์ฝ˜ํ…์ธ ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ

์ฐธ์กฐ ultralytics/models/yolo/segment/val.py

์ฐธ๊ณ 

์ด ํŒŒ์ผ์€ https://github.com/ultralytics/ ultralytics/blob/main/ ultralytics/models/ yolo/segment/val .py์—์„œ ํ™•์ธํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ๋ฌธ์ œ๋ฅผ ๋ฐœ๊ฒฌํ•˜๋ฉด ํ’€ ๋ฆฌํ€˜์ŠคํŠธ ๐Ÿ› ๏ธ ์— ๊ธฐ์—ฌํ•˜์—ฌ ๋ฌธ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜๋„๋ก ๋„์™€์ฃผ์„ธ์š”. ๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค ๐Ÿ™!



ultralytics.models.yolo.segment.val.SegmentationValidator

๋ฒ ์ด์Šค: DetectionValidator

์„ธ๋ถ„ํ™” ๋ชจ๋ธ์— ๊ธฐ๋ฐ˜ํ•œ ์œ ํšจ์„ฑ ๊ฒ€์‚ฌ๋ฅผ ์œ„ํ•ด DetectionValidator ํด๋ž˜์Šค๋ฅผ ํ™•์žฅํ•˜๋Š” ํด๋ž˜์Šค์ž…๋‹ˆ๋‹ค.

์˜ˆ
from ultralytics.models.yolo.segment import SegmentationValidator

args = dict(model='yolov8n-seg.pt', data='coco8-seg.yaml')
validator = SegmentationValidator(args=args)
validator()
์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
class SegmentationValidator(DetectionValidator):
    """
    A class extending the DetectionValidator class for validation based on a segmentation model.

    Example:
        ```python
        from ultralytics.models.yolo.segment import SegmentationValidator

        args = dict(model='yolov8n-seg.pt', data='coco8-seg.yaml')
        validator = SegmentationValidator(args=args)
        validator()
        ```
    """

    def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
        """Initialize SegmentationValidator and set task to 'segment', metrics to SegmentMetrics."""
        super().__init__(dataloader, save_dir, pbar, args, _callbacks)
        self.plot_masks = None
        self.process = None
        self.args.task = "segment"
        self.metrics = SegmentMetrics(save_dir=self.save_dir, on_plot=self.on_plot)

    def preprocess(self, batch):
        """Preprocesses batch by converting masks to float and sending to device."""
        batch = super().preprocess(batch)
        batch["masks"] = batch["masks"].to(self.device).float()
        return batch

    def init_metrics(self, model):
        """Initialize metrics and select mask processing function based on save_json flag."""
        super().init_metrics(model)
        self.plot_masks = []
        if self.args.save_json:
            check_requirements("pycocotools>=2.0.6")
            self.process = ops.process_mask_upsample  # more accurate
        else:
            self.process = ops.process_mask  # faster
        self.stats = dict(tp_m=[], tp=[], conf=[], pred_cls=[], target_cls=[], target_img=[])

    def get_desc(self):
        """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 postprocess(self, preds):
        """Post-processes YOLO predictions and returns output detections with proto."""
        p = ops.non_max_suppression(
            preds[0],
            self.args.conf,
            self.args.iou,
            labels=self.lb,
            multi_label=True,
            agnostic=self.args.single_cls,
            max_det=self.args.max_det,
            nc=self.nc,
        )
        proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
        return p, proto

    def _prepare_batch(self, si, batch):
        """Prepares a batch for training or inference by processing images and targets."""
        prepared_batch = super()._prepare_batch(si, batch)
        midx = [si] if self.args.overlap_mask else batch["batch_idx"] == si
        prepared_batch["masks"] = batch["masks"][midx]
        return prepared_batch

    def _prepare_pred(self, pred, pbatch, proto):
        """Prepares a batch for training or inference by processing images and targets."""
        predn = super()._prepare_pred(pred, pbatch)
        pred_masks = self.process(proto, pred[:, 6:], pred[:, :4], shape=pbatch["imgsz"])
        return predn, pred_masks

    def update_metrics(self, preds, batch):
        """Metrics."""
        for si, (pred, proto) in enumerate(zip(preds[0], preds[1])):
            self.seen += 1
            npr = len(pred)
            stat = dict(
                conf=torch.zeros(0, device=self.device),
                pred_cls=torch.zeros(0, device=self.device),
                tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
                tp_m=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
            )
            pbatch = self._prepare_batch(si, batch)
            cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox")
            nl = len(cls)
            stat["target_cls"] = cls
            stat["target_img"] = cls.unique()
            if npr == 0:
                if nl:
                    for k in self.stats.keys():
                        self.stats[k].append(stat[k])
                    if self.args.plots:
                        self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls)
                continue

