"] = (batch["img"].half() if self.args.half else batch["img"].float()) / 255
    for k in {"batch_idx", "cls", "bboxes"}:
        batch[k] = batch[k].to(self.device)

    return batch

def print_results(self) -> None:
    """Print training/validation set metrics per class."""
    pf = "%22s" + "%11i" * 2 + "%11.3g" * len(self.metrics.keys)  # print format
    LOGGER.info(pf % ("all", self.seen, self.metrics.nt_per_class.sum(), *self.metrics.mean_results()))
    if self.metrics.nt_per_class.sum() == 0:
        LOGGER.warning(f"no labels found in {self.args.task} set, can not compute metrics without labels")

    # Print results per class
    if self.args.verbose and not self.training and self.nc > 1 and len(self.metrics.stats):
        for i, c in enumerate(self.metrics.ap_class_index):
            LOGGER.info(
                pf
                % (
                    self.names[c],
                    self.metrics.nt_per_image[c],
                    self.metrics.nt_per_class[c],
                    *self.metrics.class_result(i),
                )
            )

def save_one_txt(self, predn: Dict[str, torch.Tensor], save_conf: bool, shape: Tuple[int, int], file: Path) -> None:
    """
    Save YOLO detections to a txt file in normalized coordinates in a specific format.

    Args:
        predn (Dict[str, torch.Tensor]): Dictionary containing predictions with keys 'bboxes', 'conf', and 'cls'.
        save_conf (bool): Whether to save confidence scores.
        shape (Tuple[int, int]): Shape of the original image (height, width).
        file (Path): File path to save the detections.
    """
    from ultralytics.engine.results import Results

    Results(
        np.zeros((shape[0], shape[1]), dtype=np.uint8),
        path=None,
        names=self.names,
        boxes=torch.cat([predn["bboxes"], predn["conf"].unsqueeze(-1), predn["cls"].unsqueeze(-1)], dim=1),
    ).save_txt(file, save_conf=save_conf)

def update_metrics(self, preds: List[Dict[str, torch.Tensor]], batch: Dict[str, Any]) -> None:
    """
    Update metrics with new predictions and ground truth.

    Args:
        preds (List[Dict[str, torch.Tensor]]): List of predictions from the model.
        batch (Dict[str, Any]): Batch data containing ground truth.
    """
    for si, pred in enumerate(preds):
        self.seen += 1
        pbatch = self._prepare_batch(si, batch)
        predn = self._prepare_pred(pred, pbatch)

        cls = pbatch["cls"].cpu().numpy()
        no_pred = len(predn["cls"]) == 0
        self.metrics.update_stats(
            {
                **self._process_batch(predn, pbatch),
                "target_cls": cls,
                "target_img": np.unique(cls),
                "conf": np.zeros(0) if no_pred else predn["conf"].cpu().numpy(),
                "pred_cls": np.zeros(0) if no_pred else predn["cls"].cpu().numpy(),
            }
        )
        # Evaluate
        if self.args.plots:
            self.confusion_matrix.process_batch(predn, pbatch, conf=self.args.conf)

        if no_pred:
            continue

        # Save
        if self.args.save_json:
            self.pred_to_json(predn, batch["im_file"][si])
        if self.args.save_txt:
            self.save_one_txt(
                predn,
                self.args.save_conf,
                pbatch["ori_shape"],
                self.save_dir / "labels" / f"{Path(batch['im_file'][si]).stem}.txt",
            )