コンテンツへスキップ

参考 ultralytics/utils/plotting.py

注

このファイルはhttps://github.com/ultralytics/ultralytics/blob/main/ ultralytics/utils/plotting .py にあります。もし問題を発見したら、Pull Request🛠️ を投稿して修正にご協力ください。ありがとうございました!



ultralytics.utils.plotting.Colors

Ultralytics デフォルトカラーパレット https://ultralytics.com/.

このクラスは、Ultralytics カラーパレットを扱うためのメソッドを提供します。 RGB 値に変換するメソッドを提供します。

属性:

名称 タイプ 説明
palette list of tuple

RGBカラー値のリスト。

n int

パレットの色数。

pose_palette ndarray

np.uint8 型のカラーパレット配列。

ソースコード ultralytics/utils/plotting.py
class Colors:
    """
    Ultralytics default color palette https://ultralytics.com/.

    This class provides methods to work with the Ultralytics color palette, including converting hex color codes to
    RGB values.

    Attributes:
        palette (list of tuple): List of RGB color values.
        n (int): The number of colors in the palette.
        pose_palette (np.ndarray): A specific color palette array with dtype np.uint8.
    """

    def __init__(self):
        """Initialize colors as hex = matplotlib.colors.TABLEAU_COLORS.values()."""
        hexs = (
            "042AFF",
            "0BDBEB",
            "F3F3F3",
            "00DFB7",
            "111F68",
            "FF6FDD",
            "FF444F",
            "CCED00",
            "00F344",
            "BD00FF",
            "00B4FF",
            "DD00BA",
            "00FFFF",
            "26C000",
            "01FFB3",
            "7D24FF",
            "7B0068",
            "FF1B6C",
            "FC6D2F",
            "A2FF0B",
        )
        self.palette = [self.hex2rgb(f"#{c}") for c in hexs]
        self.n = len(self.palette)
        self.pose_palette = np.array(
            [
                [255, 128, 0],
                [255, 153, 51],
                [255, 178, 102],
                [230, 230, 0],
                [255, 153, 255],
                [153, 204, 255],
                [255, 102, 255],
                [255, 51, 255],
                [102, 178, 255],
                [51, 153, 255],
                [255, 153, 153],
                [255, 102, 102],
                [255, 51, 51],
                [153, 255, 153],
                [102, 255, 102],
                [51, 255, 51],
                [0, 255, 0],
                [0, 0, 255],
                [255, 0, 0],
                [255, 255, 255],
            ],
            dtype=np.uint8,
        )

    def __call__(self, i, bgr=False):
        """Converts hex color codes to RGB values."""
        c = self.palette[int(i) % self.n]
        return (c[2], c[1], c[0]) if bgr else c

    @staticmethod
    def hex2rgb(h):
        """Converts hex color codes to RGB values (i.e. default PIL order)."""
        return tuple(int(h[1 + i : 1 + i + 2], 16) for i in (0, 2, 4))

__call__(i, bgr=False)

16進カラーコードをRGB値に変換します。

ソースコード ultralytics/utils/plotting.py
def __call__(self, i, bgr=False):
    """Converts hex color codes to RGB values."""
    c = self.palette[int(i) % self.n]
    return (c[2], c[1], c[0]) if bgr else c

__init__()

色を hex として初期化 = matplotlib.colors.TABLEAU_COLORS.values().

ソースコード ultralytics/utils/plotting.py
def __init__(self):
    """Initialize colors as hex = matplotlib.colors.TABLEAU_COLORS.values()."""
    hexs = (
        "042AFF",
        "0BDBEB",
        "F3F3F3",
        "00DFB7",
        "111F68",
        "FF6FDD",
        "FF444F",
        "CCED00",
        "00F344",
        "BD00FF",
        "00B4FF",
        "DD00BA",
        "00FFFF",
        "26C000",
        "01FFB3",
        "7D24FF",
        "7B0068",
        "FF1B6C",
        "FC6D2F",
        "A2FF0B",
    )
    self.palette = [self.hex2rgb(f"#{c}") for c in hexs]
    self.n = len(self.palette)
    self.pose_palette = np.array(
        [
            [255, 128, 0],
            [255, 153, 51],
            [255, 178, 102],
            [230, 230, 0],
            [255, 153, 255],
            [153, 204, 255],
            [255, 102, 255],
            [255, 51, 255],
            [102, 178, 255],
            [51, 153, 255],
            [255, 153, 153],
            [255, 102, 102],
            [255, 51, 51],
            [153, 255, 153],
            [102, 255, 102],
            [51, 255, 51],
            [0, 255, 0],
            [0, 0, 255],
            [255, 0, 0],
            [255, 255, 255],
        ],
        dtype=np.uint8,
    )

hex2rgb(h) staticmethod

16進カラーコードをRGB値に変換する(すなわちデフォルトのPIL順序)。

ソースコード ultralytics/utils/plotting.py
@staticmethod
def hex2rgb(h):
    """Converts hex color codes to RGB values (i.e. default PIL order)."""
    return tuple(int(h[1 + i : 1 + i + 2], 16) for i in (0, 2, 4))



ultralytics.utils.plotting.Annotator

Ultralytics モザイク、JPG、予測アノテーションのためのアノテーター。

属性:

名称 タイプ 説明
im Image.Image or numpy array

注釈を付ける画像。

pil bool

注釈の描画に PIL を使うか cv2 を使うか。

font truetype or load_default

テキスト注釈に使用されるフォント。

lw float

描画の線幅。

skeleton List[List[int]]

キーポイントのスケルトン構造。

limb_color List[int]

手足のカラーパレット。

kpt_color List[int]

キーポイントのカラーパレット。

ソースコード ultralytics/utils/plotting.py
 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
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
class Annotator:
    """
    Ultralytics Annotator for train/val mosaics and JPGs and predictions annotations.

    Attributes:
        im (Image.Image or numpy array): The image to annotate.
        pil (bool): Whether to use PIL or cv2 for drawing annotations.
        font (ImageFont.truetype or ImageFont.load_default): Font used for text annotations.
        lw (float): Line width for drawing.
        skeleton (List[List[int]]): Skeleton structure for keypoints.
        limb_color (List[int]): Color palette for limbs.
        kpt_color (List[int]): Color palette for keypoints.
    """

    def __init__(self, im, line_width=None, font_size=None, font="Arial.ttf", pil=False, example="abc"):
        """Initialize the Annotator class with image and line width along with color palette for keypoints and limbs."""
        non_ascii = not is_ascii(example)  # non-latin labels, i.e. asian, arabic, cyrillic
        input_is_pil = isinstance(im, Image.Image)
        self.pil = pil or non_ascii or input_is_pil
        self.lw = line_width or max(round(sum(im.size if input_is_pil else im.shape) / 2 * 0.003), 2)
        if self.pil:  # use PIL
            self.im = im if input_is_pil else Image.fromarray(im)
            self.draw = ImageDraw.Draw(self.im)
            try:
                font = check_font("Arial.Unicode.ttf" if non_ascii else font)
                size = font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)
                self.font = ImageFont.truetype(str(font), size)
            except Exception:
                self.font = ImageFont.load_default()
            # Deprecation fix for w, h = getsize(string) -> _, _, w, h = getbox(string)
            if check_version(pil_version, "9.2.0"):
                self.font.getsize = lambda x: self.font.getbbox(x)[2:4]  # text width, height
        else:  # use cv2
            assert im.data.contiguous, "Image not contiguous. Apply np.ascontiguousarray(im) to Annotator input images."
            self.im = im if im.flags.writeable else im.copy()
            self.tf = max(self.lw - 1, 1)  # font thickness
            self.sf = self.lw / 3  # font scale
        # Pose
        self.skeleton = [
            [16, 14],
            [14, 12],
            [17, 15],
            [15, 13],
            [12, 13],
            [6, 12],
            [7, 13],
            [6, 7],
            [6, 8],
            [7, 9],
            [8, 10],
            [9, 11],
            [2, 3],
            [1, 2],
            [1, 3],
            [2, 4],
            [3, 5],
            [4, 6],
            [5, 7],
        ]

        self.limb_color = colors.pose_palette[[9, 9, 9, 9, 7, 7, 7, 0, 0, 0, 0, 0, 16, 16, 16, 16, 16, 16, 16]]
        self.kpt_color = colors.pose_palette[[16, 16, 16, 16, 16, 0, 0, 0, 0, 0, 0, 9, 9, 9, 9, 9, 9]]
        self.dark_colors = {
            (235, 219, 11),
            (243, 243, 243),
            (183, 223, 0),
            (221, 111, 255),
            (0, 237, 204),
            (68, 243, 0),
            (255, 255, 0),
            (179, 255, 1),
            (11, 255, 162),
        }
        self.light_colors = {
            (255, 42, 4),
            (79, 68, 255),
            (255, 0, 189),
            (255, 180, 0),
            (186, 0, 221),
            (0, 192, 38),
            (255, 36, 125),
            (104, 0, 123),
            (108, 27, 255),
            (47, 109, 252),
            (104, 31, 17),
        }

    def get_txt_color(self, color=(128, 128, 128), txt_color=(255, 255, 255)):
        """Assign text color based on background color."""
        if color in self.dark_colors:
            return 104, 31, 17
        elif color in self.light_colors:
            return 255, 255, 255
        else:
            return txt_color

    def circle_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), margin=2):
        """
        Draws a label with a background rectangle centered within a given bounding box.

