Zum Inhalt springen

Referenz fĂŒr ultralytics/models/sam/predict.py

Hinweis

Diese Datei ist verfĂŒgbar unter https://github.com/ultralytics/ ultralytics/blob/main/ ultralytics/models/ sam/predict .py. Wenn du ein Problem entdeckst, hilf bitte mit, es zu beheben, indem du einen Pull Request đŸ› ïž einreichst. Vielen Dank 🙏!



ultralytics.models.sam.predict.Predictor

Basen: BasePredictor

Predictor-Klasse fĂŒr das Segment Anything Model (SAM), die BasePredictor erweitert.

Die Klasse bietet eine Schnittstelle fĂŒr die Modellinferenz, die auf Bildsegmentierungsaufgaben zugeschnitten ist. Mit ihrer fortschrittlichen Architektur und den prompten Segmentierungsfunktionen ermöglicht sie eine flexible und Maskenerstellung. Die Klasse ist in der Lage, mit verschiedenen Arten von Prompts zu arbeiten, wie z. B. Bounding Boxes, Punkten und niedrig aufgelösten Masken.

Attribute:

Name Typ Beschreibung
cfg dict

Konfigurationswörterbuch, das modell- und aufgabenbezogene Parameter angibt.

overrides dict

Wörterbuch mit Werten, die die Standardkonfiguration außer Kraft setzen.

_callbacks dict

Wörterbuch mit benutzerdefinierten Callback-Funktionen, um das Verhalten zu erweitern.

args namespace

Namensraum zur Aufnahme von Kommandozeilenargumenten oder anderen operativen Variablen.

im Tensor

Vorverarbeitetes Eingangsbild tensor.

features Tensor

Extrahierte Bildmerkmale, die fĂŒr die Inferenz verwendet werden.

prompts dict

Sammlung verschiedener Souffleur-Typen, wie z.B. Bounding Boxes und Punkte.

segment_all bool

Flagge, um festzulegen, ob alle Objekte im Bild segmentiert werden sollen oder nur bestimmte.

Quellcode in ultralytics/models/sam/predict.py
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
class Predictor(BasePredictor):
    """
    Predictor class for the Segment Anything Model (SAM), extending BasePredictor.

    The class provides an interface for model inference tailored to image segmentation tasks.
    With advanced architecture and promptable segmentation capabilities, it facilitates flexible and real-time
    mask generation. The class is capable of working with various types of prompts such as bounding boxes,
    points, and low-resolution masks.

    Attributes:
        cfg (dict): Configuration dictionary specifying model and task-related parameters.
        overrides (dict): Dictionary containing values that override the default configuration.
        _callbacks (dict): Dictionary of user-defined callback functions to augment behavior.
        args (namespace): Namespace to hold command-line arguments or other operational variables.
        im (torch.Tensor): Preprocessed input image tensor.
        features (torch.Tensor): Extracted image features used for inference.
        prompts (dict): Collection of various prompt types, such as bounding boxes and points.
        segment_all (bool): Flag to control whether to segment all objects in the image or only specified ones.
    """

    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
        """
        Initialize the Predictor with configuration, overrides, and callbacks.

        The method sets up the Predictor object and applies any configuration overrides or callbacks provided. It
        initializes task-specific settings for SAM, such as retina_masks being set to True for optimal results.

        Args:
            cfg (dict): Configuration dictionary.
            overrides (dict, optional): Dictionary of values to override default configuration.
            _callbacks (dict, optional): Dictionary of callback functions to customize behavior.
        """
        if overrides is None:
            overrides = {}
        overrides.update(dict(task="segment", mode="predict", imgsz=1024))
        super().__init__(cfg, overrides, _callbacks)
        self.args.retina_masks = True
        self.im = None
        self.features = None
        self.prompts = {}
        self.segment_all = False

    def preprocess(self, im):
        """
        Preprocess the input image for model inference.

        The method prepares the input image by applying transformations and normalization.
        It supports both torch.Tensor and list of np.ndarray as input formats.

        Args:
            im (torch.Tensor | List[np.ndarray]): BCHW tensor format or list of HWC numpy arrays.

        Returns:
            (torch.Tensor): The preprocessed image tensor.
        """
        if self.im is not None:
            return self.im
        not_tensor = not isinstance(im, torch.Tensor)
        if not_tensor:
            im = np.stack(self.pre_transform(im))
            im = im[..., ::-1].transpose((0, 3, 1, 2))
            im = np.ascontiguousarray(im)
            im = torch.from_numpy(im)

        im = im.to(self.device)
        im = im.half() if self.model.fp16 else im.float()
        if not_tensor:
            im = (im - self.mean) / self.std
        return im

    def pre_transform(self, im):
        """
        Perform initial transformations on the input image for preprocessing.

        The method applies transformations such as resizing to prepare the image for further preprocessing.
        Currently, batched inference is not supported; hence the list length should be 1.

        Args:
            im (List[np.ndarray]): List containing images in HWC numpy array format.

        Returns:
            (List[np.ndarray]): List of transformed images.
        """
        assert len(im) == 1, "SAM model does not currently support batched inference"
        letterbox = LetterBox(self.args.imgsz, auto=False, center=False)
        return [letterbox(image=x) for x in im]

    def inference(self, im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False, *args, **kwargs):
        """
        Perform image segmentation inference based on the given input cues, using the currently loaded image. This
        method leverages SAM's (Segment Anything Model) architecture consisting of image encoder, prompt encoder, and
        mask decoder for real-time and promptable segmentation tasks.

        Args:
            im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
            bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
            points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates.
            labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background.
            masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256.
            multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False.

        Returns:
            (tuple): Contains the following three elements.
                - np.ndarray: The output masks in shape CxHxW, where C is the number of generated masks.
                - np.ndarray: An array of length C containing quality scores predicted by the model for each mask.
                - np.ndarray: Low-resolution logits of shape CxHxW for subsequent inference, where H=W=256.
        """
        # Override prompts if any stored in self.prompts
        bboxes = self.prompts.pop("bboxes", bboxes)
        points = self.prompts.pop("points", points)
        masks = self.prompts.pop("masks", masks)

        if all(i is None for i in [bboxes, points, masks]):
            return self.generate(im, *args, **kwargs)

        return self.prompt_inference(im, bboxes, points, labels, masks, multimask_output)

    def prompt_inference(self, im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False):
        """
        Internal function for image segmentation inference based on cues like bounding boxes, points, and masks.
        Leverages SAM's specialized architecture for prompt-based, real-time segmentation.

