2025-简单点-ultralytics.models.yolo.detect.predict.py解析

代码

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

from ultralytics.engine.predictor import BasePredictor
from ultralytics.engine.results import Results
from ultralytics.utils import ops


class DetectionPredictor(BasePredictor):
    """
    A class extending the BasePredictor class for prediction based on a detection model.

    Example:
        ```python
        from ultralytics.utils import ASSETS
        from ultralytics.models.yolo.detect import DetectionPredictor

        args = dict(model="yolo11n.pt", source=ASSETS)
        predictor = DetectionPredictor(overrides=args)
        predictor.predict_cli()
        ```
    """

    def postprocess(self, preds, img, orig_imgs, **kwargs):
        """Post-processes predictions and returns a list of Results objects."""
        preds = ops.non_max_suppression(
            preds,
            self.args.conf,
            self.args.iou,
            self.args.classes,
            self.args.agnostic_nms,
            max_det=self.args.max_det,
            nc=len(self.model.names),
            end2end=getattr(self.model, "end2end", False),
            rotated=self.args.task == "obb",
        )

        if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
            orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)

        return self.construct_results(preds, img, orig_imgs, **kwargs)

    def construct_results(self, preds, img, orig_imgs):
        """
        Constructs a list of result objects from the predictions.

        Args:
            preds (List[torch.Tensor]): List of predicted bounding boxes and scores.
            img (torch.Tensor): The image after preprocessing.
            orig_imgs (List[np.ndarray]): List of original images before preprocessing.

        Returns:
            (list): List of result objects containing the original images, image paths, class names, and bounding boxes.
        """
        return [
            self.construct_result(pred, img, orig_img, img_path)
            for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0])
        ]

    def construct_result(self, pred, img, orig_img, img_path):
        """
        Constructs the result object from the prediction.

        Args:
            pred (torch.Tensor): The predicted bounding boxes and scores.
            img (torch.Tensor): The image after preprocessing.
            orig_img (np.ndarray): The original image before preprocessing.
            img_path (str): The path to the original image.

        Returns:
            (Results): The result object containing the original image, image path, class names, and bounding boxes.
        """
        pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
        return Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6])

继承BasePredictor： 有preprocess和pre_transform和stream_inference等方法

自己重写了 postprocess:

主要关注nms和construct_results

construct_results就是构造成独有的Result对象

non_max_pression就是极大值抑制，具体代码如下：

non_max_suppression

def non_max_suppression(
    prediction,
    conf_thres=0.25,
    iou_thres=0.45,
    classes=None,
    agnostic=False,
    multi_label=False,
    labels=(),
    max_det=300,
    nc=0,  # number of classes (optional)
    max_time_img=0.05,
    max_nms=30000,
    max_wh=7680,
    in_place=True,
    rotated=False,
    end2end=False,
):
    """
    Perform non-maximum suppression (NMS) on a set of boxes, with support for masks and multiple labels per box.

    Args:
        prediction (torch.Tensor): A tensor of shape (batch_size, num_classes + 4 + num_masks, num_boxes)
            containing the predicted boxes, classes, and masks. The tensor should be in the format
            output by a model, such as YOLO.
        conf_thres (float): The confidence threshold below which boxes will be filtered out.
            Valid values are between 0.0 and 1.0.
        iou_thres (float): The IoU threshold below which boxes will be filtered out during NMS.
            Valid values are between 0.0 and 1.0.
        classes (List[int]): A list of class indices to consider. If None, all classes will be considered.
        agnostic (bool): If True, the model is agnostic to the number of classes, and all
            classes will be considered as one.
        multi_label (bool): If True, each box may have multiple labels.
        labels (List[List[Union[int, float, torch.Tensor]]]): A list of lists, where each inner
            list contains the apriori labels for a given image. The list should be in the format
            output by a dataloader, with each label being a tuple of (class_index, x1, y1, x2, y2).
        max_det (int): The maximum number of boxes to keep after NMS.
        nc (int, optional): The number of classes output by the model. Any indices after this will be considered masks.
        max_time_img (float): The maximum time (seconds) for processing one image.
        max_nms (int): The maximum number of boxes into torchvision.ops.nms().
        max_wh (int): The maximum box width and height in pixels.
        in_place (bool): If True, the input prediction tensor will be modified in place.
        rotated (bool): If Oriented Bounding Boxes (OBB) are being passed for NMS.
        end2end (bool): If the model doesn't require NMS.