            # Masks
            gt_masks = pbatch.pop("masks")
            # Predictions
            if self.args.single_cls:
                pred[:, 5] = 0
            predn, pred_masks = self._prepare_pred(pred, pbatch, proto)
            stat["conf"] = predn[:, 4]
            stat["pred_cls"] = predn[:, 5]

            # Evaluate
            if nl:
                stat["tp"] = self._process_batch(predn, bbox, cls)
                stat["tp_m"] = self._process_batch(
                    predn, bbox, cls, pred_masks, gt_masks, self.args.overlap_mask, masks=True
                )
                if self.args.plots:
                    self.confusion_matrix.process_batch(predn, bbox, cls)

            for k in self.stats.keys():
                self.stats[k].append(stat[k])

            pred_masks = torch.as_tensor(pred_masks, dtype=torch.uint8)
            if self.args.plots and self.batch_i < 3:
                self.plot_masks.append(pred_masks[:15].cpu())  # filter top 15 to plot

            # Save
            if self.args.save_json:
                pred_masks = ops.scale_image(
                    pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(),
                    pbatch["ori_shape"],
                    ratio_pad=batch["ratio_pad"][si],
                )
                self.pred_to_json(predn, batch["im_file"][si], pred_masks)
            # if self.args.save_txt:
            #    save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt')

    def finalize_metrics(self, *args, **kwargs):
        """Sets speed and confusion matrix for evaluation metrics."""
        self.metrics.speed = self.speed
        self.metrics.confusion_matrix = self.confusion_matrix

    def _process_batch(self, detections, gt_bboxes, gt_cls, pred_masks=None, gt_masks=None, overlap=False, masks=False):
        """
        Return correct prediction matrix.

        Args:
            detections (array[N, 6]), x1, y1, x2, y2, conf, class
            labels (array[M, 5]), class, x1, y1, x2, y2

        Returns:
            correct (array[N, 10]), for 10 IoU levels
        """
        if masks:
            if overlap:
                nl = len(gt_cls)
                index = torch.arange(nl, device=gt_masks.device).view(nl, 1, 1) + 1
                gt_masks = gt_masks.repeat(nl, 1, 1)  # shape(1,640,640) -> (n,640,640)
                gt_masks = torch.where(gt_masks == index, 1.0, 0.0)
            if gt_masks.shape[1:] != pred_masks.shape[1:]:
                gt_masks = F.interpolate(gt_masks[None], pred_masks.shape[1:], mode="bilinear", align_corners=False)[0]
                gt_masks = gt_masks.gt_(0.5)
            iou = mask_iou(gt_masks.view(gt_masks.shape[0], -1), pred_masks.view(pred_masks.shape[0], -1))
        else:  # boxes
            iou = box_iou(gt_bboxes, detections[:, :4])

        return self.match_predictions(detections[:, 5], gt_cls, iou)

    def plot_val_samples(self, batch, ni):
        """Plots validation samples with bounding box labels."""
        plot_images(
            batch["img"],
            batch["batch_idx"],
            batch["cls"].squeeze(-1),
            batch["bboxes"],
            masks=batch["masks"],
            paths=batch["im_file"],
            fname=self.save_dir / f"val_batch{ni}_labels.jpg",
            names=self.names,
            on_plot=self.on_plot,
        )

    def plot_predictions(self, batch, preds, ni):
        """Plots batch predictions with masks and bounding boxes."""
        plot_images(
            batch["img"],
            *output_to_target(preds[0], max_det=15),  # not set to self.args.max_det due to slow plotting speed
            torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks,
            paths=batch["im_file"],
            fname=self.save_dir / f"val_batch{ni}_pred.jpg",
            names=self.names,
            on_plot=self.on_plot,
        )  # pred
        self.plot_masks.clear()

    def pred_to_json(self, predn, filename, pred_masks):
        """
        Save one JSON result.