        Args:
            box (tuple): The bounding box coordinates (x1, y1, x2, y2).
            label (str): The text label to be displayed.
            color (tuple, optional): The background color of the rectangle (R, G, B).
            txt_color (tuple, optional): The color of the text (R, G, B).
            margin (int, optional): The margin between the text and the rectangle border.
        """

        # If label have more than 3 characters, skip other characters, due to circle size
        if len(label) > 3:
            print(
                f"Length of label is {len(label)}, initial 3 label characters will be considered for circle annotation!"
            )
            label = label[:3]

        # Calculate the center of the box
        x_center, y_center = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
        # Get the text size
        text_size = cv2.getTextSize(str(label), cv2.FONT_HERSHEY_SIMPLEX, self.sf - 0.15, self.tf)[0]
        # Calculate the required radius to fit the text with the margin
        required_radius = int(((text_size[0] ** 2 + text_size[1] ** 2) ** 0.5) / 2) + margin
        # Draw the circle with the required radius
        cv2.circle(self.im, (x_center, y_center), required_radius, color, -1)
        # Calculate the position for the text
        text_x = x_center - text_size[0] // 2
        text_y = y_center + text_size[1] // 2
        # Draw the text
        cv2.putText(
            self.im,
            str(label),
            (text_x, text_y),
            cv2.FONT_HERSHEY_SIMPLEX,
            self.sf - 0.15,
            self.get_txt_color(color, txt_color),
            self.tf,
            lineType=cv2.LINE_AA,
        )

    def text_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), margin=5):
        """
        Draws a label with a background rectangle centered within a given bounding box.

        Args:
            box (tuple): The bounding box coordinates (x1, y1, x2, y2).
            label (str): The text label to be displayed.
            color (tuple, optional): The background color of the rectangle (R, G, B).
            txt_color (tuple, optional): The color of the text (R, G, B).
            margin (int, optional): The margin between the text and the rectangle border.
        """

        # Calculate the center of the bounding box
        x_center, y_center = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
        # Get the size of the text
        text_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, self.sf - 0.1, self.tf)[0]
        # Calculate the top-left corner of the text (to center it)
        text_x = x_center - text_size[0] // 2
        text_y = y_center + text_size[1] // 2
        # Calculate the coordinates of the background rectangle
        rect_x1 = text_x - margin
        rect_y1 = text_y - text_size[1] - margin
        rect_x2 = text_x + text_size[0] + margin
        rect_y2 = text_y + margin
        # Draw the background rectangle
        cv2.rectangle(self.im, (rect_x1, rect_y1), (rect_x2, rect_y2), color, -1)
        # Draw the text on top of the rectangle
        cv2.putText(
            self.im,
            label,
            (text_x, text_y),
            cv2.FONT_HERSHEY_SIMPLEX,
            self.sf - 0.1,
            self.get_txt_color(color, txt_color),
            self.tf,
            lineType=cv2.LINE_AA,
        )

    def box_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), rotated=False):
        """
        Draws a bounding box to image with label.

        Args:
            box (tuple): The bounding box coordinates (x1, y1, x2, y2).
            label (str): The text label to be displayed.
            color (tuple, optional): The background color of the rectangle (R, G, B).
            txt_color (tuple, optional): The color of the text (R, G, B).
            rotated (bool, optional): Variable used to check if task is OBB
        """

        txt_color = self.get_txt_color(color, txt_color)
        if isinstance(box, torch.Tensor):
            box = box.tolist()
        if self.pil or not is_ascii(label):
            if rotated:
                p1 = box[0]
                self.draw.polygon([tuple(b) for b in box], width=self.lw, outline=color)  # PIL requires tuple box
            else:
                p1 = (box[0], box[1])
                self.draw.rectangle(box, width=self.lw, outline=color)  # box
            if label:
                w, h = self.font.getsize(label)  # text width, height
                outside = p1[1] >= h  # label fits outside box
                if p1[0] > self.im.size[1] - w:  # check if label extend beyond right side of image
                    p1 = self.im.size[1] - w, p1[1]
                self.draw.rectangle(
                    (p1[0], p1[1] - h if outside else p1[1], p1[0] + w + 1, p1[1] + 1 if outside else p1[1] + h + 1),
                    fill=color,
                )
                # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls')  # for PIL>8.0
                self.draw.text((p1[0], p1[1] - h if outside else p1[1]), label, fill=txt_color, font=self.font)
        else:  # cv2
            if rotated:
                p1 = [int(b) for b in box[0]]
                cv2.polylines(self.im, [np.asarray(box, dtype=int)], True, color, self.lw)  # cv2 requires nparray box
            else:
                p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
                cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA)
            if label:
                w, h = cv2.getTextSize(label, 0, fontScale=self.sf, thickness=self.tf)[0]  # text width, height
                h += 3  # add pixels to pad text
                outside = p1[1] >= h  # label fits outside box
                if p1[0] > self.im.shape[1] - w:  # check if label extend beyond right side of image
                    p1 = self.im.shape[1] - w, p1[1]
                p2 = p1[0] + w, p1[1] - h if outside else p1[1] + h
                cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA)  # filled
                cv2.putText(
                    self.im,
                    label,
                    (p1[0], p1[1] - 2 if outside else p1[1] + h - 1),
                    0,
                    self.sf,
                    txt_color,
                    thickness=self.tf,
                    lineType=cv2.LINE_AA,
                )

    def masks(self, masks, colors, im_gpu, alpha=0.5, retina_masks=False):
        """
        Plot masks on image.

        Args:
            masks (tensor): Predicted masks on cuda, shape: [n, h, w]
            colors (List[List[Int]]): Colors for predicted masks, [[r, g, b] * n]
            im_gpu (tensor): Image is in cuda, shape: [3, h, w], range: [0, 1]
            alpha (float): Mask transparency: 0.0 fully transparent, 1.0 opaque
            retina_masks (bool): Whether to use high resolution masks or not. Defaults to False.
        """

        if self.pil:
            # Convert to numpy first
            self.im = np.asarray(self.im).copy()
        if len(masks) == 0:
            self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
        if im_gpu.device != masks.device:
            im_gpu = im_gpu.to(masks.device)
        colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0  # shape(n,3)
        colors = colors[:, None, None]  # shape(n,1,1,3)
        masks = masks.unsqueeze(3)  # shape(n,h,w,1)
        masks_color = masks * (colors * alpha)  # shape(n,h,w,3)

        inv_alpha_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
        mcs = masks_color.max(dim=0).values  # shape(n,h,w,3)

        im_gpu = im_gpu.flip(dims=[0])  # flip channel
        im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
        im_gpu = im_gpu * inv_alpha_masks[-1] + mcs
        im_mask = im_gpu * 255
        im_mask_np = im_mask.byte().cpu().numpy()
        self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape)
        if self.pil:
            # Convert im back to PIL and update draw
            self.fromarray(self.im)

    def kpts(self, kpts, shape=(640, 640), radius=5, kpt_line=True, conf_thres=0.25):
        """
        Plot keypoints on the image.

        Args:
            kpts (tensor): Predicted keypoints with shape [17, 3]. Each keypoint has (x, y, confidence).
            shape (tuple): Image shape as a tuple (h, w), where h is the height and w is the width.
            radius (int, optional): Radius of the drawn keypoints. Default is 5.
            kpt_line (bool, optional): If True, the function will draw lines connecting keypoints
                                       for human pose. Default is True.

        Note:
            `kpt_line=True` currently only supports human pose plotting.
        """

        if self.pil:
            # Convert to numpy first
            self.im = np.asarray(self.im).copy()
        nkpt, ndim = kpts.shape
        is_pose = nkpt == 17 and ndim in {2, 3}
        kpt_line &= is_pose  # `kpt_line=True` for now only supports human pose plotting
        for i, k in enumerate(kpts):
            color_k = [int(x) for x in self.kpt_color[i]] if is_pose else colors(i)
            x_coord, y_coord = k[0], k[1]
            if x_coord % shape[1] != 0 and y_coord % shape[0] != 0:
                if len(k) == 3:
                    conf = k[2]
                    if conf < conf_thres:
                        continue
                cv2.circle(self.im, (int(x_coord), int(y_coord)), radius, color_k, -1, lineType=cv2.LINE_AA)

        if kpt_line:
            ndim = kpts.shape[-1]
            for i, sk in enumerate(self.skeleton):
                pos1 = (int(kpts[(sk[0] - 1), 0]), int(kpts[(sk[0] - 1), 1]))
                pos2 = (int(kpts[(sk[1] - 1), 0]), int(kpts[(sk[1] - 1), 1]))
                if ndim == 3:
                    conf1 = kpts[(sk[0] - 1), 2]
                    conf2 = kpts[(sk[1] - 1), 2]
                    if conf1 < conf_thres or conf2 < conf_thres:
                        continue
                if pos1[0] % shape[1] == 0 or pos1[1] % shape[0] == 0 or pos1[0] < 0 or pos1[1] < 0:
                    continue
                if pos2[0] % shape[1] == 0 or pos2[1] % shape[0] == 0 or pos2[0] < 0 or pos2[1] < 0:
                    continue
                cv2.line(self.im, pos1, pos2, [int(x) for x in self.limb_color[i]], thickness=2, lineType=cv2.LINE_AA)
        if self.pil:
            # Convert im back to PIL and update draw
            self.fromarray(self.im)

    def rectangle(self, xy, fill=None, outline=None, width=1):
        """Add rectangle to image (PIL-only)."""
        self.draw.rectangle(xy, fill, outline, width)

    def text(self, xy, text, txt_color=(255, 255, 255), anchor="top", box_style=False):
        """Adds text to an image using PIL or cv2."""
        if anchor == "bottom":  # start y from font bottom
            w, h = self.font.getsize(text)  # text width, height
            xy[1] += 1 - h
        if self.pil:
            if box_style:
                w, h = self.font.getsize(text)
                self.draw.rectangle((xy[0], xy[1], xy[0] + w + 1, xy[1] + h + 1), fill=txt_color)
                # Using `txt_color` for background and draw fg with white color
                txt_color = (255, 255, 255)
            if "\n" in text:
                lines = text.split("\n")
                _, h = self.font.getsize(text)
                for line in lines:
                    self.draw.text(xy, line, fill=txt_color, font=self.font)
                    xy[1] += h
            else:
                self.draw.text(xy, text, fill=txt_color, font=self.font)
        else:
            if box_style:
                w, h = cv2.getTextSize(text, 0, fontScale=self.sf, thickness=self.tf)[0]  # text width, height
                h += 3  # add pixels to pad text
                outside = xy[1] >= h  # label fits outside box
                p2 = xy[0] + w, xy[1] - h if outside else xy[1] + h
                cv2.rectangle(self.im, xy, p2, txt_color, -1, cv2.LINE_AA)  # filled
                # Using `txt_color` for background and draw fg with white color
                txt_color = (255, 255, 255)
            cv2.putText(self.im, text, xy, 0, self.sf, txt_color, thickness=self.tf, lineType=cv2.LINE_AA)

    def fromarray(self, im):
        """Update self.im from a numpy array."""
        self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
        self.draw = ImageDraw.Draw(self.im)

    def result(self):
        """Return annotated image as array."""
        return np.asarray(self.im)

    def show(self, title=None):
        """Show the annotated image."""
        Image.fromarray(np.asarray(self.im)[..., ::-1]).show(title)

    def save(self, filename="image.jpg"):
        """Save the annotated image to 'filename'."""
        cv2.imwrite(filename, np.asarray(self.im))

    def get_bbox_dimension(self, bbox=None):
        """
        Calculate the area of a bounding box.