    Returns:
        (List[torch.Tensor]): A list of length batch_size, where each element is a tensor of
            shape (num_boxes, 6 + num_masks) containing the kept boxes, with columns
            (x1, y1, x2, y2, confidence, class, mask1, mask2, ...).
    """
    import torchvision  # scope for faster 'import ultralytics'

    # Checks
    assert 0 <= conf_thres <= 1, f"Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0"
    assert 0 <= iou_thres <= 1, f"Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0"
    if isinstance(prediction, (list, tuple)):  # YOLOv8 model in validation model, output = (inference_out, loss_out)
        prediction = prediction[0]  # select only inference output
    if classes is not None:
        classes = torch.tensor(classes, device=prediction.device)

    if prediction.shape[-1] == 6 or end2end:  # end-to-end model (BNC, i.e. 1,300,6)
        output = [pred[pred[:, 4] > conf_thres][:max_det] for pred in prediction]
        if classes is not None:
            output = [pred[(pred[:, 5:6] == classes).any(1)] for pred in output]
        return output

    bs = prediction.shape[0]  # batch size (BCN, i.e. 1,84,6300)
    nc = nc or (prediction.shape[1] - 4)  # number of classes
    nm = prediction.shape[1] - nc - 4  # number of masks
    mi = 4 + nc  # mask start index
    xc = prediction[:, 4:mi].amax(1) > conf_thres  # candidates

    # Settings
    # min_wh = 2  # (pixels) minimum box width and height
    time_limit = 2.0 + max_time_img * bs  # seconds to quit after
    multi_label &= nc > 1  # multiple labels per box (adds 0.5ms/img)

    prediction = prediction.transpose(-1, -2)  # shape(1,84,6300) to shape(1,6300,84)
    if not rotated:
        if in_place:
            prediction[..., :4] = xywh2xyxy(prediction[..., :4])  # xywh to xyxy
        else:
            prediction = torch.cat((xywh2xyxy(prediction[..., :4]), prediction[..., 4:]), dim=-1)  # xywh to xyxy

    t = time.time()
    output = [torch.zeros((0, 6 + nm), device=prediction.device)] * bs
    for xi, x in enumerate(prediction):  # image index, image inference
        # Apply constraints
        # x[((x[:, 2:4] < min_wh) | (x[:, 2:4] > max_wh)).any(1), 4] = 0  # width-height
        x = x[xc[xi]]  # confidence

        # Cat apriori labels if autolabelling
        if labels and len(labels[xi]) and not rotated:
            lb = labels[xi]
            v = torch.zeros((len(lb), nc + nm + 4), device=x.device)
            v[:, :4] = xywh2xyxy(lb[:, 1:5])  # box
            v[range(len(lb)), lb[:, 0].long() + 4] = 1.0  # cls
            x = torch.cat((x, v), 0)

        # If none remain process next image
        if not x.shape[0]:
            continue

        # Detections matrix nx6 (xyxy, conf, cls)
        box, cls, mask = x.split((4, nc, nm), 1)

        if multi_label:
            i, j = torch.where(cls > conf_thres)
            x = torch.cat((box[i], x[i, 4 + j, None], j[:, None].float(), mask[i]), 1)
        else:  # best class only
            conf, j = cls.max(1, keepdim=True)
            x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres]

        # Filter by class
        if classes is not None:
            x = x[(x[:, 5:6] == classes).any(1)]

        # Check shape
        n = x.shape[0]  # number of boxes
        if not n:  # no boxes
            continue
        if n > max_nms:  # excess boxes
            x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence and remove excess boxes

