─░├žeri─če ge├ž

Referans i├žin ultralytics/models/fastsam/predict.py

Not

Bu dosya https://github.com/ultralytics/ultralytics/blob/main/ ultralytics/models/ fastsam/predict .py adresinde mevcuttur. Bir sorun tespit ederseniz l├╝tfen bir ├çekme ─░ste─či ­čŤá´ŞĆ ile katk─▒da bulunarak d├╝zeltilmesine yard─▒mc─▒ olun. Te┼čekk├╝rler ­čÖĆ!



ultralytics.models.fastsam.predict.FastSAMPredictor

├ťsler: DetectionPredictor

FastSAMPredictor, Ultralytics YOLO ├žer├ževesinde h─▒zl─▒ SAM (Segment Anything Model) segmentasyon tahmin g├Ârevleri i├žin ├Âzelle┼čtirilmi┼čtir.

Bu s─▒n─▒f DetectionPredictor'─▒ geni┼čleterek tahmin i┼člem hatt─▒n─▒ ├Âzellikle h─▒zl─▒ SAM i├žin ├Âzelle┼čtirir. Maske tahminini ve maksimum olmayan bast─▒rmay─▒ dahil etmek i├žin i┼člem sonras─▒ ad─▒mlar─▒ ayarlarken tek s─▒n─▒fl─▒ segmentasyon i├žin.

Nitelikler:

─░sim Tip A├ž─▒klama
cfg dict

Tahmin i├žin konfig├╝rasyon parametreleri.

overrides dict

├ľzel davran─▒┼č i├žin iste─če ba─čl─▒ parametre ge├žersiz k─▒lmalar─▒.

_callbacks dict

Tahmin s─▒ras─▒nda ├ža─čr─▒lacak geri arama i┼člevlerinin iste─če ba─čl─▒ listesi.

Kaynak kodu ultralytics/models/fastsam/predict.py
class FastSAMPredictor(DetectionPredictor):
    """
    FastSAMPredictor is specialized for fast SAM (Segment Anything Model) segmentation prediction tasks in Ultralytics
    YOLO framework.

    This class extends the DetectionPredictor, customizing the prediction pipeline specifically for fast SAM.
    It adjusts post-processing steps to incorporate mask prediction and non-max suppression while optimizing
    for single-class segmentation.

    Attributes:
        cfg (dict): Configuration parameters for prediction.
        overrides (dict, optional): Optional parameter overrides for custom behavior.
        _callbacks (dict, optional): Optional list of callback functions to be invoked during prediction.
    """

    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
        """
        Initializes the FastSAMPredictor class, inheriting from DetectionPredictor and setting the task to 'segment'.

        Args:
            cfg (dict): Configuration parameters for prediction.
            overrides (dict, optional): Optional parameter overrides for custom behavior.
            _callbacks (dict, optional): Optional list of callback functions to be invoked during prediction.
        """
        super().__init__(cfg, overrides, _callbacks)
        self.args.task = "segment"

    def postprocess(self, preds, img, orig_imgs):
        """
        Perform post-processing steps on predictions, including non-max suppression and scaling boxes to original image
        size, and returns the final results.

        Args:
            preds (list): The raw output predictions from the model.
            img (torch.Tensor): The processed image tensor.
            orig_imgs (list | torch.Tensor): The original image or list of images.

        Returns:
            (list): A list of Results objects, each containing processed boxes, masks, and other metadata.
        """
        p = ops.non_max_suppression(
            preds[0],
            self.args.conf,
            self.args.iou,
            agnostic=self.args.agnostic_nms,
            max_det=self.args.max_det,
            nc=1,  # set to 1 class since SAM has no class predictions
            classes=self.args.classes,
        )
        full_box = torch.zeros(p[0].shape[1], device=p[0].device)
        full_box[2], full_box[3], full_box[4], full_box[6:] = img.shape[3], img.shape[2], 1.0, 1.0
        full_box = full_box.view(1, -1)
        critical_iou_index = bbox_iou(full_box[0][:4], p[0][:, :4], iou_thres=0.9, image_shape=img.shape[2:])
        if critical_iou_index.numel() != 0:
            full_box[0][4] = p[0][critical_iou_index][:, 4]
            full_box[0][6:] = p[0][critical_iou_index][:, 6:]
            p[0][critical_iou_index] = full_box

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

        results = []
        proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
        for i, pred in enumerate(p):
            orig_img = orig_imgs[i]
            img_path = self.batch[0][i]
            if not len(pred):  # save empty boxes
                masks = None
            elif self.args.retina_masks:
                pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
                masks = ops.process_mask_native(proto[i], pred[:, 6:], pred[:, :4], orig_img.shape[:2])  # HWC
            else:
                masks = ops.process_mask(proto[i], pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True)  # HWC
                pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
            results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks))
        return results

__init__(cfg=DEFAULT_CFG, overrides=None, _callbacks=None)

FastSAMPredictor s─▒n─▒f─▒n─▒ ba┼člat─▒r, DetectionPredictor'dan miras al─▒r ve g├Ârevi 'segment' olarak ayarlar.