        Args:
            bbox (tuple): Bounding box coordinates in the format (x_min, y_min, x_max, y_max).

        Returns:
            angle (degree): Degree value of angle between three points
        """

        x_min, y_min, x_max, y_max = bbox
        width = x_max - x_min
        height = y_max - y_min
        return width, height, width * height

    def draw_region(self, reg_pts=None, color=(0, 255, 0), thickness=5):
        """
        Draw region line.

        Args:
            reg_pts (list): Region Points (for line 2 points, for region 4 points)
            color (tuple): Region Color value
            thickness (int): Region area thickness value
        """

        cv2.polylines(self.im, [np.array(reg_pts, dtype=np.int32)], isClosed=True, color=color, thickness=thickness)

    def draw_centroid_and_tracks(self, track, color=(255, 0, 255), track_thickness=2):
        """
        Draw centroid point and track trails.

        Args:
            track (list): object tracking points for trails display
            color (tuple): tracks line color
            track_thickness (int): track line thickness value
        """

        points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
        cv2.polylines(self.im, [points], isClosed=False, color=color, thickness=track_thickness)
        cv2.circle(self.im, (int(track[-1][0]), int(track[-1][1])), track_thickness * 2, color, -1)

    def queue_counts_display(self, label, points=None, region_color=(255, 255, 255), txt_color=(0, 0, 0)):
        """
        Displays queue counts on an image centered at the points with customizable font size and colors.

        Args:
            label (str): queue counts label
            points (tuple): region points for center point calculation to display text
            region_color (RGB): queue region color
            txt_color (RGB): text display color
        """

        x_values = [point[0] for point in points]
        y_values = [point[1] for point in points]
        center_x = sum(x_values) // len(points)
        center_y = sum(y_values) // len(points)

        text_size = cv2.getTextSize(label, 0, fontScale=self.sf, thickness=self.tf)[0]
        text_width = text_size[0]
        text_height = text_size[1]

        rect_width = text_width + 20
        rect_height = text_height + 20
        rect_top_left = (center_x - rect_width // 2, center_y - rect_height // 2)
        rect_bottom_right = (center_x + rect_width // 2, center_y + rect_height // 2)
        cv2.rectangle(self.im, rect_top_left, rect_bottom_right, region_color, -1)

        text_x = center_x - text_width // 2
        text_y = center_y + text_height // 2

        # Draw text
        cv2.putText(
            self.im,
            label,
            (text_x, text_y),
            0,
            fontScale=self.sf,
            color=txt_color,
            thickness=self.tf,
            lineType=cv2.LINE_AA,
        )

    def display_objects_labels(self, im0, text, txt_color, bg_color, x_center, y_center, margin):
        """
        Display the bounding boxes labels in parking management app.

        Args:
            im0 (ndarray): inference image
            text (str): object/class name
            txt_color (bgr color): display color for text foreground
            bg_color (bgr color): display color for text background
            x_center (float): x position center point for bounding box
            y_center (float): y position center point for bounding box
            margin (int): gap between text and rectangle for better display
        """

        text_size = cv2.getTextSize(text, 0, fontScale=self.sf, thickness=self.tf)[0]
        text_x = x_center - text_size[0] // 2
        text_y = y_center + text_size[1] // 2

        rect_x1 = text_x - margin
        rect_y1 = text_y - text_size[1] - margin
        rect_x2 = text_x + text_size[0] + margin
        rect_y2 = text_y + margin
        cv2.rectangle(im0, (rect_x1, rect_y1), (rect_x2, rect_y2), bg_color, -1)
        cv2.putText(im0, text, (text_x, text_y), 0, self.sf, txt_color, self.tf, lineType=cv2.LINE_AA)

    def display_analytics(self, im0, text, txt_color, bg_color, margin):
        """
        Display the overall statistics for parking lots
        Args:
            im0 (ndarray): inference image
            text (dict): labels dictionary
            txt_color (bgr color): display color for text foreground
            bg_color (bgr color): display color for text background
            margin (int): gap between text and rectangle for better display
        """

        horizontal_gap = int(im0.shape[1] * 0.02)
        vertical_gap = int(im0.shape[0] * 0.01)
        text_y_offset = 0
        for label, value in text.items():
            txt = f"{label}: {value}"
            text_size = cv2.getTextSize(txt, 0, self.sf, self.tf)[0]
            if text_size[0] < 5 or text_size[1] < 5:
                text_size = (5, 5)
            text_x = im0.shape[1] - text_size[0] - margin * 2 - horizontal_gap
            text_y = text_y_offset + text_size[1] + margin * 2 + vertical_gap
            rect_x1 = text_x - margin * 2
            rect_y1 = text_y - text_size[1] - margin * 2
            rect_x2 = text_x + text_size[0] + margin * 2
            rect_y2 = text_y + margin * 2
            cv2.rectangle(im0, (rect_x1, rect_y1), (rect_x2, rect_y2), bg_color, -1)
            cv2.putText(im0, txt, (text_x, text_y), 0, self.sf, txt_color, self.tf, lineType=cv2.LINE_AA)
            text_y_offset = rect_y2

    @staticmethod
    def estimate_pose_angle(a, b, c):
        """
        Calculate the pose angle for object.

        Args:
            a (float) : The value of pose point a
            b (float): The value of pose point b
            c (float): The value o pose point c

        Returns:
            angle (degree): Degree value of angle between three points
        """

        a, b, c = np.array(a), np.array(b), np.array(c)
        radians = np.arctan2(c[1] - b[1], c[0] - b[0]) - np.arctan2(a[1] - b[1], a[0] - b[0])
        angle = np.abs(radians * 180.0 / np.pi)
        if angle > 180.0:
            angle = 360 - angle
        return angle

    def draw_specific_points(self, keypoints, indices=None, shape=(640, 640), radius=2, conf_thres=0.25):
        """
        Draw specific keypoints for gym steps counting.

        Args:
            keypoints (list): list of keypoints data to be plotted
            indices (list): keypoints ids list to be plotted
            shape (tuple): imgsz for model inference
            radius (int): Keypoint radius value
        """

        if indices is None:
            indices = [2, 5, 7]
        for i, k in enumerate(keypoints):
            if i in indices:
                x_coord, y_coord = k[0], k[1]
                if x_coord % shape[1] != 0 and y_coord % shape[0] != 0:
                    if len(k) == 3:
                        conf = k[2]
                        if conf < conf_thres:
                            continue
                    cv2.circle(self.im, (int(x_coord), int(y_coord)), radius, (0, 255, 0), -1, lineType=cv2.LINE_AA)
        return self.im

    def plot_angle_and_count_and_stage(
        self, angle_text, count_text, stage_text, center_kpt, color=(104, 31, 17), txt_color=(255, 255, 255)
    ):
        """
        Plot the pose angle, count value and step stage.

        Args:
            angle_text (str): angle value for workout monitoring
            count_text (str): counts value for workout monitoring
            stage_text (str): stage decision for workout monitoring
            center_kpt (int): centroid pose index for workout monitoring
            color (tuple): text background color for workout monitoring
            txt_color (tuple): text foreground color for workout monitoring
        """

        angle_text, count_text, stage_text = (f" {angle_text:.2f}", f"Steps : {count_text}", f" {stage_text}")

        # Draw angle
        (angle_text_width, angle_text_height), _ = cv2.getTextSize(angle_text, 0, self.sf, self.tf)
        angle_text_position = (int(center_kpt[0]), int(center_kpt[1]))
        angle_background_position = (angle_text_position[0], angle_text_position[1] - angle_text_height - 5)
        angle_background_size = (angle_text_width + 2 * 5, angle_text_height + 2 * 5 + (self.tf * 2))
        cv2.rectangle(
            self.im,
            angle_background_position,
            (
                angle_background_position[0] + angle_background_size[0],
                angle_background_position[1] + angle_background_size[1],
            ),
            color,
            -1,
        )
        cv2.putText(self.im, angle_text, angle_text_position, 0, self.sf, txt_color, self.tf)

        # Draw Counts
        (count_text_width, count_text_height), _ = cv2.getTextSize(count_text, 0, self.sf, self.tf)
        count_text_position = (angle_text_position[0], angle_text_position[1] + angle_text_height + 20)
        count_background_position = (
            angle_background_position[0],
            angle_background_position[1] + angle_background_size[1] + 5,
        )
        count_background_size = (count_text_width + 10, count_text_height + 10 + self.tf)

        cv2.rectangle(
            self.im,
            count_background_position,
            (
                count_background_position[0] + count_background_size[0],
                count_background_position[1] + count_background_size[1],
            ),
            color,
            -1,
        )
        cv2.putText(self.im, count_text, count_text_position, 0, self.sf, txt_color, self.tf)

        # Draw Stage
        (stage_text_width, stage_text_height), _ = cv2.getTextSize(stage_text, 0, self.sf, self.tf)
        stage_text_position = (int(center_kpt[0]), int(center_kpt[1]) + angle_text_height + count_text_height + 40)
        stage_background_position = (stage_text_position[0], stage_text_position[1] - stage_text_height - 5)
        stage_background_size = (stage_text_width + 10, stage_text_height + 10)

        cv2.rectangle(
            self.im,
            stage_background_position,
            (
                stage_background_position[0] + stage_background_size[0],
                stage_background_position[1] + stage_background_size[1],
            ),
            color,
            -1,
        )
        cv2.putText(self.im, stage_text, stage_text_position, 0, self.sf, txt_color, self.tf)

    def seg_bbox(self, mask, mask_color=(255, 0, 255), det_label=None, track_label=None):
        """
        Function for drawing segmented object in bounding box shape.