        # Batched NMS
        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
        scores = x[:, 4]  # scores
        if rotated:
            boxes = torch.cat((x[:, :2] + c, x[:, 2:4], x[:, -1:]), dim=-1)  # xywhr
            i = nms_rotated(boxes, scores, iou_thres)
        else:
            boxes = x[:, :4] + c  # boxes (offset by class)
            i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
        i = i[:max_det]  # limit detections

        # # Experimental
        # merge = False  # use merge-NMS
        # if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
        #     # Update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
        #     from .metrics import box_iou
        #     iou = box_iou(boxes[i], boxes) > iou_thres  # IoU matrix
        #     weights = iou * scores[None]  # box weights
        #     x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
        #     redundant = True  # require redundant detections
        #     if redundant:
        #         i = i[iou.sum(1) > 1]  # require redundancy

        output[xi] = x[i]
        if (time.time() - t) > time_limit:
            LOGGER.warning(f"WARNING ⚠️ NMS time limit {time_limit:.3f}s exceeded")
            break  # time limit exceeded

    return output

核心是一个这个：

 i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS

ops.scale_boxes

def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None, padding=True, xywh=False):
    """
    Rescales bounding boxes (in the format of xyxy by default) from the shape of the image they were originally
    specified in (img1_shape) to the shape of a different image (img0_shape).

    Args:
        img1_shape (tuple): The shape of the image that the bounding boxes are for, in the format of (height, width).
        boxes (torch.Tensor): the bounding boxes of the objects in the image, in the format of (x1, y1, x2, y2)
        img0_shape (tuple): the shape of the target image, in the format of (height, width).
        ratio_pad (tuple): a tuple of (ratio, pad) for scaling the boxes. If not provided, the ratio and pad will be
            calculated based on the size difference between the two images.
        padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular
            rescaling.
        xywh (bool): The box format is xywh or not, default=False.

    Returns:
        boxes (torch.Tensor): The scaled bounding boxes, in the format of (x1, y1, x2, y2)
    """
    if ratio_pad is None:  # calculate from img0_shape
        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
        pad = (
            round((img1_shape[1] - img0_shape[1] * gain) / 2 - 0.1),
            round((img1_shape[0] - img0_shape[0] * gain) / 2 - 0.1),
        )  # wh padding
    else:
        gain = ratio_pad[0][0]
        pad = ratio_pad[1]

    if padding:
        boxes[..., 0] -= pad[0]  # x padding
        boxes[..., 1] -= pad[1]  # y padding
        if not xywh:
            boxes[..., 2] -= pad[0]  # x padding
            boxes[..., 3] -= pad[1]  # y padding
    boxes[..., :4] /= gain
    return clip_boxes(boxes, img0_shape)

老东西了，扣除padding后，除以gain，返回到最初的大小。这里有个clip_boxes:

def clip_boxes(boxes, shape):
    """
    Takes a list of bounding boxes and a shape (height, width) and clips the bounding boxes to the shape.

    Args:
        boxes (torch.Tensor): The bounding boxes to clip.
        shape (tuple): The shape of the image.

    Returns:
        (torch.Tensor | numpy.ndarray): The clipped boxes.
    """
    if isinstance(boxes, torch.Tensor):  # faster individually (WARNING: inplace .clamp_() Apple MPS bug)
        boxes[..., 0] = boxes[..., 0].clamp(0, shape[1])  # x1
        boxes[..., 1] = boxes[..., 1].clamp(0, shape[0])  # y1
        boxes[..., 2] = boxes[..., 2].clamp(0, shape[1])  # x2
        boxes[..., 3] = boxes[..., 3].clamp(0, shape[0])  # y2
    else:  # np.array (faster grouped)
        boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, shape[1])  # x1, x2
        boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, shape[0])  # y1, y2
    return boxes

就是个控制上下界，避免计算错误