        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[:, :4])  # xywh
        box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
        pred_masks = np.transpose(pred_masks, (2, 0, 1))
        with ThreadPool(NUM_THREADS) as pool:
            rles = pool.map(single_encode, pred_masks)
        for i, (p, b) in enumerate(zip(predn.tolist(), box.tolist())):
            self.jdict.append(
                {
                    "image_id": image_id,
                    "category_id": self.class_map[int(p[5])],
                    "bbox": [round(x, 3) for x in b],
                    "score": round(p[4], 5),
                    "segmentation": rles[i],
                }
            )

    def eval_json(self, stats):
        """Return COCO-style object detection evaluation metrics."""
        if self.args.save_json and self.is_coco and len(self.jdict):
            anno_json = self.data["path"] / "annotations/instances_val2017.json"  # annotations
            pred_json = self.save_dir / "predictions.json"  # predictions
            LOGGER.info(f"\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...")
            try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
                check_requirements("pycocotools>=2.0.6")
                from pycocotools.coco import COCO  # noqa
                from pycocotools.cocoeval import COCOeval  # noqa

                for x in anno_json, pred_json:
                    assert x.is_file(), f"{x} file not found"
                anno = COCO(str(anno_json))  # init annotations api
                pred = anno.loadRes(str(pred_json))  # init predictions api (must pass string, not Path)
                for i, eval in enumerate([COCOeval(anno, pred, "bbox"), COCOeval(anno, pred, "segm")]):
                    if self.is_coco:
                        eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # im to eval
                    eval.evaluate()
                    eval.accumulate()
                    eval.summarize()
                    idx = i * 4 + 2
                    stats[self.metrics.keys[idx + 1]], stats[self.metrics.keys[idx]] = eval.stats[
                        :2
                    ]  # update mAP50-95 and mAP50
            except Exception as e:
                LOGGER.warning(f"pycocotools unable to run: {e}")
        return stats

__init__(dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None)

์„ธ๊ทธ๋จผํŠธ ๊ฒ€์ฆ๊ธฐ๋ฅผ ์ดˆ๊ธฐํ™”ํ•˜๊ณ  ์ž‘์—…์„ '์„ธ๊ทธ๋จผํŠธ'๋กœ, ๋ฉ”ํŠธ๋ฆญ์„ ์„ธ๊ทธ๋จผํŠธ๋ฉ”ํŠธ๋ฆญ์œผ๋กœ ์„ค์ •ํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
    """Initialize SegmentationValidator and set task to 'segment', metrics to SegmentMetrics."""
    super().__init__(dataloader, save_dir, pbar, args, _callbacks)
    self.plot_masks = None
    self.process = None
    self.args.task = "segment"
    self.metrics = SegmentMetrics(save_dir=self.save_dir, on_plot=self.on_plot)

eval_json(stats)

COCO ์Šคํƒ€์ผ์˜ ๊ฐ์ฒด ๊ฐ์ง€ ํ‰๊ฐ€ ์ง€ํ‘œ๋ฅผ ๋ฐ˜ํ™˜ํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def eval_json(self, stats):
    """Return COCO-style object detection evaluation metrics."""
    if self.args.save_json and self.is_coco and len(self.jdict):
        anno_json = self.data["path"] / "annotations/instances_val2017.json"  # annotations
        pred_json = self.save_dir / "predictions.json"  # predictions
        LOGGER.info(f"\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...")
        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
            check_requirements("pycocotools>=2.0.6")
            from pycocotools.coco import COCO  # noqa
            from pycocotools.cocoeval import COCOeval  # noqa

            for x in anno_json, pred_json:
                assert x.is_file(), f"{x} file not found"
            anno = COCO(str(anno_json))  # init annotations api
            pred = anno.loadRes(str(pred_json))  # init predictions api (must pass string, not Path)
            for i, eval in enumerate([COCOeval(anno, pred, "bbox"), COCOeval(anno, pred, "segm")]):
                if self.is_coco:
                    eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # im to eval
                eval.evaluate()
                eval.accumulate()
                eval.summarize()
                idx = i * 4 + 2
                stats[self.metrics.keys[idx + 1]], stats[self.metrics.keys[idx]] = eval.stats[
                    :2
                ]  # update mAP50-95 and mAP50
        except Exception as e:
            LOGGER.warning(f"pycocotools unable to run: {e}")
    return stats

finalize_metrics(*args, **kwargs)