        Args:
            im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
            bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
            points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates.
            labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background.
            masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256.
            multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False.

        Returns:
            (tuple): Contains the following three elements.
                - np.ndarray: The output masks in shape CxHxW, where C is the number of generated masks.
                - np.ndarray: An array of length C containing quality scores predicted by the model for each mask.
                - np.ndarray: Low-resolution logits of shape CxHxW for subsequent inference, where H=W=256.
        """
        features = self.model.image_encoder(im) if self.features is None else self.features

        src_shape, dst_shape = self.batch[1][0].shape[:2], im.shape[2:]
        r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1])
        # Transform input prompts
        if points is not None:
            points = torch.as_tensor(points, dtype=torch.float32, device=self.device)
            points = points[None] if points.ndim == 1 else points
            # Assuming labels are all positive if users don't pass labels.
            if labels is None:
                labels = np.ones(points.shape[0])
            labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device)
            points *= r
            # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1)
            points, labels = points[:, None, :], labels[:, None]
        if bboxes is not None:
            bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
            bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
            bboxes *= r
        if masks is not None:
            masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)

        points = (points, labels) if points is not None else None
        # Embed prompts
        sparse_embeddings, dense_embeddings = self.model.prompt_encoder(points=points, boxes=bboxes, masks=masks)

        # Predict masks
        pred_masks, pred_scores = self.model.mask_decoder(
            image_embeddings=features,
            image_pe=self.model.prompt_encoder.get_dense_pe(),
            sparse_prompt_embeddings=sparse_embeddings,
            dense_prompt_embeddings=dense_embeddings,
            multimask_output=multimask_output,
        )

        # (N, d, H, W) --> (N*d, H, W), (N, d) --> (N*d, )
        # `d` could be 1 or 3 depends on `multimask_output`.
        return pred_masks.flatten(0, 1), pred_scores.flatten(0, 1)

    def generate(
        self,
        im,
        crop_n_layers=0,
        crop_overlap_ratio=512 / 1500,
        crop_downscale_factor=1,
        point_grids=None,
        points_stride=32,
        points_batch_size=64,
        conf_thres=0.88,
        stability_score_thresh=0.95,
        stability_score_offset=0.95,
        crop_nms_thresh=0.7,
    ):
        """
        Perform image segmentation using the Segment Anything Model (SAM).

        This function segments an entire image into constituent parts by leveraging SAM's advanced architecture
        and real-time performance capabilities. It can optionally work on image crops for finer segmentation.

        Args:
            im (torch.Tensor): Input tensor representing the preprocessed image with dimensions (N, C, H, W).
            crop_n_layers (int): Specifies the number of layers for additional mask predictions on image crops.
                                 Each layer produces 2**i_layer number of image crops.
            crop_overlap_ratio (float): Determines the extent of overlap between crops. Scaled down in subsequent layers.
            crop_downscale_factor (int): Scaling factor for the number of sampled points-per-side in each layer.
            point_grids (list[np.ndarray], optional): Custom grids for point sampling normalized to [0,1].
                                                      Used in the nth crop layer.
            points_stride (int, optional): Number of points to sample along each side of the image.
                                           Exclusive with 'point_grids'.
            points_batch_size (int): Batch size for the number of points processed simultaneously.
            conf_thres (float): Confidence threshold [0,1] for filtering based on the model's mask quality prediction.
            stability_score_thresh (float): Stability threshold [0,1] for mask filtering based on mask stability.
            stability_score_offset (float): Offset value for calculating stability score.
            crop_nms_thresh (float): IoU cutoff for Non-Maximum Suppression (NMS) to remove duplicate masks between crops.

        Returns:
            (tuple): A tuple containing segmented masks, confidence scores, and bounding boxes.
        """
        self.segment_all = True
        ih, iw = im.shape[2:]
        crop_regions, layer_idxs = generate_crop_boxes((ih, iw), crop_n_layers, crop_overlap_ratio)
        if point_grids is None:
            point_grids = build_all_layer_point_grids(points_stride, crop_n_layers, crop_downscale_factor)
        pred_masks, pred_scores, pred_bboxes, region_areas = [], [], [], []
        for crop_region, layer_idx in zip(crop_regions, layer_idxs):
            x1, y1, x2, y2 = crop_region
            w, h = x2 - x1, y2 - y1
            area = torch.tensor(w * h, device=im.device)
            points_scale = np.array([[w, h]])  # w, h
            # Crop image and interpolate to input size
            crop_im = F.interpolate(im[..., y1:y2, x1:x2], (ih, iw), mode="bilinear", align_corners=False)
            # (num_points, 2)
            points_for_image = point_grids[layer_idx] * points_scale
            crop_masks, crop_scores, crop_bboxes = [], [], []
            for (points,) in batch_iterator(points_batch_size, points_for_image):
                pred_mask, pred_score = self.prompt_inference(crop_im, points=points, multimask_output=True)
                # Interpolate predicted masks to input size
                pred_mask = F.interpolate(pred_mask[None], (h, w), mode="bilinear", align_corners=False)[0]
                idx = pred_score > conf_thres
                pred_mask, pred_score = pred_mask[idx], pred_score[idx]

                stability_score = calculate_stability_score(
                    pred_mask, self.model.mask_threshold, stability_score_offset
                )
                idx = stability_score > stability_score_thresh
                pred_mask, pred_score = pred_mask[idx], pred_score[idx]
                # Bool type is much more memory-efficient.
                pred_mask = pred_mask > self.model.mask_threshold
                # (N, 4)
                pred_bbox = batched_mask_to_box(pred_mask).float()
                keep_mask = ~is_box_near_crop_edge(pred_bbox, crop_region, [0, 0, iw, ih])
                if not torch.all(keep_mask):
                    pred_bbox, pred_mask, pred_score = pred_bbox[keep_mask], pred_mask[keep_mask], pred_score[keep_mask]

                crop_masks.append(pred_mask)
                crop_bboxes.append(pred_bbox)
                crop_scores.append(pred_score)