        Args:
            mask (list): masks data list for instance segmentation area plotting
            mask_color (tuple): mask foreground color
            det_label (str): Detection label text
            track_label (str): Tracking label text
        """

        cv2.polylines(self.im, [np.int32([mask])], isClosed=True, color=mask_color, thickness=2)

        label = f"Track ID: {track_label}" if track_label else det_label
        text_size, _ = cv2.getTextSize(label, 0, 0.7, 1)

        cv2.rectangle(
            self.im,
            (int(mask[0][0]) - text_size[0] // 2 - 10, int(mask[0][1]) - text_size[1] - 10),
            (int(mask[0][0]) + text_size[0] // 2 + 5, int(mask[0][1] + 5)),
            mask_color,
            -1,
        )

        cv2.putText(
            self.im, label, (int(mask[0][0]) - text_size[0] // 2, int(mask[0][1]) - 5), 0, 0.7, (255, 255, 255), 2
        )

    def plot_distance_and_line(self, distance_m, distance_mm, centroids, line_color, centroid_color):
        """
        Plot the distance and line on frame.

        Args:
            distance_m (float): Distance between two bbox centroids in meters.
            distance_mm (float): Distance between two bbox centroids in millimeters.
            centroids (list): Bounding box centroids data.
            line_color (RGB): Distance line color.
            centroid_color (RGB): Bounding box centroid color.
        """

        (text_width_m, text_height_m), _ = cv2.getTextSize(f"Distance M: {distance_m:.2f}m", 0, self.sf, self.tf)
        cv2.rectangle(self.im, (15, 25), (15 + text_width_m + 10, 25 + text_height_m + 20), line_color, -1)
        cv2.putText(
            self.im,
            f"Distance M: {distance_m:.2f}m",
            (20, 50),
            0,
            self.sf,
            centroid_color,
            self.tf,
            cv2.LINE_AA,
        )

        (text_width_mm, text_height_mm), _ = cv2.getTextSize(f"Distance MM: {distance_mm:.2f}mm", 0, self.sf, self.tf)
        cv2.rectangle(self.im, (15, 75), (15 + text_width_mm + 10, 75 + text_height_mm + 20), line_color, -1)
        cv2.putText(
            self.im,
            f"Distance MM: {distance_mm:.2f}mm",
            (20, 100),
            0,
            self.sf,
            centroid_color,
            self.tf,
            cv2.LINE_AA,
        )

        cv2.line(self.im, centroids[0], centroids[1], line_color, 3)
        cv2.circle(self.im, centroids[0], 6, centroid_color, -1)
        cv2.circle(self.im, centroids[1], 6, centroid_color, -1)

    def visioneye(self, box, center_point, color=(235, 219, 11), pin_color=(255, 0, 255)):
        """
        Function for pinpoint human-vision eye mapping and plotting.

        Args:
            box (list): Bounding box coordinates
            center_point (tuple): center point for vision eye view
            color (tuple): object centroid and line color value
            pin_color (tuple): visioneye point color value
        """

        center_bbox = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
        cv2.circle(self.im, center_point, self.tf * 2, pin_color, -1)
        cv2.circle(self.im, center_bbox, self.tf * 2, color, -1)
        cv2.line(self.im, center_point, center_bbox, color, self.tf)

__init__(im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc')

画像と線幅、キーポイントと手足のカラーパレットでアノテーター・クラスを初期化する。

ソースコード ultralytics/utils/plotting.py
def __init__(self, im, line_width=None, font_size=None, font="Arial.ttf", pil=False, example="abc"):
    """Initialize the Annotator class with image and line width along with color palette for keypoints and limbs."""
    non_ascii = not is_ascii(example)  # non-latin labels, i.e. asian, arabic, cyrillic
    input_is_pil = isinstance(im, Image.Image)
    self.pil = pil or non_ascii or input_is_pil
    self.lw = line_width or max(round(sum(im.size if input_is_pil else im.shape) / 2 * 0.003), 2)
    if self.pil:  # use PIL
        self.im = im if input_is_pil else Image.fromarray(im)
        self.draw = ImageDraw.Draw(self.im)
        try:
            font = check_font("Arial.Unicode.ttf" if non_ascii else font)
            size = font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)
            self.font = ImageFont.truetype(str(font), size)
        except Exception:
            self.font = ImageFont.load_default()
        # Deprecation fix for w, h = getsize(string) -> _, _, w, h = getbox(string)
        if check_version(pil_version, "9.2.0"):
            self.font.getsize = lambda x: self.font.getbbox(x)[2:4]  # text width, height
    else:  # use cv2
        assert im.data.contiguous, "Image not contiguous. Apply np.ascontiguousarray(im) to Annotator input images."
        self.im = im if im.flags.writeable else im.copy()
        self.tf = max(self.lw - 1, 1)  # font thickness
        self.sf = self.lw / 3  # font scale
    # Pose
    self.skeleton = [
        [16, 14],
        [14, 12],
        [17, 15],
        [15, 13],
        [12, 13],
        [6, 12],
        [7, 13],
        [6, 7],
        [6, 8],
        [7, 9],
        [8, 10],
        [9, 11],
        [2, 3],
        [1, 2],
        [1, 3],
        [2, 4],
        [3, 5],
        [4, 6],
        [5, 7],
    ]

    self.limb_color = colors.pose_palette[[9, 9, 9, 9, 7, 7, 7, 0, 0, 0, 0, 0, 16, 16, 16, 16, 16, 16, 16]]
    self.kpt_color = colors.pose_palette[[16, 16, 16, 16, 16, 0, 0, 0, 0, 0, 0, 9, 9, 9, 9, 9, 9]]
    self.dark_colors = {
        (235, 219, 11),
        (243, 243, 243),
        (183, 223, 0),
        (221, 111, 255),
        (0, 237, 204),
        (68, 243, 0),
        (255, 255, 0),
        (179, 255, 1),
        (11, 255, 162),
    }
    self.light_colors = {
        (255, 42, 4),
        (79, 68, 255),
        (255, 0, 189),
        (255, 180, 0),
        (186, 0, 221),
        (0, 192, 38),
        (255, 36, 125),
        (104, 0, 123),
        (108, 27, 255),
        (47, 109, 252),
        (104, 31, 17),
    }

box_label(box, label='', color=(128, 128, 128), txt_color=(255, 255, 255), rotated=False)

Draws a bounding box to image with label.

パラメーター

名称 タイプ 説明 デフォルト
box tuple

The bounding box coordinates (x1, y1, x2, y2).

必須
label str

The text label to be displayed.

''
color tuple

The background color of the rectangle (R, G, B).

(128, 128, 128)
txt_color tuple

The color of the text (R, G, B).

(255, 255, 255)
rotated bool

Variable used to check if task is OBB

False
ソースコード ultralytics/utils/plotting.py
def box_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), rotated=False):
    """
    Draws a bounding box to image with label.

    Args:
        box (tuple): The bounding box coordinates (x1, y1, x2, y2).
        label (str): The text label to be displayed.
        color (tuple, optional): The background color of the rectangle (R, G, B).
        txt_color (tuple, optional): The color of the text (R, G, B).
        rotated (bool, optional): Variable used to check if task is OBB
    """

    txt_color = self.get_txt_color(color, txt_color)
    if isinstance(box, torch.Tensor):
        box = box.tolist()
    if self.pil or not is_ascii(label):
        if rotated:
            p1 = box[0]
            self.draw.polygon([tuple(b) for b in box], width=self.lw, outline=color)  # PIL requires tuple box
        else:
            p1 = (box[0], box[1])
            self.draw.rectangle(box, width=self.lw, outline=color)  # box
        if label:
            w, h = self.font.getsize(label)  # text width, height
            outside = p1[1] >= h  # label fits outside box
            if p1[0] > self.im.size[1] - w:  # check if label extend beyond right side of image
                p1 = self.im.size[1] - w, p1[1]
            self.draw.rectangle(
                (p1[0], p1[1] - h if outside else p1[1], p1[0] + w + 1, p1[1] + 1 if outside else p1[1] + h + 1),
                fill=color,
            )
            # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls')  # for PIL>8.0
            self.draw.text((p1[0], p1[1] - h if outside else p1[1]), label, fill=txt_color, font=self.font)
    else:  # cv2
        if rotated:
            p1 = [int(b) for b in box[0]]
            cv2.polylines(self.im, [np.asarray(box, dtype=int)], True, color, self.lw)  # cv2 requires nparray box
        else:
            p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
            cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA)
        if label:
            w, h = cv2.getTextSize(label, 0, fontScale=self.sf, thickness=self.tf)[0]  # text width, height
            h += 3  # add pixels to pad text
            outside = p1[1] >= h  # label fits outside box
            if p1[0] > self.im.shape[1] - w:  # check if label extend beyond right side of image
                p1 = self.im.shape[1] - w, p1[1]
            p2 = p1[0] + w, p1[1] - h if outside else p1[1] + h
            cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA)  # filled
            cv2.putText(
                self.im,
                label,
                (p1[0], p1[1] - 2 if outside else p1[1] + h - 1),
                0,
                self.sf,
                txt_color,
                thickness=self.tf,
                lineType=cv2.LINE_AA,
            )

circle_label(box, label='', color=(128, 128, 128), txt_color=(255, 255, 255), margin=2)

Draws a label with a background rectangle centered within a given bounding box.