ํ‰๊ฐ€ ์ง€ํ‘œ์— ๋Œ€ํ•œ ์†๋„ ๋ฐ ํ˜ผ๋™ ํ–‰๋ ฌ์„ ์„ค์ •ํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def finalize_metrics(self, *args, **kwargs):
    """Sets speed and confusion matrix for evaluation metrics."""
    self.metrics.speed = self.speed
    self.metrics.confusion_matrix = self.confusion_matrix

get_desc()

ํ‰๊ฐ€ ์ง€ํ‘œ์— ๋Œ€ํ•œ ํ˜•์‹ํ™”๋œ ์„ค๋ช…์„ ๋ฐ˜ํ™˜ํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def get_desc(self):
    """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)",
    )

init_metrics(model)

๋ฉ”ํŠธ๋ฆญ์„ ์ดˆ๊ธฐํ™”ํ•˜๊ณ  save_json ํ”Œ๋ž˜๊ทธ์— ๋”ฐ๋ผ ๋งˆ์Šคํฌ ์ฒ˜๋ฆฌ ๊ธฐ๋Šฅ์„ ์„ ํƒํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def init_metrics(self, model):
    """Initialize metrics and select mask processing function based on save_json flag."""
    super().init_metrics(model)
    self.plot_masks = []
    if self.args.save_json:
        check_requirements("pycocotools>=2.0.6")
        self.process = ops.process_mask_upsample  # more accurate
    else:
        self.process = ops.process_mask  # faster
    self.stats = dict(tp_m=[], tp=[], conf=[], pred_cls=[], target_cls=[], target_img=[])

plot_predictions(batch, preds, ni)

๋งˆ์Šคํฌ ๋ฐ ๊ฒฝ๊ณ„ ์ƒ์ž๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๋ฐฐ์น˜ ์˜ˆ์ธก์„ ํ”Œ๋กฏํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def plot_predictions(self, batch, preds, ni):
    """Plots batch predictions with masks and bounding boxes."""
    plot_images(
        batch["img"],
        *output_to_target(preds[0], max_det=15),  # not set to self.args.max_det due to slow plotting speed
        torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks,
        paths=batch["im_file"],
        fname=self.save_dir / f"val_batch{ni}_pred.jpg",
        names=self.names,
        on_plot=self.on_plot,
    )  # pred
    self.plot_masks.clear()

plot_val_samples(batch, ni)

๋ฐ”์šด๋”ฉ ๋ฐ•์Šค ๋ ˆ์ด๋ธ”์„ ์‚ฌ์šฉํ•˜์—ฌ ์œ ํšจ์„ฑ ๊ฒ€์‚ฌ ์ƒ˜ํ”Œ์„ ํ”Œ๋กฏํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def plot_val_samples(self, batch, ni):
    """Plots validation samples with bounding box labels."""
    plot_images(
        batch["img"],
        batch["batch_idx"],
        batch["cls"].squeeze(-1),
        batch["bboxes"],
        masks=batch["masks"],
        paths=batch["im_file"],
        fname=self.save_dir / f"val_batch{ni}_labels.jpg",
        names=self.names,
        on_plot=self.on_plot,
    )

postprocess(preds)

YOLO ์˜ˆ์ธก์„ ํ›„์ฒ˜๋ฆฌํ•˜๊ณ  ํ”„๋กœํ† ๋กœ ์ถœ๋ ฅ ๊ฐ์ง€๋ฅผ ๋ฐ˜ํ™˜ํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def postprocess(self, preds):
    """Post-processes YOLO predictions and returns output detections with proto."""
    p = ops.non_max_suppression(
        preds[0],
        self.args.conf,
        self.args.iou,
        labels=self.lb,
        multi_label=True,
        agnostic=self.args.single_cls,
        max_det=self.args.max_det,
        nc=self.nc,
    )
    proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
    return p, proto

pred_to_json(predn, filename, pred_masks)

JSON ๊ฒฐ๊ณผ ํ•˜๋‚˜๋ฅผ ์ €์žฅํ•ฉ๋‹ˆ๋‹ค.