            # Do nms within this crop
            crop_masks = torch.cat(crop_masks)
            crop_bboxes = torch.cat(crop_bboxes)
            crop_scores = torch.cat(crop_scores)
            keep = torchvision.ops.nms(crop_bboxes, crop_scores, self.args.iou)  # NMS
            crop_bboxes = uncrop_boxes_xyxy(crop_bboxes[keep], crop_region)
            crop_masks = uncrop_masks(crop_masks[keep], crop_region, ih, iw)
            crop_scores = crop_scores[keep]

            pred_masks.append(crop_masks)
            pred_bboxes.append(crop_bboxes)
            pred_scores.append(crop_scores)
            region_areas.append(area.expand(len(crop_masks)))

        pred_masks = torch.cat(pred_masks)
        pred_bboxes = torch.cat(pred_bboxes)
        pred_scores = torch.cat(pred_scores)
        region_areas = torch.cat(region_areas)

        # Remove duplicate masks between crops
        if len(crop_regions) > 1:
            scores = 1 / region_areas
            keep = torchvision.ops.nms(pred_bboxes, scores, crop_nms_thresh)
            pred_masks, pred_bboxes, pred_scores = pred_masks[keep], pred_bboxes[keep], pred_scores[keep]

        return pred_masks, pred_scores, pred_bboxes

    def setup_model(self, model, verbose=True):
        """
        Initializes the Segment Anything Model (SAM) for inference.

        This method sets up the SAM model by allocating it to the appropriate device and initializing the necessary
        parameters for image normalization and other Ultralytics compatibility settings.

        Args:
            model (torch.nn.Module): A pre-trained SAM model. If None, a model will be built based on configuration.
            verbose (bool): If True, prints selected device information.

        Attributes:
            model (torch.nn.Module): The SAM model allocated to the chosen device for inference.
            device (torch.device): The device to which the model and tensors are allocated.
            mean (torch.Tensor): The mean values for image normalization.
            std (torch.Tensor): The standard deviation values for image normalization.
        """
        device = select_device(self.args.device, verbose=verbose)
        if model is None:
            model = build_sam(self.args.model)
        model.eval()
        self.model = model.to(device)
        self.device = device
        self.mean = torch.tensor([123.675, 116.28, 103.53]).view(-1, 1, 1).to(device)
        self.std = torch.tensor([58.395, 57.12, 57.375]).view(-1, 1, 1).to(device)

        # Ultralytics compatibility settings
        self.model.pt = False
        self.model.triton = False
        self.model.stride = 32
        self.model.fp16 = False
        self.done_warmup = True

    def postprocess(self, preds, img, orig_imgs):
        """
        Post-processes SAM's inference outputs to generate object detection masks and bounding boxes.

        The method scales masks and boxes to the original image size and applies a threshold to the mask predictions. The
        SAM model uses advanced architecture and promptable segmentation tasks to achieve real-time performance.

        Args:
            preds (tuple): The output from SAM model inference, containing masks, scores, and optional bounding boxes.
            img (torch.Tensor): The processed input image tensor.
            orig_imgs (list | torch.Tensor): The original, unprocessed images.

        Returns:
            (list): List of Results objects containing detection masks, bounding boxes, and other metadata.
        """
        # (N, 1, H, W), (N, 1)
        pred_masks, pred_scores = preds[:2]
        pred_bboxes = preds[2] if self.segment_all else None
        names = dict(enumerate(str(i) for i in range(len(pred_masks))))

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

        results = []
        for i, masks in enumerate([pred_masks]):
            orig_img = orig_imgs[i]
            if pred_bboxes is not None:
                pred_bboxes = ops.scale_boxes(img.shape[2:], pred_bboxes.float(), orig_img.shape, padding=False)
                cls = torch.arange(len(pred_masks), dtype=torch.int32, device=pred_masks.device)
                pred_bboxes = torch.cat([pred_bboxes, pred_scores[:, None], cls[:, None]], dim=-1)

            masks = ops.scale_masks(masks[None].float(), orig_img.shape[:2], padding=False)[0]
            masks = masks > self.model.mask_threshold  # to bool
            img_path = self.batch[0][i]
            results.append(Results(orig_img, path=img_path, names=names, masks=masks, boxes=pred_bboxes))
        # Reset segment-all mode.
        self.segment_all = False
        return results

    def setup_source(self, source):
        """
        Sets up the data source for inference.

        This method configures the data source from which images will be fetched for inference. The source could be a
        directory, a video file, or other types of image data sources.

        Args:
            source (str | Path): The path to the image data source for inference.
        """
        if source is not None:
            super().setup_source(source)

    def set_image(self, image):
        """
        Preprocesses and sets a single image for inference.

        This function sets up the model if not already initialized, configures the data source to the specified image,
        and preprocesses the image for feature extraction. Only one image can be set at a time.

        Args:
            image (str | np.ndarray): Image file path as a string, or a np.ndarray image read by cv2.

        Raises:
            AssertionError: If more than one image is set.
        """
        if self.model is None:
            model = build_sam(self.args.model)
            self.setup_model(model)
        self.setup_source(image)
        assert len(self.dataset) == 1, "`set_image` only supports setting one image!"
        for batch in self.dataset:
            im = self.preprocess(batch[1])
            self.features = self.model.image_encoder(im)
            self.im = im
            break

    def set_prompts(self, prompts):
        """Set prompts in advance."""
        self.prompts = prompts

    def reset_image(self):
        """Resets the image and its features to None."""
        self.im = None
        self.features = None

    @staticmethod
    def remove_small_regions(masks, min_area=0, nms_thresh=0.7):
        """
        Perform post-processing on segmentation masks generated by the Segment Anything Model (SAM). Specifically, this
        function removes small disconnected regions and holes from the input masks, and then performs Non-Maximum
        Suppression (NMS) to eliminate any newly created duplicate boxes.

        Args:
            masks (torch.Tensor): A tensor containing the masks to be processed. Shape should be (N, H, W), where N is
                                  the number of masks, H is height, and W is width.
            min_area (int): The minimum area below which disconnected regions and holes will be removed. Defaults to 0.
            nms_thresh (float): The IoU threshold for the NMS algorithm. Defaults to 0.7.

