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

def eval_json(self, stats: Dict[str, Any]) -> Dict[str, Any]:
    """Return COCO-style instance segmentation evaluation metrics."""
    if self.args.save_json and (self.is_lvis or self.is_coco) and len(self.jdict):
        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

        pkg = "pycocotools" if self.is_coco else "lvis"
        LOGGER.info(f"\nEvaluating {pkg} mAP using {pred_json} and {anno_json}...")
        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
            for x in anno_json, pred_json:
                assert x.is_file(), f"{x} file not found"
            check_requirements("pycocotools>=2.0.6" if self.is_coco else "lvis>=0.5.3")
            if self.is_coco:
                from pycocotools.coco import COCO  # noqa
                from pycocotools.cocoeval import COCOeval  # noqa

                anno = COCO(str(anno_json))  # init annotations api
                pred = anno.loadRes(str(pred_json))  # init predictions api (must pass string, not Path)
                vals = [COCOeval(anno, pred, "bbox"), COCOeval(anno, pred, "segm")]
            else:
                from lvis import LVIS, LVISEval

                anno = LVIS(str(anno_json))
                pred = anno._load_json(str(pred_json))
                vals = [LVISEval(anno, pred, "bbox"), LVISEval(anno, pred, "segm")]

            for i, eval in enumerate(vals):
                eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # im to eval
                eval.evaluate()
                eval.accumulate()
                eval.summarize()
                if self.is_lvis:
                    eval.print_results()
                idx = i * 4 + 2
                # update mAP50-95 and mAP50
                stats[self.metrics.keys[idx + 1]], stats[self.metrics.keys[idx]] = (
                    eval.stats[:2] if self.is_coco else [eval.results["AP"], eval.results["AP50"]]
                )
                if self.is_lvis:
                    tag = "B" if i == 0 else "M"
                    stats[f"metrics/APr({tag})"] = eval.results["APr"]
                    stats[f"metrics/APc({tag})"] = eval.results["APc"]
                    stats[f"metrics/APf({tag})"] = eval.results["APf"]

            if self.is_lvis:
                stats["fitness"] = stats["metrics/mAP50-95(B)"]

        except Exception as e:
            LOGGER.warning(f"{pkg} unable to run: {e}")
    return stats

def get_desc(self) -> str:
    """Return a formatted description of evaluation metrics."""
    return ("%22s" + "%11s" * 10) % (
        "Class",
        "Images",
        "Instances",
        "Box(P",
        "R",
        "mAP50",
        "mAP50-95)",
        "Mask(P",
        "R",
        "mAP50",
        "mAP50-95)",
    )

def init_metrics(self, model: torch.nn.Module) -> None:
    """
    Initialize metrics and select mask processing function based on save_json flag.

    Args:
        model (torch.nn.Module): Model to validate.
    """
    super().init_metrics(model)
    if self.args.save_json:
        check_requirements("pycocotools>=2.0.6")
    # More accurate vs faster
    self.process = ops.process_mask_native if self.args.save_json or self.args.save_txt else ops.process_mask

def plot_predictions(self, batch: Dict[str, Any], preds: List[Dict[str, torch.Tensor]], ni: int) -> None:
    """
    Plot batch predictions with masks and bounding boxes.

    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.
    """
    for p in preds:
        masks = p["masks"]
        if masks.shape[0] > 50:
            LOGGER.warning("Limiting validation plots to first 50 items per image for speed...")
        p["masks"] = torch.as_tensor(masks[:50], dtype=torch.uint8).cpu()
    super().plot_predictions(batch, preds, ni, max_det=50)  # plot bboxes

def postprocess(self, preds: List[torch.Tensor]) -> List[Dict[str, torch.Tensor]]:
    """
    Post-process YOLO predictions and return output detections with proto.

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

    Returns:
        List[Dict[str, torch.Tensor]]: Processed detection predictions with masks.
    """
    proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
    preds = super().postprocess(preds[0])
    imgsz = [4 * x for x in proto.shape[2:]]  # get image size from proto
    for i, pred in enumerate(preds):
        coefficient = pred.pop("extra")
        pred["masks"] = (
            self.process(proto[i], coefficient, pred["bboxes"], shape=imgsz)
            if len(coefficient)
            else torch.zeros((0, imgsz[0], imgsz[1]), dtype=torch.uint8, device=pred["bboxes"].device)
        )
    return preds

def pred_to_json(self, predn: torch.Tensor, filename: str) -> None:
    """
    Save one JSON result for COCO evaluation.

    Args:
        predn (Dict[str, torch.Tensor]): Predictions containing bboxes, masks, confidence scores, and classes.
        filename (str): Image filename.

    Examples:
         >>> result = {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}
    """
    from pycocotools.mask import encode  # noqa

    def single_encode(x):
        """Encode predicted masks as RLE and append results to jdict."""
        rle = encode(np.asarray(x[:, :, None], order="F", dtype="uint8"))[0]
        rle["counts"] = rle["counts"].decode("utf-8")
        return rle

    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
    pred_masks = np.transpose(predn["coco_masks"], (2, 0, 1))
    with ThreadPool(NUM_THREADS) as pool:
        rles = pool.map(single_encode, pred_masks)
    for i, (b, s, c) in enumerate(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),
                "segmentation": rles[i],
            }
        )

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

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

    Returns:
        (Dict[str, Any]): Preprocessed batch.
    """
    batch = super().preprocess(batch)
    batch["masks"] = batch["masks"].to(self.device).float()
    return batch

def save_one_txt(self, predn: 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 (torch.Tensor): Predictions in the format (x1, y1, x2, y2, conf, class).
        save_conf (bool): Whether to save confidence scores.
        shape (Tuple[int, int]): Shape of the original image.
        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),
        masks=torch.as_tensor(predn["masks"], dtype=torch.uint8),
    ).save_txt(file, save_conf=save_conf)