์˜ˆ์‹œ:

>>> result = {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}
์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def pred_to_json(self, predn, filename, pred_masks):
    """
    Save one JSON result.

    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[:, :4])  # xywh
    box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
    pred_masks = np.transpose(pred_masks, (2, 0, 1))
    with ThreadPool(NUM_THREADS) as pool:
        rles = pool.map(single_encode, pred_masks)
    for i, (p, b) in enumerate(zip(predn.tolist(), box.tolist())):
        self.jdict.append(
            {
                "image_id": image_id,
                "category_id": self.class_map[int(p[5])],
                "bbox": [round(x, 3) for x in b],
                "score": round(p[4], 5),
                "segmentation": rles[i],
            }
        )

preprocess(batch)

๋งˆ์Šคํฌ๋ฅผ ํ”Œ๋กœํŠธ๋กœ ๋ณ€ํ™˜ํ•˜๊ณ  ๋””๋ฐ”์ด์Šค๋กœ ์ „์†กํ•˜์—ฌ ์ผ๊ด„ ์ฒ˜๋ฆฌ๋ฅผ ์‚ฌ์ „ ์ฒ˜๋ฆฌํ•ฉ๋‹ˆ๋‹ค.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def preprocess(self, batch):
    """Preprocesses batch by converting masks to float and sending to device."""
    batch = super().preprocess(batch)
    batch["masks"] = batch["masks"].to(self.device).float()
    return batch

update_metrics(preds, batch)

๋ฉ”ํŠธ๋ฆญ.

์˜ ์†Œ์Šค ์ฝ”๋“œ ultralytics/models/yolo/segment/val.py
def update_metrics(self, preds, batch):
    """Metrics."""
    for si, (pred, proto) in enumerate(zip(preds[0], preds[1])):
        self.seen += 1
        npr = len(pred)
        stat = dict(
            conf=torch.zeros(0, device=self.device),
            pred_cls=torch.zeros(0, device=self.device),
            tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
            tp_m=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
        )
        pbatch = self._prepare_batch(si, batch)
        cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox")
        nl = len(cls)
        stat["target_cls"] = cls
        stat["target_img"] = cls.unique()
        if npr == 0:
            if nl:
                for k in self.stats.keys():
                    self.stats[k].append(stat[k])
                if self.args.plots:
                    self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls)
            continue

        # Masks
        gt_masks = pbatch.pop("masks")
        # Predictions
        if self.args.single_cls:
            pred[:, 5] = 0
        predn, pred_masks = self._prepare_pred(pred, pbatch, proto)
        stat["conf"] = predn[:, 4]
        stat["pred_cls"] = predn[:, 5]

        # Evaluate
        if nl:
            stat["tp"] = self._process_batch(predn, bbox, cls)
            stat["tp_m"] = self._process_batch(
                predn, bbox, cls, pred_masks, gt_masks, self.args.overlap_mask, masks=True
            )
            if self.args.plots:
                self.confusion_matrix.process_batch(predn, bbox, cls)

        for k in self.stats.keys():
            self.stats[k].append(stat[k])

        pred_masks = torch.as_tensor(pred_masks, dtype=torch.uint8)
        if self.args.plots and self.batch_i < 3:
            self.plot_masks.append(pred_masks[:15].cpu())  # filter top 15 to plot

        # Save
        if self.args.save_json:
            pred_masks = ops.scale_image(
                pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(),
                pbatch["ori_shape"],
                ratio_pad=batch["ratio_pad"][si],
            )
            self.pred_to_json(predn, batch["im_file"][si], pred_masks)





Created 2023-11-12, Updated 2024-06-02
Authors: glenn-jocher (5), Burhan-Q (1)