        Returns:
            (tuple([torch.Tensor, List[int]])):
                - new_masks (torch.Tensor): The processed masks with small regions removed. Shape is (N, H, W).
                - keep (List[int]): The indices of the remaining masks post-NMS, which can be used to filter the boxes.
        """
        if len(masks) == 0:
            return masks

        # Filter small disconnected regions and holes
        new_masks = []
        scores = []
        for mask in masks:
            mask = mask.cpu().numpy().astype(np.uint8)
            mask, changed = remove_small_regions(mask, min_area, mode="holes")
            unchanged = not changed
            mask, changed = remove_small_regions(mask, min_area, mode="islands")
            unchanged = unchanged and not changed

            new_masks.append(torch.as_tensor(mask).unsqueeze(0))
            # Give score=0 to changed masks and 1 to unchanged masks so NMS prefers masks not needing postprocessing
            scores.append(float(unchanged))

        # Recalculate boxes and remove any new duplicates
        new_masks = torch.cat(new_masks, dim=0)
        boxes = batched_mask_to_box(new_masks)
        keep = torchvision.ops.nms(boxes.float(), torch.as_tensor(scores), nms_thresh)

        return new_masks[keep].to(device=masks.device, dtype=masks.dtype), keep

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

Initialisiere den Predictor mit Konfiguration, Overrides und Callbacks.

Die Methode richtet das Predictor-Objekt ein und wendet alle KonfigurationsĂŒberschreibungen oder RĂŒckrufe an. Sie initialisiert aufgabenspezifische Einstellungen fĂŒr SAM, z. B. dass retina_masks fĂŒr optimale Ergebnisse auf True gesetzt wird.

Parameter:

Name Typ Beschreibung Standard
cfg dict

Konfigurationswörterbuch.

DEFAULT_CFG
overrides dict

Wörterbuch mit Werten, die die Standardkonfiguration außer Kraft setzen.

None
_callbacks dict

Wörterbuch der Callback-Funktionen, um das Verhalten anzupassen.

None
Quellcode in ultralytics/models/sam/predict.py
def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
    """
    Initialize the Predictor with configuration, overrides, and callbacks.

    The method sets up the Predictor object and applies any configuration overrides or callbacks provided. It
    initializes task-specific settings for SAM, such as retina_masks being set to True for optimal results.

    Args:
        cfg (dict): Configuration dictionary.
        overrides (dict, optional): Dictionary of values to override default configuration.
        _callbacks (dict, optional): Dictionary of callback functions to customize behavior.
    """
    if overrides is None:
        overrides = {}
    overrides.update(dict(task="segment", mode="predict", imgsz=1024))
    super().__init__(cfg, overrides, _callbacks)
    self.args.retina_masks = True
    self.im = None
    self.features = None
    self.prompts = {}
    self.segment_all = False

generate(im, crop_n_layers=0, crop_overlap_ratio=512 / 1500, crop_downscale_factor=1, point_grids=None, points_stride=32, points_batch_size=64, conf_thres=0.88, stability_score_thresh=0.95, stability_score_offset=0.95, crop_nms_thresh=0.7)

FĂŒhre die Bildsegmentierung mit dem Segment Anything Model (SAM) durch.

Diese Funktion zerlegt ein ganzes Bild in seine Einzelteile, indem sie die fortschrittliche Architektur von SAM und Echtzeit-LeistungsfÀhigkeiten nutzt. Sie kann optional mit Bildausschnitten arbeiten, um die Segmentierung zu verfeinern.

Parameter:

Name Typ Beschreibung Standard
im Tensor

Eingabe tensor , die das vorverarbeitete Bild mit den Abmessungen (N, C, H, W) darstellt.

erforderlich
crop_n_layers int

Gibt die Anzahl der Ebenen fĂŒr zusĂ€tzliche Maskenvorhersagen auf Bildausschnitten an. Jede Ebene erzeugt 2**i_Layer Anzahl von Bildausschnitten.

0
crop_overlap_ratio float

Bestimmt das Ausmaß der Überlappung zwischen den Kulturen. Wird in den nachfolgenden Ebenen verkleinert.

512 / 1500
crop_downscale_factor int

Skalierungsfaktor fĂŒr die Anzahl der gesampelten Punkte pro Seite in jeder Schicht.

1
point_grids list[ndarray]

Benutzerdefinierte Raster fĂŒr Punktstichproben, normalisiert auf [0,1]. Wird in der n-ten Erntestufe verwendet.

None
points_stride int

Anzahl der Punkte, die auf jeder Seite des Bildes gesampelt werden. Ausschließlich mit 'point_grids'.

32
points_batch_size int

StapelgrĂ¶ĂŸe fĂŒr die Anzahl der gleichzeitig verarbeiteten Punkte.

64
conf_thres float

Konfidenzschwelle [0,1] fĂŒr die Filterung auf der Grundlage der Vorhersage der MaskenqualitĂ€t durch das Modell.

0.88
stability_score_thresh float

StabilitĂ€tsschwelle [0,1] fĂŒr die Maskenfilterung auf Basis der MaskenstabilitĂ€t.

0.95
stability_score_offset float

Offset-Wert fĂŒr die Berechnung der StabilitĂ€tsbewertung.

0.95
crop_nms_thresh float

IoU-Cutoff fĂŒr Non-Maximum Suppression (NMS), um doppelte Masken zwischen Kulturen zu entfernen.

0.7

Retouren:

Typ Beschreibung
tuple

Ein Tupel mit segmentierten Masken, Konfidenzwerten und Bounding Boxes.

Quellcode in ultralytics/models/sam/predict.py
def generate(
    self,
    im,
    crop_n_layers=0,
    crop_overlap_ratio=512 / 1500,
    crop_downscale_factor=1,
    point_grids=None,
    points_stride=32,
    points_batch_size=64,
    conf_thres=0.88,
    stability_score_thresh=0.95,
    stability_score_offset=0.95,
    crop_nms_thresh=0.7,
):
    """
    Perform image segmentation using the Segment Anything Model (SAM).

    This function segments an entire image into constituent parts by leveraging SAM's advanced architecture
    and real-time performance capabilities. It can optionally work on image crops for finer segmentation.

    Args:
        im (torch.Tensor): Input tensor representing the preprocessed image with dimensions (N, C, H, W).
        crop_n_layers (int): Specifies the number of layers for additional mask predictions on image crops.
                             Each layer produces 2**i_layer number of image crops.
        crop_overlap_ratio (float): Determines the extent of overlap between crops. Scaled down in subsequent layers.
        crop_downscale_factor (int): Scaling factor for the number of sampled points-per-side in each layer.
        point_grids (list[np.ndarray], optional): Custom grids for point sampling normalized to [0,1].
                                                  Used in the nth crop layer.
        points_stride (int, optional): Number of points to sample along each side of the image.
                                       Exclusive with 'point_grids'.
        points_batch_size (int): Batch size for the number of points processed simultaneously.
        conf_thres (float): Confidence threshold [0,1] for filtering based on the model's mask quality prediction.
        stability_score_thresh (float): Stability threshold [0,1] for mask filtering based on mask stability.
        stability_score_offset (float): Offset value for calculating stability score.
        crop_nms_thresh (float): IoU cutoff for Non-Maximum Suppression (NMS) to remove duplicate masks between crops.