パラメーター

名称 タイプ 説明 デフォルト
box tuple

The bounding box coordinates (x1, y1, x2, y2).

必須
label str

The text label to be displayed.

''
color tuple

The background color of the rectangle (R, G, B).

(128, 128, 128)
txt_color tuple

The color of the text (R, G, B).

(255, 255, 255)
margin int

The margin between the text and the rectangle border.

2
ソースコード ultralytics/utils/plotting.py
def circle_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), margin=2):
    """
    Draws a label with a background rectangle centered within a given bounding box.

    Args:
        box (tuple): The bounding box coordinates (x1, y1, x2, y2).
        label (str): The text label to be displayed.
        color (tuple, optional): The background color of the rectangle (R, G, B).
        txt_color (tuple, optional): The color of the text (R, G, B).
        margin (int, optional): The margin between the text and the rectangle border.
    """

    # If label have more than 3 characters, skip other characters, due to circle size
    if len(label) > 3:
        print(
            f"Length of label is {len(label)}, initial 3 label characters will be considered for circle annotation!"
        )
        label = label[:3]

    # Calculate the center of the box
    x_center, y_center = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
    # Get the text size
    text_size = cv2.getTextSize(str(label), cv2.FONT_HERSHEY_SIMPLEX, self.sf - 0.15, self.tf)[0]
    # Calculate the required radius to fit the text with the margin
    required_radius = int(((text_size[0] ** 2 + text_size[1] ** 2) ** 0.5) / 2) + margin
    # Draw the circle with the required radius
    cv2.circle(self.im, (x_center, y_center), required_radius, color, -1)
    # Calculate the position for the text
    text_x = x_center - text_size[0] // 2
    text_y = y_center + text_size[1] // 2
    # Draw the text
    cv2.putText(
        self.im,
        str(label),
        (text_x, text_y),
        cv2.FONT_HERSHEY_SIMPLEX,
        self.sf - 0.15,
        self.get_txt_color(color, txt_color),
        self.tf,
        lineType=cv2.LINE_AA,
    )

display_analytics(im0, text, txt_color, bg_color, margin)

駐車場の全体的な統計を表示する 引数 im0 (ndarray): 推測画像 text (dict): ラベル辞書 txt_color (bgr color): テキストの前景色を表示する色 bg_color (bgr カラー): テキストの背景色。 margin (int): テキストと矩形の間の隙間。

ソースコード ultralytics/utils/plotting.py
def display_analytics(self, im0, text, txt_color, bg_color, margin):
    """
    Display the overall statistics for parking lots
    Args:
        im0 (ndarray): inference image
        text (dict): labels dictionary
        txt_color (bgr color): display color for text foreground
        bg_color (bgr color): display color for text background
        margin (int): gap between text and rectangle for better display
    """

    horizontal_gap = int(im0.shape[1] * 0.02)
    vertical_gap = int(im0.shape[0] * 0.01)
    text_y_offset = 0
    for label, value in text.items():
        txt = f"{label}: {value}"
        text_size = cv2.getTextSize(txt, 0, self.sf, self.tf)[0]
        if text_size[0] < 5 or text_size[1] < 5:
            text_size = (5, 5)
        text_x = im0.shape[1] - text_size[0] - margin * 2 - horizontal_gap
        text_y = text_y_offset + text_size[1] + margin * 2 + vertical_gap
        rect_x1 = text_x - margin * 2
        rect_y1 = text_y - text_size[1] - margin * 2
        rect_x2 = text_x + text_size[0] + margin * 2
        rect_y2 = text_y + margin * 2
        cv2.rectangle(im0, (rect_x1, rect_y1), (rect_x2, rect_y2), bg_color, -1)
        cv2.putText(im0, txt, (text_x, text_y), 0, self.sf, txt_color, self.tf, lineType=cv2.LINE_AA)
        text_y_offset = rect_y2

display_objects_labels(im0, text, txt_color, bg_color, x_center, y_center, margin)

駐車場管理アプリにバウンディングボックスのラベルを表示する。

パラメーター

名称 タイプ 説明 デフォルト
im0 ndarray

推論イメージ

必須
text str

オブジェクト/クラス名

必須
txt_color bgr color

テキスト前景の表示色

必須
bg_color bgr color

テキスト背景の表示色

必須
x_center float

バウンディングボックスのx位置中心点

必須
y_center float

y 位置 外接ボックスの中心点

必須
margin int

テキストと矩形の間のギャップをより見やすく

必須
ソースコード ultralytics/utils/plotting.py
def display_objects_labels(self, im0, text, txt_color, bg_color, x_center, y_center, margin):
    """
    Display the bounding boxes labels in parking management app.

    Args:
        im0 (ndarray): inference image
        text (str): object/class name
        txt_color (bgr color): display color for text foreground
        bg_color (bgr color): display color for text background
        x_center (float): x position center point for bounding box
        y_center (float): y position center point for bounding box
        margin (int): gap between text and rectangle for better display
    """

    text_size = cv2.getTextSize(text, 0, fontScale=self.sf, thickness=self.tf)[0]
    text_x = x_center - text_size[0] // 2
    text_y = y_center + text_size[1] // 2

    rect_x1 = text_x - margin
    rect_y1 = text_y - text_size[1] - margin
    rect_x2 = text_x + text_size[0] + margin
    rect_y2 = text_y + margin
    cv2.rectangle(im0, (rect_x1, rect_y1), (rect_x2, rect_y2), bg_color, -1)
    cv2.putText(im0, text, (text_x, text_y), 0, self.sf, txt_color, self.tf, lineType=cv2.LINE_AA)

draw_centroid_and_tracks(track, color=(255, 0, 255), track_thickness=2)

重心点とトラックの軌跡を描く。

パラメーター

名称 タイプ 説明 デフォルト
track list

軌跡表示のためのオブジェクト追跡ポイント

必須
color tuple

トラック・ライン・カラー

(255, 0, 255)
track_thickness int

トラック線の太さの値

2
ソースコード ultralytics/utils/plotting.py
def draw_centroid_and_tracks(self, track, color=(255, 0, 255), track_thickness=2):
    """
    Draw centroid point and track trails.

    Args:
        track (list): object tracking points for trails display
        color (tuple): tracks line color
        track_thickness (int): track line thickness value
    """

    points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
    cv2.polylines(self.im, [points], isClosed=False, color=color, thickness=track_thickness)
    cv2.circle(self.im, (int(track[-1][0]), int(track[-1][1])), track_thickness * 2, color, -1)

draw_region(reg_pts=None, color=(0, 255, 0), thickness=5)

リージョン・ラインを引く。

パラメーター

名称 タイプ 説明 デフォルト
reg_pts list

リージョンポイント(ライン2ポイント用、リージョン4ポイント用)

None
color tuple

リージョンカラー値

(0, 255, 0)
thickness int

領域面積厚さ値

5
ソースコード ultralytics/utils/plotting.py
def draw_region(self, reg_pts=None, color=(0, 255, 0), thickness=5):
    """
    Draw region line.

    Args:
        reg_pts (list): Region Points (for line 2 points, for region 4 points)
        color (tuple): Region Color value
        thickness (int): Region area thickness value
    """

    cv2.polylines(self.im, [np.array(reg_pts, dtype=np.int32)], isClosed=True, color=color, thickness=thickness)

draw_specific_points(keypoints, indices=None, shape=(640, 640), radius=2, conf_thres=0.25)

ジムの歩数カウントの具体的なキーポイントを描く。

パラメーター

名称 タイプ 説明 デフォルト
keypoints list

プロットするキーポイントデータのリスト

必須
indices list

プロットされるキーポイントIDリスト

None
shape tuple

モデル推論用imgsz

(640, 640)
radius int

キーポイント半径値

2
ソースコード ultralytics/utils/plotting.py
def draw_specific_points(self, keypoints, indices=None, shape=(640, 640), radius=2, conf_thres=0.25):
    """
    Draw specific keypoints for gym steps counting.

    Args:
        keypoints (list): list of keypoints data to be plotted
        indices (list): keypoints ids list to be plotted
        shape (tuple): imgsz for model inference
        radius (int): Keypoint radius value
    """

    if indices is None:
        indices = [2, 5, 7]
    for i, k in enumerate(keypoints):
        if i in indices:
            x_coord, y_coord = k[0], k[1]
            if x_coord % shape[1] != 0 and y_coord % shape[0] != 0:
                if len(k) == 3:
                    conf = k[2]
                    if conf < conf_thres:
                        continue
                cv2.circle(self.im, (int(x_coord), int(y_coord)), radius, (0, 255, 0), -1, lineType=cv2.LINE_AA)
    return self.im

estimate_pose_angle(a, b, c) staticmethod

オブジェクトのポーズ角度を計算する。

パラメーター

名称 タイプ 説明 デフォルト
a float)

ポーズポイントaの値

必須
b float

ポーズポイントbの値

必須
c float

ポーズポイントcの値

必須

リターンズ

名称 タイプ 説明
angle degree

3点間の角度の度数値

ソースコード ultralytics/utils/plotting.py
@staticmethod
def estimate_pose_angle(a, b, c):
    """
    Calculate the pose angle for object.