Parametreler:

─░sim Tip A├ž─▒klama Varsay─▒lan
cfg dict

Tahmin i├žin konfig├╝rasyon parametreleri.

DEFAULT_CFG
overrides dict

├ľzel davran─▒┼č i├žin iste─če ba─čl─▒ parametre ge├žersiz k─▒lmalar─▒.

None
_callbacks dict

Tahmin s─▒ras─▒nda ├ža─čr─▒lacak geri arama i┼člevlerinin iste─če ba─čl─▒ listesi.

None
Kaynak kodu ultralytics/models/fastsam/predict.py
def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
    """
    Initializes the FastSAMPredictor class, inheriting from DetectionPredictor and setting the task to 'segment'.

    Args:
        cfg (dict): Configuration parameters for prediction.
        overrides (dict, optional): Optional parameter overrides for custom behavior.
        _callbacks (dict, optional): Optional list of callback functions to be invoked during prediction.
    """
    super().__init__(cfg, overrides, _callbacks)
    self.args.task = "segment"

postprocess(preds, img, orig_imgs)

Tahminler ├╝zerinde, maksimum olmayan bast─▒rma ve kutular─▒ orijinal g├Âr├╝nt├╝ye ├Âl├žeklendirme dahil olmak ├╝zere i┼člem sonras─▒ ad─▒mlar─▒ ger├žekle┼čtirin boyutunu belirler ve nihai sonu├žlar─▒ d├Ând├╝r├╝r.

Parametreler:

─░sim Tip A├ž─▒klama Varsay─▒lan
preds list

Modelden elde edilen ham ├ž─▒kt─▒ tahminleri.

gerekli
img Tensor

─░┼členmi┼č g├Âr├╝nt├╝ tensor.

gerekli
orig_imgs list | Tensor

Orijinal g├Âr├╝nt├╝ veya g├Âr├╝nt├╝ listesi.

gerekli

─░ade:

Tip A├ž─▒klama
list

Her biri i┼členmi┼č kutular, maskeler ve di─čer meta verileri i├žeren Sonu├ž nesnelerinin bir listesi.

Kaynak kodu ultralytics/models/fastsam/predict.py
def postprocess(self, preds, img, orig_imgs):
    """
    Perform post-processing steps on predictions, including non-max suppression and scaling boxes to original image
    size, and returns the final results.

    Args:
        preds (list): The raw output predictions from the model.
        img (torch.Tensor): The processed image tensor.
        orig_imgs (list | torch.Tensor): The original image or list of images.

    Returns:
        (list): A list of Results objects, each containing processed boxes, masks, and other metadata.
    """
    p = ops.non_max_suppression(
        preds[0],
        self.args.conf,
        self.args.iou,
        agnostic=self.args.agnostic_nms,
        max_det=self.args.max_det,
        nc=1,  # set to 1 class since SAM has no class predictions
        classes=self.args.classes,
    )
    full_box = torch.zeros(p[0].shape[1], device=p[0].device)
    full_box[2], full_box[3], full_box[4], full_box[6:] = img.shape[3], img.shape[2], 1.0, 1.0
    full_box = full_box.view(1, -1)
    critical_iou_index = bbox_iou(full_box[0][:4], p[0][:, :4], iou_thres=0.9, image_shape=img.shape[2:])
    if critical_iou_index.numel() != 0:
        full_box[0][4] = p[0][critical_iou_index][:, 4]
        full_box[0][6:] = p[0][critical_iou_index][:, 6:]
        p[0][critical_iou_index] = full_box

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

    results = []
    proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
    for i, pred in enumerate(p):
        orig_img = orig_imgs[i]
        img_path = self.batch[0][i]
        if not len(pred):  # save empty boxes
            masks = None
        elif self.args.retina_masks:
            pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
            masks = ops.process_mask_native(proto[i], pred[:, 6:], pred[:, :4], orig_img.shape[:2])  # HWC
        else:
            masks = ops.process_mask(proto[i], pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True)  # HWC
            pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
        results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks))
    return results





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