    Returns:
        (tuple): A tuple containing segmented masks, confidence scores, and bounding boxes.
    """
    self.segment_all = True
    ih, iw = im.shape[2:]
    crop_regions, layer_idxs = generate_crop_boxes((ih, iw), crop_n_layers, crop_overlap_ratio)
    if point_grids is None:
        point_grids = build_all_layer_point_grids(points_stride, crop_n_layers, crop_downscale_factor)
    pred_masks, pred_scores, pred_bboxes, region_areas = [], [], [], []
    for crop_region, layer_idx in zip(crop_regions, layer_idxs):
        x1, y1, x2, y2 = crop_region
        w, h = x2 - x1, y2 - y1
        area = torch.tensor(w * h, device=im.device)
        points_scale = np.array([[w, h]])  # w, h
        # Crop image and interpolate to input size
        crop_im = F.interpolate(im[..., y1:y2, x1:x2], (ih, iw), mode="bilinear", align_corners=False)
        # (num_points, 2)
        points_for_image = point_grids[layer_idx] * points_scale
        crop_masks, crop_scores, crop_bboxes = [], [], []
        for (points,) in batch_iterator(points_batch_size, points_for_image):
            pred_mask, pred_score = self.prompt_inference(crop_im, points=points, multimask_output=True)
            # Interpolate predicted masks to input size
            pred_mask = F.interpolate(pred_mask[None], (h, w), mode="bilinear", align_corners=False)[0]
            idx = pred_score > conf_thres
            pred_mask, pred_score = pred_mask[idx], pred_score[idx]

            stability_score = calculate_stability_score(
                pred_mask, self.model.mask_threshold, stability_score_offset
            )
            idx = stability_score > stability_score_thresh
            pred_mask, pred_score = pred_mask[idx], pred_score[idx]
            # Bool type is much more memory-efficient.
            pred_mask = pred_mask > self.model.mask_threshold
            # (N, 4)
            pred_bbox = batched_mask_to_box(pred_mask).float()
            keep_mask = ~is_box_near_crop_edge(pred_bbox, crop_region, [0, 0, iw, ih])
            if not torch.all(keep_mask):
                pred_bbox, pred_mask, pred_score = pred_bbox[keep_mask], pred_mask[keep_mask], pred_score[keep_mask]

            crop_masks.append(pred_mask)
            crop_bboxes.append(pred_bbox)
            crop_scores.append(pred_score)

        # Do nms within this crop
        crop_masks = torch.cat(crop_masks)
        crop_bboxes = torch.cat(crop_bboxes)
        crop_scores = torch.cat(crop_scores)
        keep = torchvision.ops.nms(crop_bboxes, crop_scores, self.args.iou)  # NMS
        crop_bboxes = uncrop_boxes_xyxy(crop_bboxes[keep], crop_region)
        crop_masks = uncrop_masks(crop_masks[keep], crop_region, ih, iw)
        crop_scores = crop_scores[keep]

        pred_masks.append(crop_masks)
        pred_bboxes.append(crop_bboxes)
        pred_scores.append(crop_scores)
        region_areas.append(area.expand(len(crop_masks)))

    pred_masks = torch.cat(pred_masks)
    pred_bboxes = torch.cat(pred_bboxes)
    pred_scores = torch.cat(pred_scores)
    region_areas = torch.cat(region_areas)

    # Remove duplicate masks between crops
    if len(crop_regions) > 1:
        scores = 1 / region_areas
        keep = torchvision.ops.nms(pred_bboxes, scores, crop_nms_thresh)
        pred_masks, pred_bboxes, pred_scores = pred_masks[keep], pred_bboxes[keep], pred_scores[keep]

    return pred_masks, pred_scores, pred_bboxes

inference(im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False, *args, **kwargs)

FĂŒhrt eine Bildsegmentierung auf der Grundlage der gegebenen Eingabehinweise durch und verwendet dabei das aktuell geladene Bild. Diese Methode nutzt die Architektur von SAM(Segment Anything Model), die aus einem Bild-Encoder, einem Prompt-Encoder und einem Maskendekoder fĂŒr Echtzeit- und promptable Segmentierungsaufgaben.

Parameter:

Name Typ Beschreibung Standard
im Tensor

Das vorverarbeitete Eingangsbild im Format tensor , mit Form (N, C, H, W).

erforderlich
bboxes ndarray | List

Bounding Boxes mit der Form (N, 4), im XYXY-Format.

None
points ndarray | List

Punkte, die die Objektpositionen mit der Form (N, 2) in Pixelkoordinaten angeben.

None
labels ndarray | List

Bezeichnungen fĂŒr Punktaufforderungen, Form (N, ). 1 fĂŒr den Vordergrund und 0 fĂŒr den Hintergrund.

None
masks ndarray

Niedrig aufgelöste Masken aus frĂŒheren Vorhersagen. Die Form sollte (N, H, W) sein. FĂŒr SAM, H=W=256.

None
multimask_output bool

Flagge, um mehrere Masken zurĂŒckzugeben. Hilfreich bei zweideutigen Aufforderungen. Der Standardwert ist False.

False

Retouren:

Typ Beschreibung
tuple

EnthĂ€lt die folgenden drei Elemente. - np.ndarray: Die Ausgangsmasken in der Form CxHxW, wobei C die Anzahl der erzeugten Masken ist. - np.ndarray: Ein Array der LĂ€nge C, das die vom Modell vorhergesagten QualitĂ€tswerte fĂŒr jede Maske enthĂ€lt. - np.ndarray: Niedrig aufgelöste Logits der Form CxHxW fĂŒr die anschließende Inferenz, wobei H=W=256.

Quellcode in ultralytics/models/sam/predict.py
def inference(self, im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False, *args, **kwargs):
    """
    Perform image segmentation inference based on the given input cues, using the currently loaded image. This
    method leverages SAM's (Segment Anything Model) architecture consisting of image encoder, prompt encoder, and
    mask decoder for real-time and promptable segmentation tasks.