    Args:
        a (float) : The value of pose point a
        b (float): The value of pose point b
        c (float): The value o pose point c

    Returns:
        angle (degree): Degree value of angle between three points
    """

    a, b, c = np.array(a), np.array(b), np.array(c)
    radians = np.arctan2(c[1] - b[1], c[0] - b[0]) - np.arctan2(a[1] - b[1], a[0] - b[0])
    angle = np.abs(radians * 180.0 / np.pi)
    if angle > 180.0:
        angle = 360 - angle
    return angle

fromarray(im)

numpy配列からself.imを更新する。

ソースコード ultralytics/utils/plotting.py
def fromarray(self, im):
    """Update self.im from a numpy array."""
    self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
    self.draw = ImageDraw.Draw(self.im)

get_bbox_dimension(bbox=None)

バウンディングボックスの面積を計算します。

パラメーター

名称 タイプ 説明 デフォルト
bbox tuple

x_min, y_min, x_max, y_max)形式のバウンディングボックス座標。

None

リターンズ

名称 タイプ 説明
angle degree

3点間の角度の度数値

ソースコード ultralytics/utils/plotting.py
def get_bbox_dimension(self, bbox=None):
    """
    Calculate the area of a bounding box.

    Args:
        bbox (tuple): Bounding box coordinates in the format (x_min, y_min, x_max, y_max).

    Returns:
        angle (degree): Degree value of angle between three points
    """

    x_min, y_min, x_max, y_max = bbox
    width = x_max - x_min
    height = y_max - y_min
    return width, height, width * height

get_txt_color(color=(128, 128, 128), txt_color=(255, 255, 255))

Assign text color based on background color.

ソースコード ultralytics/utils/plotting.py
def get_txt_color(self, color=(128, 128, 128), txt_color=(255, 255, 255)):
    """Assign text color based on background color."""
    if color in self.dark_colors:
        return 104, 31, 17
    elif color in self.light_colors:
        return 255, 255, 255
    else:
        return txt_color

kpts(kpts, shape=(640, 640), radius=5, kpt_line=True, conf_thres=0.25)

画像上にキーポイントをプロットする。

パラメーター

名称 タイプ 説明 デフォルト
kpts tensor

形状[17, 3]を持つ予測キーポイント。各キーポイントは(x, y, confidence)を持つ。

必須
shape tuple

hは高さ、wは幅。

(640, 640)
radius int

描画されるキーポイントの半径。デフォルトは5。

5
kpt_line bool

Trueの場合、この関数はキーポイントを結ぶ線を描画します。 を描画します。デフォルトは True。

True
注

kpt_line=True 現在のところ、人間のポーズプロットしかサポートしていない。

ソースコード ultralytics/utils/plotting.py
def kpts(self, kpts, shape=(640, 640), radius=5, kpt_line=True, conf_thres=0.25):
    """
    Plot keypoints on the image.

    Args:
        kpts (tensor): Predicted keypoints with shape [17, 3]. Each keypoint has (x, y, confidence).
        shape (tuple): Image shape as a tuple (h, w), where h is the height and w is the width.
        radius (int, optional): Radius of the drawn keypoints. Default is 5.
        kpt_line (bool, optional): If True, the function will draw lines connecting keypoints
                                   for human pose. Default is True.

    Note:
        `kpt_line=True` currently only supports human pose plotting.
    """

    if self.pil:
        # Convert to numpy first
        self.im = np.asarray(self.im).copy()
    nkpt, ndim = kpts.shape
    is_pose = nkpt == 17 and ndim in {2, 3}
    kpt_line &= is_pose  # `kpt_line=True` for now only supports human pose plotting
    for i, k in enumerate(kpts):
        color_k = [int(x) for x in self.kpt_color[i]] if is_pose else colors(i)
        x_coord, y_coord = k[0], k[1]
        if x_coord % shape[1] != 0 and y_coord % shape[0] != 0:
            if len(k) == 3:
                conf = k[2]
                if conf < conf_thres:
                    continue
            cv2.circle(self.im, (int(x_coord), int(y_coord)), radius, color_k, -1, lineType=cv2.LINE_AA)

    if kpt_line:
        ndim = kpts.shape[-1]
        for i, sk in enumerate(self.skeleton):
            pos1 = (int(kpts[(sk[0] - 1), 0]), int(kpts[(sk[0] - 1), 1]))
            pos2 = (int(kpts[(sk[1] - 1), 0]), int(kpts[(sk[1] - 1), 1]))
            if ndim == 3:
                conf1 = kpts[(sk[0] - 1), 2]
                conf2 = kpts[(sk[1] - 1), 2]
                if conf1 < conf_thres or conf2 < conf_thres:
                    continue
            if pos1[0] % shape[1] == 0 or pos1[1] % shape[0] == 0 or pos1[0] < 0 or pos1[1] < 0:
                continue
            if pos2[0] % shape[1] == 0 or pos2[1] % shape[0] == 0 or pos2[0] < 0 or pos2[1] < 0:
                continue
            cv2.line(self.im, pos1, pos2, [int(x) for x in self.limb_color[i]], thickness=2, lineType=cv2.LINE_AA)
    if self.pil:
        # Convert im back to PIL and update draw
        self.fromarray(self.im)

masks(masks, colors, im_gpu, alpha=0.5, retina_masks=False)

画像にマスクをプロットする。

パラメーター

名称 タイプ 説明 デフォルト
masks tensor

cudaで予測されるマスク、形状:[n, h, w]

必須
colors List[List[Int]]

予測マスクの色, [[r, g, b] * n].

必須
im_gpu tensor

画像はcudaで、形状は[3, h, w]、範囲:[0, 1]

必須
alpha float

マスクの透明度:0.0完全透明、1.0不透明

0.5
retina_masks bool

高解像度マスクを使用するかどうか。デフォルトは False。

False
ソースコード ultralytics/utils/plotting.py
def masks(self, masks, colors, im_gpu, alpha=0.5, retina_masks=False):
    """
    Plot masks on image.

    Args:
        masks (tensor): Predicted masks on cuda, shape: [n, h, w]
        colors (List[List[Int]]): Colors for predicted masks, [[r, g, b] * n]
        im_gpu (tensor): Image is in cuda, shape: [3, h, w], range: [0, 1]
        alpha (float): Mask transparency: 0.0 fully transparent, 1.0 opaque
        retina_masks (bool): Whether to use high resolution masks or not. Defaults to False.
    """

    if self.pil:
        # Convert to numpy first
        self.im = np.asarray(self.im).copy()
    if len(masks) == 0:
        self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
    if im_gpu.device != masks.device:
        im_gpu = im_gpu.to(masks.device)
    colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0  # shape(n,3)
    colors = colors[:, None, None]  # shape(n,1,1,3)
    masks = masks.unsqueeze(3)  # shape(n,h,w,1)
    masks_color = masks * (colors * alpha)  # shape(n,h,w,3)

    inv_alpha_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
    mcs = masks_color.max(dim=0).values  # shape(n,h,w,3)

    im_gpu = im_gpu.flip(dims=[0])  # flip channel
    im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
    im_gpu = im_gpu * inv_alpha_masks[-1] + mcs
    im_mask = im_gpu * 255
    im_mask_np = im_mask.byte().cpu().numpy()
    self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape)
    if self.pil:
        # Convert im back to PIL and update draw
        self.fromarray(self.im)

plot_angle_and_count_and_stage(angle_text, count_text, stage_text, center_kpt, color=(104, 31, 17), txt_color=(255, 255, 255))

ポーズ角度、カウント値、ステップステージをプロットする。

パラメーター

名称 タイプ 説明 デフォルト
angle_text str

ワークアウト監視のための角度値

必須
count_text str

ワークアウト監視のためのカウント値

必須
stage_text str

ワークアウト・モニタリングのステージ決定

必須
center_kpt int

ワークアウト監視のための重心ポーズ指数

必須
color tuple

ワークアウトモニターのテキスト背景色

(104, 31, 17)
txt_color tuple

ワークアウトモニターのテキストの前景色

(255, 255, 255)
ソースコード ultralytics/utils/plotting.py
def plot_angle_and_count_and_stage(
    self, angle_text, count_text, stage_text, center_kpt, color=(104, 31, 17), txt_color=(255, 255, 255)
):
    """
    Plot the pose angle, count value and step stage.