    Args:
        im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
        bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
        points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates.
        labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background.
        masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256.
        multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False.

    Returns:
        (tuple): Contains the following three elements.
            - np.ndarray: The output masks in shape CxHxW, where C is the number of generated masks.
            - np.ndarray: An array of length C containing quality scores predicted by the model for each mask.
            - np.ndarray: Low-resolution logits of shape CxHxW for subsequent inference, where H=W=256.
    """
    # Override prompts if any stored in self.prompts
    bboxes = self.prompts.pop("bboxes", bboxes)
    points = self.prompts.pop("points", points)
    masks = self.prompts.pop("masks", masks)

    if all(i is None for i in [bboxes, points, masks]):
        return self.generate(im, *args, **kwargs)

    return self.prompt_inference(im, bboxes, points, labels, masks, multimask_output)

postprocess(preds, img, orig_imgs)

Verarbeitet die Ergebnisse von SAM nach, um Masken und Boundingboxen fĂŒr die Objekterkennung zu erstellen.

Die Methode skaliert Masken und Boxen auf die ursprĂŒngliche BildgrĂ¶ĂŸe und wendet einen Schwellenwert auf die Maskenvorhersagen an. Das SAM Das Modell nutzt eine fortschrittliche Architektur und prompte Segmentierungsaufgaben, um eine Echtzeitleistung zu erzielen.

Parameter:

Name Typ Beschreibung Standard
preds tuple

Die Ausgabe der SAM Modellinferenz, die Masken, Bewertungen und optionale Bounding Boxes enthÀlt.

erforderlich
img Tensor

Das bearbeitete Eingangsbild tensor.

erforderlich
orig_imgs list | Tensor

Die ursprĂŒnglichen, unbearbeiteten Bilder.

erforderlich

Retouren:

Typ Beschreibung
list

Liste der Ergebnisobjekte mit Erkennungsmasken, Begrenzungsrahmen und anderen Metadaten.

Quellcode in ultralytics/models/sam/predict.py
def postprocess(self, preds, img, orig_imgs):
    """
    Post-processes SAM's inference outputs to generate object detection masks and bounding boxes.

    The method scales masks and boxes to the original image size and applies a threshold to the mask predictions. The
    SAM model uses advanced architecture and promptable segmentation tasks to achieve real-time performance.

    Args:
        preds (tuple): The output from SAM model inference, containing masks, scores, and optional bounding boxes.
        img (torch.Tensor): The processed input image tensor.
        orig_imgs (list | torch.Tensor): The original, unprocessed images.

    Returns:
        (list): List of Results objects containing detection masks, bounding boxes, and other metadata.
    """
    # (N, 1, H, W), (N, 1)
    pred_masks, pred_scores = preds[:2]
    pred_bboxes = preds[2] if self.segment_all else None
    names = dict(enumerate(str(i) for i in range(len(pred_masks))))

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

    results = []
    for i, masks in enumerate([pred_masks]):
        orig_img = orig_imgs[i]
        if pred_bboxes is not None:
            pred_bboxes = ops.scale_boxes(img.shape[2:], pred_bboxes.float(), orig_img.shape, padding=False)
            cls = torch.arange(len(pred_masks), dtype=torch.int32, device=pred_masks.device)
            pred_bboxes = torch.cat([pred_bboxes, pred_scores[:, None], cls[:, None]], dim=-1)

        masks = ops.scale_masks(masks[None].float(), orig_img.shape[:2], padding=False)[0]
        masks = masks > self.model.mask_threshold  # to bool
        img_path = self.batch[0][i]
        results.append(Results(orig_img, path=img_path, names=names, masks=masks, boxes=pred_bboxes))
    # Reset segment-all mode.
    self.segment_all = False
    return results

pre_transform(im)

FĂŒhre erste Transformationen am Eingangsbild durch, um es vorzuverarbeiten.

Die Methode wendet Transformationen wie die GrĂ¶ĂŸenĂ€nderung an, um das Bild fĂŒr die weitere Vorverarbeitung vorzubereiten. Zurzeit wird die Batch-Inferenz nicht unterstĂŒtzt; daher sollte die ListenlĂ€nge 1 sein.

Parameter:

Name Typ Beschreibung Standard
im List[ndarray]

Liste mit Bildern im HWC Numpy-Array-Format.

erforderlich

Retouren:

Typ Beschreibung
List[ndarray]

Liste der transformierten Bilder.

Quellcode in ultralytics/models/sam/predict.py
def pre_transform(self, im):
    """
    Perform initial transformations on the input image for preprocessing.

    The method applies transformations such as resizing to prepare the image for further preprocessing.
    Currently, batched inference is not supported; hence the list length should be 1.

    Args:
        im (List[np.ndarray]): List containing images in HWC numpy array format.

    Returns:
        (List[np.ndarray]): List of transformed images.
    """
    assert len(im) == 1, "SAM model does not currently support batched inference"
    letterbox = LetterBox(self.args.imgsz, auto=False, center=False)
    return [letterbox(image=x) for x in im]

preprocess(im)

Verarbeite das Eingangsbild fĂŒr die Modellinferenz vor.

Die Methode bereitet das Eingabebild durch Anwendung von Transformationen und Normalisierung vor. Sie unterstĂŒtzt sowohl torch.Tensor als auch list of np.ndarray als Eingabeformate.

Parameter:

Name Typ Beschreibung Standard
im Tensor | List[ndarray]

BCHW tensor Format oder Liste der HWC Numpy-Arrays.

erforderlich

Retouren:

Typ Beschreibung
Tensor

Das vorverarbeitete Bild tensor.

Quellcode in ultralytics/models/sam/predict.py
def preprocess(self, im):
    """
    Preprocess the input image for model inference.

    The method prepares the input image by applying transformations and normalization.
    It supports both torch.Tensor and list of np.ndarray as input formats.

    Args:
        im (torch.Tensor | List[np.ndarray]): BCHW tensor format or list of HWC numpy arrays.

    Returns:
        (torch.Tensor): The preprocessed image tensor.
    """
    if self.im is not None:
        return self.im
    not_tensor = not isinstance(im, torch.Tensor)
    if not_tensor:
        im = np.stack(self.pre_transform(im))
        im = im[..., ::-1].transpose((0, 3, 1, 2))
        im = np.ascontiguousarray(im)
        im = torch.from_numpy(im)

    im = im.to(self.device)
    im = im.half() if self.model.fp16 else im.float()
    if not_tensor:
        im = (im - self.mean) / self.std
    return im

prompt_inference(im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False)

Interne Funktion fĂŒr die Segmentierung von Bildern auf der Grundlage von Begrenzungsrahmen, Punkten und Masken. Nutzt die spezielle Architektur von SAM fĂŒr prompt-basierte Segmentierung in Echtzeit.

Parameter:

Name Typ Beschreibung Standard
im Tensor

Das vorverarbeitete Eingangsbild im Format tensor , mit Form (N, C, H, W).

erforderlich
bboxes ndarray | List

Bounding Boxes mit der Form (N, 4), im XYXY-Format.

None
points ndarray | List

Punkte, die die Objektpositionen mit der Form (N, 2) in Pixelkoordinaten angeben.

None
labels ndarray | List

Bezeichnungen fĂŒr Punktaufforderungen, Form (N, ). 1 fĂŒr den Vordergrund und 0 fĂŒr den Hintergrund.

None
masks ndarray

Niedrig aufgelöste Masken aus frĂŒheren Vorhersagen. Die Form sollte (N, H, W) sein. FĂŒr SAM, H=W=256.

None
multimask_output bool

Flagge, um mehrere Masken zurĂŒckzugeben. Hilfreich bei zweideutigen Aufforderungen. Der Standardwert ist False.

False

Retouren:

Typ Beschreibung
tuple

EnthĂ€lt die folgenden drei Elemente. - np.ndarray: Die Ausgangsmasken in der Form CxHxW, wobei C die Anzahl der erzeugten Masken ist. - np.ndarray: Ein Array der LĂ€nge C, das die vom Modell vorhergesagten QualitĂ€tswerte fĂŒr jede Maske enthĂ€lt. - np.ndarray: Niedrig aufgelöste Logits der Form CxHxW fĂŒr die anschließende Inferenz, wobei H=W=256.

Quellcode in ultralytics/models/sam/predict.py
def prompt_inference(self, im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False):
    """
    Internal function for image segmentation inference based on cues like bounding boxes, points, and masks.
    Leverages SAM's specialized architecture for prompt-based, real-time segmentation.

    Args:
        im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
        bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
        points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates.
        labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background.
        masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256.
        multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False.

    Returns:
        (tuple): Contains the following three elements.
            - np.ndarray: The output masks in shape CxHxW, where C is the number of generated masks.
            - np.ndarray: An array of length C containing quality scores predicted by the model for each mask.
            - np.ndarray: Low-resolution logits of shape CxHxW for subsequent inference, where H=W=256.
    """
    features = self.model.image_encoder(im) if self.features is None else self.features

    src_shape, dst_shape = self.batch[1][0].shape[:2], im.shape[2:]
    r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1])
    # Transform input prompts
    if points is not None:
        points = torch.as_tensor(points, dtype=torch.float32, device=self.device)
        points = points[None] if points.ndim == 1 else points
        # Assuming labels are all positive if users don't pass labels.
        if labels is None:
            labels = np.ones(points.shape[0])
        labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device)
        points *= r
        # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1)
        points, labels = points[:, None, :], labels[:, None]
    if bboxes is not None:
        bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
        bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
        bboxes *= r
    if masks is not None:
        masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)

    points = (points, labels) if points is not None else None
    # Embed prompts
    sparse_embeddings, dense_embeddings = self.model.prompt_encoder(points=points, boxes=bboxes, masks=masks)

    # Predict masks
    pred_masks, pred_scores = self.model.mask_decoder(
        image_embeddings=features,
        image_pe=self.model.prompt_encoder.get_dense_pe(),
        sparse_prompt_embeddings=sparse_embeddings,
        dense_prompt_embeddings=dense_embeddings,
        multimask_output=multimask_output,
    )

    # (N, d, H, W) --> (N*d, H, W), (N, d) --> (N*d, )
    # `d` could be 1 or 3 depends on `multimask_output`.
    return pred_masks.flatten(0, 1), pred_scores.flatten(0, 1)

remove_small_regions(masks, min_area=0, nms_thresh=0.7) staticmethod

FĂŒhre eine Nachbearbeitung der Segmentierungsmasken durch, die mit dem Segment Anything Model (SAM) erstellt wurden. Konkret bedeutet dies Funktion entfernt insbesondere kleine unzusammenhĂ€ngende Regionen und Löcher aus den Eingabemasken und fĂŒhrt dann eine Non-Maximum Suppression (NMS) durch, um alle neu erstellten doppelten Boxen zu entfernen.

Parameter:

Name Typ Beschreibung Standard
masks Tensor

Eine tensor , die die zu bearbeitenden Masken enthĂ€lt. Shape sollte (N, H, W) sein, wobei N fĂŒr die Anzahl der Masken, H die Höhe und W die Breite ist.

erforderlich
min_area int

Die MindestflÀche, unterhalb derer nicht verbundene Regionen und Löcher entfernt werden. Der Standardwert ist 0.

0
nms_thresh float

Der IoU-Schwellenwert fĂŒr den NMS-Algorithmus. Der Standardwert ist 0,7.

0.7

Retouren:

Typ Beschreibung
tuple([Tensor, List[int]])
  • new_masks (torch.Tensor): Die bearbeiteten Masken, bei denen kleine Regionen entfernt wurden. Die Form ist (N, H, W).
  • keep (Liste[int]): Die Indizes der verbleibenden Masken nach NMS, die zum Filtern der Boxen verwendet werden können.
Quellcode in ultralytics/models/sam/predict.py
@staticmethod
def remove_small_regions(masks, min_area=0, nms_thresh=0.7):
    """
    Perform post-processing on segmentation masks generated by the Segment Anything Model (SAM). Specifically, this
    function removes small disconnected regions and holes from the input masks, and then performs Non-Maximum
    Suppression (NMS) to eliminate any newly created duplicate boxes.

    Args:
        masks (torch.Tensor): A tensor containing the masks to be processed. Shape should be (N, H, W), where N is
                              the number of masks, H is height, and W is width.
        min_area (int): The minimum area below which disconnected regions and holes will be removed. Defaults to 0.
        nms_thresh (float): The IoU threshold for the NMS algorithm. Defaults to 0.7.