    Args:
        angle_text (str): angle value for workout monitoring
        count_text (str): counts value for workout monitoring
        stage_text (str): stage decision for workout monitoring
        center_kpt (int): centroid pose index for workout monitoring
        color (tuple): text background color for workout monitoring
        txt_color (tuple): text foreground color for workout monitoring
    """

    angle_text, count_text, stage_text = (f" {angle_text:.2f}", f"Steps : {count_text}", f" {stage_text}")

    # Draw angle
    (angle_text_width, angle_text_height), _ = cv2.getTextSize(angle_text, 0, self.sf, self.tf)
    angle_text_position = (int(center_kpt[0]), int(center_kpt[1]))
    angle_background_position = (angle_text_position[0], angle_text_position[1] - angle_text_height - 5)
    angle_background_size = (angle_text_width + 2 * 5, angle_text_height + 2 * 5 + (self.tf * 2))
    cv2.rectangle(
        self.im,
        angle_background_position,
        (
            angle_background_position[0] + angle_background_size[0],
            angle_background_position[1] + angle_background_size[1],
        ),
        color,
        -1,
    )
    cv2.putText(self.im, angle_text, angle_text_position, 0, self.sf, txt_color, self.tf)

    # Draw Counts
    (count_text_width, count_text_height), _ = cv2.getTextSize(count_text, 0, self.sf, self.tf)
    count_text_position = (angle_text_position[0], angle_text_position[1] + angle_text_height + 20)
    count_background_position = (
        angle_background_position[0],
        angle_background_position[1] + angle_background_size[1] + 5,
    )
    count_background_size = (count_text_width + 10, count_text_height + 10 + self.tf)

    cv2.rectangle(
        self.im,
        count_background_position,
        (
            count_background_position[0] + count_background_size[0],
            count_background_position[1] + count_background_size[1],
        ),
        color,
        -1,
    )
    cv2.putText(self.im, count_text, count_text_position, 0, self.sf, txt_color, self.tf)

    # Draw Stage
    (stage_text_width, stage_text_height), _ = cv2.getTextSize(stage_text, 0, self.sf, self.tf)
    stage_text_position = (int(center_kpt[0]), int(center_kpt[1]) + angle_text_height + count_text_height + 40)
    stage_background_position = (stage_text_position[0], stage_text_position[1] - stage_text_height - 5)
    stage_background_size = (stage_text_width + 10, stage_text_height + 10)

    cv2.rectangle(
        self.im,
        stage_background_position,
        (
            stage_background_position[0] + stage_background_size[0],
            stage_background_position[1] + stage_background_size[1],
        ),
        color,
        -1,
    )
    cv2.putText(self.im, stage_text, stage_text_position, 0, self.sf, txt_color, self.tf)

plot_distance_and_line(distance_m, distance_mm, centroids, line_color, centroid_color)

距離とラインをフレームにプロットする。

パラメーター

名称 タイプ 説明 デフォルト
distance_m float

2つのbboxの中心間の距離(メートル単位)。

必須
distance_mm float

2つのbboxの中心点間の距離(ミリメートル単位)。

必須
centroids list

バウンディングボックスのセントロイドデータ。

必須
line_color RGB

距離線の色。

必須
centroid_color RGB

バウンディングボックスの重心の色。

必須
ソースコード ultralytics/utils/plotting.py
def plot_distance_and_line(self, distance_m, distance_mm, centroids, line_color, centroid_color):
    """
    Plot the distance and line on frame.

    Args:
        distance_m (float): Distance between two bbox centroids in meters.
        distance_mm (float): Distance between two bbox centroids in millimeters.
        centroids (list): Bounding box centroids data.
        line_color (RGB): Distance line color.
        centroid_color (RGB): Bounding box centroid color.
    """

    (text_width_m, text_height_m), _ = cv2.getTextSize(f"Distance M: {distance_m:.2f}m", 0, self.sf, self.tf)
    cv2.rectangle(self.im, (15, 25), (15 + text_width_m + 10, 25 + text_height_m + 20), line_color, -1)
    cv2.putText(
        self.im,
        f"Distance M: {distance_m:.2f}m",
        (20, 50),
        0,
        self.sf,
        centroid_color,
        self.tf,
        cv2.LINE_AA,
    )

    (text_width_mm, text_height_mm), _ = cv2.getTextSize(f"Distance MM: {distance_mm:.2f}mm", 0, self.sf, self.tf)
    cv2.rectangle(self.im, (15, 75), (15 + text_width_mm + 10, 75 + text_height_mm + 20), line_color, -1)
    cv2.putText(
        self.im,
        f"Distance MM: {distance_mm:.2f}mm",
        (20, 100),
        0,
        self.sf,
        centroid_color,
        self.tf,
        cv2.LINE_AA,
    )

    cv2.line(self.im, centroids[0], centroids[1], line_color, 3)
    cv2.circle(self.im, centroids[0], 6, centroid_color, -1)
    cv2.circle(self.im, centroids[1], 6, centroid_color, -1)

queue_counts_display(label, points=None, region_color=(255, 255, 255), txt_color=(0, 0, 0))

カスタマイズ可能なフォントサイズと色で、キューカウントをポイント中心の画像上に表示します。

パラメーター

名称 タイプ 説明 デフォルト
label str

キューカウントラベル

必須
points tuple

テキストを表示するための中心点計算のための領域点

None
region_color RGB

キュー領域の色

(255, 255, 255)
txt_color RGB

テキスト表示色

(0, 0, 0)
ソースコード ultralytics/utils/plotting.py
def queue_counts_display(self, label, points=None, region_color=(255, 255, 255), txt_color=(0, 0, 0)):
    """
    Displays queue counts on an image centered at the points with customizable font size and colors.

    Args:
        label (str): queue counts label
        points (tuple): region points for center point calculation to display text
        region_color (RGB): queue region color
        txt_color (RGB): text display color
    """

    x_values = [point[0] for point in points]
    y_values = [point[1] for point in points]
    center_x = sum(x_values) // len(points)
    center_y = sum(y_values) // len(points)

    text_size = cv2.getTextSize(label, 0, fontScale=self.sf, thickness=self.tf)[0]
    text_width = text_size[0]
    text_height = text_size[1]

    rect_width = text_width + 20
    rect_height = text_height + 20
    rect_top_left = (center_x - rect_width // 2, center_y - rect_height // 2)
    rect_bottom_right = (center_x + rect_width // 2, center_y + rect_height // 2)
    cv2.rectangle(self.im, rect_top_left, rect_bottom_right, region_color, -1)

    text_x = center_x - text_width // 2
    text_y = center_y + text_height // 2

    # Draw text
    cv2.putText(
        self.im,
        label,
        (text_x, text_y),
        0,
        fontScale=self.sf,
        color=txt_color,
        thickness=self.tf,
        lineType=cv2.LINE_AA,
    )

rectangle(xy, fill=None, outline=None, width=1)

画像に矩形を追加する(PILのみ)。

ソースコード ultralytics/utils/plotting.py
def rectangle(self, xy, fill=None, outline=None, width=1):
    """Add rectangle to image (PIL-only)."""
    self.draw.rectangle(xy, fill, outline, width)

result()

注釈付き画像を配列で返します。

ソースコード ultralytics/utils/plotting.py
def result(self):
    """Return annotated image as array."""
    return np.asarray(self.im)

save(filename='image.jpg')

注釈付き画像を「ファイル名」に保存する。

ソースコード ultralytics/utils/plotting.py
def save(self, filename="image.jpg"):
    """Save the annotated image to 'filename'."""
    cv2.imwrite(filename, np.asarray(self.im))

seg_bbox(mask, mask_color=(255, 0, 255), det_label=None, track_label=None)

分割されたオブジェクトをバウンディングボックス状に描画する関数。

パラメーター

名称 タイプ 説明 デフォルト
mask list

セグメンテーション・エリア・プロット用のマスク・データ・リスト

必須
mask_color tuple

マスクの前景色

(255, 0, 255)
det_label str

検出ラベルテキスト

None
track_label str

トラッキング・ラベルのテキスト

None
ソースコード ultralytics/utils/plotting.py
def seg_bbox(self, mask, mask_color=(255, 0, 255), det_label=None, track_label=None):
    """
    Function for drawing segmented object in bounding box shape.

    Args:
        mask (list): masks data list for instance segmentation area plotting
        mask_color (tuple): mask foreground color
        det_label (str): Detection label text
        track_label (str): Tracking label text
    """

    cv2.polylines(self.im, [np.int32([mask])], isClosed=True, color=mask_color, thickness=2)

    label = f"Track ID: {track_label}" if track_label else det_label
    text_size, _ = cv2.getTextSize(label, 0, 0.7, 1)

    cv2.rectangle(
        self.im,
        (int(mask[0][0]) - text_size[0] // 2 - 10, int(mask[0][1]) - text_size[1] - 10),
        (int(mask[0][0]) + text_size[0] // 2 + 5, int(mask[0][1] + 5)),
        mask_color,
        -1,
    )

    cv2.putText(
        self.im, label, (int(mask[0][0]) - text_size[0] // 2, int(mask[0][1]) - 5), 0, 0.7, (255, 255, 255), 2
    )

show(title=None)

注釈付き画像を表示する。

ソースコード ultralytics/utils/plotting.py
def show(self, title=None):
    """Show the annotated image."""
    Image.fromarray(np.asarray(self.im)[..., ::-1]).show(title)

text(xy, text, txt_color=(255, 255, 255), anchor='top', box_style=False)

PIL または cv2 を使って画像にテキストを追加します。

ソースコード ultralytics/utils/plotting.py
def text(self, xy, text, txt_color=(255, 255, 255), anchor="top", box_style=False):
    """Adds text to an image using PIL or cv2."""
    if anchor == "bottom":  # start y from font bottom
        w, h = self.font.getsize(text)  # text width, height
        xy[1] += 1 - h
    if self.pil:
        if box_style:
            w, h = self.font.getsize(text)
            self.draw.rectangle((xy[0], xy[1], xy[0] + w + 1, xy[1] + h + 1), fill=txt_color)
            # Using `txt_color` for background and draw fg with white color
            txt_color = (255, 255, 255)
        if "\n" in text:
            lines = text.split("\n")
            _, h = self.font.getsize(text)
            for line in lines:
                self.draw.text(xy, line, fill=txt_color, font=self.font)
                xy[1] += h
        else:
            self.draw.text(xy, text, fill=txt_color, font=self.font)
    else:
        if box_style:
            w, h = cv2.getTextSize(text, 0, fontScale=self.sf, thickness=self.tf)[0]  # text width, height
            h += 3  # add pixels to pad text
            outside = xy[1] >= h  # label fits outside box
            p2 = xy[0] + w, xy[1] - h if outside else xy[1] + h
            cv2.rectangle(self.im, xy, p2, txt_color, -1, cv2.LINE_AA)  # filled
            # Using `txt_color` for background and draw fg with white color
            txt_color = (255, 255, 255)
        cv2.putText(self.im, text, xy, 0, self.sf, txt_color, thickness=self.tf, lineType=cv2.LINE_AA)

text_label(box, label='', color=(128, 128, 128), txt_color=(255, 255, 255), margin=5)

Draws a label with a background rectangle centered within a given bounding box.