    Returns:
        (tuple([torch.Tensor, List[int]])):
            - new_masks (torch.Tensor): The processed masks with small regions removed. Shape is (N, H, W).
            - keep (List[int]): The indices of the remaining masks post-NMS, which can be used to filter the boxes.
    """
    if len(masks) == 0:
        return masks

    # Filter small disconnected regions and holes
    new_masks = []
    scores = []
    for mask in masks:
        mask = mask.cpu().numpy().astype(np.uint8)
        mask, changed = remove_small_regions(mask, min_area, mode="holes")
        unchanged = not changed
        mask, changed = remove_small_regions(mask, min_area, mode="islands")
        unchanged = unchanged and not changed

        new_masks.append(torch.as_tensor(mask).unsqueeze(0))
        # Give score=0 to changed masks and 1 to unchanged masks so NMS prefers masks not needing postprocessing
        scores.append(float(unchanged))

    # Recalculate boxes and remove any new duplicates
    new_masks = torch.cat(new_masks, dim=0)
    boxes = batched_mask_to_box(new_masks)
    keep = torchvision.ops.nms(boxes.float(), torch.as_tensor(scores), nms_thresh)

    return new_masks[keep].to(device=masks.device, dtype=masks.dtype), keep

reset_image()

Setzt das Bild und seine Merkmale auf Keine zurĂŒck.

Quellcode in ultralytics/models/sam/predict.py
def reset_image(self):
    """Resets the image and its features to None."""
    self.im = None
    self.features = None

set_image(image)

Verarbeitet ein einzelnes Bild vor und stellt es fĂŒr die Inferenz ein.

Diese Funktion richtet das Modell ein, falls es noch nicht initialisiert ist, konfiguriert die Datenquelle fĂŒr das angegebene Bild, und bereitet das Bild fĂŒr die Merkmalsextraktion vor. Es kann jeweils nur ein Bild eingestellt werden.

Parameter:

Name Typ Beschreibung Standard
image str | ndarray

Pfad der Bilddatei als String oder ein np.ndarray-Bild, das von cv2 gelesen wird.

erforderlich

Erhöht:

Typ Beschreibung
AssertionError

Wenn mehr als ein Bild eingestellt ist.

Quellcode in ultralytics/models/sam/predict.py
def set_image(self, image):
    """
    Preprocesses and sets a single image for inference.

    This function sets up the model if not already initialized, configures the data source to the specified image,
    and preprocesses the image for feature extraction. Only one image can be set at a time.

    Args:
        image (str | np.ndarray): Image file path as a string, or a np.ndarray image read by cv2.

    Raises:
        AssertionError: If more than one image is set.
    """
    if self.model is None:
        model = build_sam(self.args.model)
        self.setup_model(model)
    self.setup_source(image)
    assert len(self.dataset) == 1, "`set_image` only supports setting one image!"
    for batch in self.dataset:
        im = self.preprocess(batch[1])
        self.features = self.model.image_encoder(im)
        self.im = im
        break

set_prompts(prompts)

Lege die Aufforderungen im Voraus fest.

Quellcode in ultralytics/models/sam/predict.py
def set_prompts(self, prompts):
    """Set prompts in advance."""
    self.prompts = prompts

setup_model(model, verbose=True)

Initialisiert das Segment Anything Model (SAM) fĂŒr die Inferenz.

Diese Methode richtet das Modell SAM ein, indem sie es dem entsprechenden GerĂ€t zuweist und die notwendigen Parameter fĂŒr die Bildnormalisierung und andere Ultralytics KompatibilitĂ€tseinstellungen initialisiert.

Parameter:

Name Typ Beschreibung Standard
model Module

Ein vortrainiertes SAM Modell. Wenn Keine, wird ein Modell basierend auf der Konfiguration erstellt.

erforderlich
verbose bool

Wenn True, werden die ausgewÀhlten GerÀteinformationen gedruckt.

True

Attribute:

Name Typ Beschreibung
model Module

Das SAM Modell, das dem ausgewĂ€hlten GerĂ€t fĂŒr die Inferenz zugewiesen wurde.

device device

Das GerÀt, dem das Modell und die Tensoren zugewiesen werden.

mean Tensor

Die Mittelwerte fĂŒr die Bildnormalisierung.

std Tensor

Die Standardabweichungswerte fĂŒr die Bildnormalisierung.

Quellcode in ultralytics/models/sam/predict.py
def setup_model(self, model, verbose=True):
    """
    Initializes the Segment Anything Model (SAM) for inference.

    This method sets up the SAM model by allocating it to the appropriate device and initializing the necessary
    parameters for image normalization and other Ultralytics compatibility settings.

    Args:
        model (torch.nn.Module): A pre-trained SAM model. If None, a model will be built based on configuration.
        verbose (bool): If True, prints selected device information.

    Attributes:
        model (torch.nn.Module): The SAM model allocated to the chosen device for inference.
        device (torch.device): The device to which the model and tensors are allocated.
        mean (torch.Tensor): The mean values for image normalization.
        std (torch.Tensor): The standard deviation values for image normalization.
    """
    device = select_device(self.args.device, verbose=verbose)
    if model is None:
        model = build_sam(self.args.model)
    model.eval()
    self.model = model.to(device)
    self.device = device
    self.mean = torch.tensor([123.675, 116.28, 103.53]).view(-1, 1, 1).to(device)
    self.std = torch.tensor([58.395, 57.12, 57.375]).view(-1, 1, 1).to(device)

    # Ultralytics compatibility settings
    self.model.pt = False
    self.model.triton = False
    self.model.stride = 32
    self.model.fp16 = False
    self.done_warmup = True

setup_source(source)

Richtet die Datenquelle fĂŒr die Inferenz ein.

Diese Methode konfiguriert die Datenquelle, aus der die Bilder fĂŒr die Inferenz geholt werden. Bei der Quelle kann es sich um ein Verzeichnis, eine Videodatei oder eine andere Art von Bilddatenquelle sein.

Parameter:

Name Typ Beschreibung Standard
source str | Path

Der Pfad zur Bilddatenquelle fĂŒr die Inferenz.

erforderlich
Quellcode in ultralytics/models/sam/predict.py
def setup_source(self, source):
    """
    Sets up the data source for inference.

    This method configures the data source from which images will be fetched for inference. The source could be a
    directory, a video file, or other types of image data sources.

    Args:
        source (str | Path): The path to the image data source for inference.
    """
    if source is not None:
        super().setup_source(source)





Erstellt am 2023-11-12, Aktualisiert am 2023-11-25
Autoren: glenn-jocher (3)