パラメーター

名称 タイプ 説明 デフォルト
box tuple

The bounding box coordinates (x1, y1, x2, y2).

必須
label str

The text label to be displayed.

''
color tuple

The background color of the rectangle (R, G, B).

(128, 128, 128)
txt_color tuple

The color of the text (R, G, B).

(255, 255, 255)
margin int

The margin between the text and the rectangle border.

5
ソースコード ultralytics/utils/plotting.py
def text_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), margin=5):
    """
    Draws a label with a background rectangle centered within a given bounding box.

    Args:
        box (tuple): The bounding box coordinates (x1, y1, x2, y2).
        label (str): The text label to be displayed.
        color (tuple, optional): The background color of the rectangle (R, G, B).
        txt_color (tuple, optional): The color of the text (R, G, B).
        margin (int, optional): The margin between the text and the rectangle border.
    """

    # Calculate the center of the bounding box
    x_center, y_center = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
    # Get the size of the text
    text_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, self.sf - 0.1, self.tf)[0]
    # Calculate the top-left corner of the text (to center it)
    text_x = x_center - text_size[0] // 2
    text_y = y_center + text_size[1] // 2
    # Calculate the coordinates of the background rectangle
    rect_x1 = text_x - margin
    rect_y1 = text_y - text_size[1] - margin
    rect_x2 = text_x + text_size[0] + margin
    rect_y2 = text_y + margin
    # Draw the background rectangle
    cv2.rectangle(self.im, (rect_x1, rect_y1), (rect_x2, rect_y2), color, -1)
    # Draw the text on top of the rectangle
    cv2.putText(
        self.im,
        label,
        (text_x, text_y),
        cv2.FONT_HERSHEY_SIMPLEX,
        self.sf - 0.1,
        self.get_txt_color(color, txt_color),
        self.tf,
        lineType=cv2.LINE_AA,
    )

visioneye(box, center_point, color=(235, 219, 11), pin_color=(255, 0, 255))

ピンポイントでの視線マッピングとプロット機能。

パラメーター

名称 タイプ 説明 デフォルト
box list

バウンディングボックス座標

必須
center_point tuple

視野の中心点

必須
color tuple

オブジェクトの重心と線の色の値

(235, 219, 11)
pin_color tuple

ビジョンアイポイントの色値

(255, 0, 255)
ソースコード ultralytics/utils/plotting.py
def visioneye(self, box, center_point, color=(235, 219, 11), pin_color=(255, 0, 255)):
    """
    Function for pinpoint human-vision eye mapping and plotting.

    Args:
        box (list): Bounding box coordinates
        center_point (tuple): center point for vision eye view
        color (tuple): object centroid and line color value
        pin_color (tuple): visioneye point color value
    """

    center_bbox = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
    cv2.circle(self.im, center_point, self.tf * 2, pin_color, -1)
    cv2.circle(self.im, center_bbox, self.tf * 2, color, -1)
    cv2.line(self.im, center_point, center_bbox, color, self.tf)



ultralytics.utils.plotting.plot_labels(boxes, cls, names=(), save_dir=Path(''), on_plot=None)

クラスヒストグラムや箱ひげ統計を含むトレーニングラベルをプロットします。

ソースコード ultralytics/utils/plotting.py
@TryExcept()  # known issue https://github.com/ultralytics/yolov5/issues/5395
@plt_settings()
def plot_labels(boxes, cls, names=(), save_dir=Path(""), on_plot=None):
    """Plot training labels including class histograms and box statistics."""
    import pandas  # scope for faster 'import ultralytics'
    import seaborn  # scope for faster 'import ultralytics'

    # Filter matplotlib>=3.7.2 warning and Seaborn use_inf and is_categorical FutureWarnings
    warnings.filterwarnings("ignore", category=UserWarning, message="The figure layout has changed to tight")
    warnings.filterwarnings("ignore", category=FutureWarning)

    # Plot dataset labels
    LOGGER.info(f"Plotting labels to {save_dir / 'labels.jpg'}... ")
    nc = int(cls.max() + 1)  # number of classes
    boxes = boxes[:1000000]  # limit to 1M boxes
    x = pandas.DataFrame(boxes, columns=["x", "y", "width", "height"])

    # Seaborn correlogram
    seaborn.pairplot(x, corner=True, diag_kind="auto", kind="hist", diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9))
    plt.savefig(save_dir / "labels_correlogram.jpg", dpi=200)
    plt.close()

    # Matplotlib labels
    ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel()
    y = ax[0].hist(cls, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8)
    for i in range(nc):
        y[2].patches[i].set_color([x / 255 for x in colors(i)])
    ax[0].set_ylabel("instances")
    if 0 < len(names) < 30:
        ax[0].set_xticks(range(len(names)))
        ax[0].set_xticklabels(list(names.values()), rotation=90, fontsize=10)
    else:
        ax[0].set_xlabel("classes")
    seaborn.histplot(x, x="x", y="y", ax=ax[2], bins=50, pmax=0.9)
    seaborn.histplot(x, x="width", y="height", ax=ax[3], bins=50, pmax=0.9)

    # Rectangles
    boxes[:, 0:2] = 0.5  # center
    boxes = ops.xywh2xyxy(boxes) * 1000
    img = Image.fromarray(np.ones((1000, 1000, 3), dtype=np.uint8) * 255)
    for cls, box in zip(cls[:500], boxes[:500]):
        ImageDraw.Draw(img).rectangle(box, width=1, outline=colors(cls))  # plot
    ax[1].imshow(img)
    ax[1].axis("off")

    for a in [0, 1, 2, 3]:
        for s in ["top", "right", "left", "bottom"]:
            ax[a].spines[s].set_visible(False)

    fname = save_dir / "labels.jpg"
    plt.savefig(fname, dpi=200)
    plt.close()
    if on_plot:
        on_plot(fname)



ultralytics.utils.plotting.save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False, BGR=False, save=True)

画像の切り抜きを {file} と し て、 切り抜きサ イ ズを複数 {gain} と {pad} ピ ク セルで保存。トリミングを保存または返します。

この関数は、バウンディングボックスと画像を受け取り、バウンディングボックスに従って画像の一部を切り抜いて保存する。 を保存します。オプションで,切り抜き部分を四角にすることもできます。 の調整が可能です。

パラメーター

名称 タイプ 説明 デフォルト
xyxy Tensor or list

xyxy 形式のバウンディングボックスを表すtensor またはリスト。

必須
im ndarray

入力画像。

必須
file Path

切り取った画像を保存するパス。デフォルトは 'im.jpg' です。

Path('im.jpg')
gain float

バウンディングボックスのサイズを大きくするための乗法係数。デフォルトは1.02。

1.02
pad int

バウンディングボックスの幅と高さに加えるピクセル数。デフォルトは10。

10
square bool

True にする と 、 外接枠は正方形に変形 さ れます。デフォルトは False。

False
BGR bool

Trueの場合、画像はBGRフォーマットで保存され、そうでない場合はRGBで保存されます。デフォルトはFalse。

False
save bool

Trueの場合、切り取られた画像はディスクに保存されます。デフォルトはTrue。

True

リターンズ

タイプ 説明
ndarray

トリミングされた画像。

例
from ultralytics.utils.plotting import save_one_box

xyxy = [50, 50, 150, 150]
im = cv2.imread('image.jpg')
cropped_im = save_one_box(xyxy, im, file='cropped.jpg', square=True)
ソースコード ultralytics/utils/plotting.py
def save_one_box(xyxy, im, file=Path("im.jpg"), gain=1.02, pad=10, square=False, BGR=False, save=True):
    """
    Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop.

    This function takes a bounding box and an image, and then saves a cropped portion of the image according
    to the bounding box. Optionally, the crop can be squared, and the function allows for gain and padding
    adjustments to the bounding box.

    Args:
        xyxy (torch.Tensor or list): A tensor or list representing the bounding box in xyxy format.
        im (numpy.ndarray): The input image.
        file (Path, optional): The path where the cropped image will be saved. Defaults to 'im.jpg'.
        gain (float, optional): A multiplicative factor to increase the size of the bounding box. Defaults to 1.02.
        pad (int, optional): The number of pixels to add to the width and height of the bounding box. Defaults to 10.
        square (bool, optional): If True, the bounding box will be transformed into a square. Defaults to False.
        BGR (bool, optional): If True, the image will be saved in BGR format, otherwise in RGB. Defaults to False.
        save (bool, optional): If True, the cropped image will be saved to disk. Defaults to True.

    Returns:
        (numpy.ndarray): The cropped image.

    Example:
        ```python
        from ultralytics.utils.plotting import save_one_box

        xyxy = [50, 50, 150, 150]
        im = cv2.imread('image.jpg')
        cropped_im = save_one_box(xyxy, im, file='cropped.jpg', square=True)
        ```
    """

    if not isinstance(xyxy, torch.Tensor):  # may be list
        xyxy = torch.stack(xyxy)
    b = ops.xyxy2xywh(xyxy.view(-1, 4))  # boxes
    if square:
        b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1)  # attempt rectangle to square
    b[:, 2:] = b[:, 2:] * gain + pad  # box wh * gain + pad
    xyxy = ops.xywh2xyxy(b).long()
    xyxy = ops.clip_boxes(xyxy, im.shape)
    crop = im[int(xyxy[0, 1]) : int(xyxy[0, 3]), int(xyxy[0, 0]) : int(xyxy[0, 2]), :: (1 if BGR else -1)]
    if save:
        file.parent.mkdir(parents=True, exist_ok=True)  # make directory
        f = str(increment_path(file).with_suffix(".jpg"))
        # cv2.imwrite(f, crop)  # save BGR, https://github.com/ultralytics/yolov5/issues/7007 chroma subsampling issue
        Image.fromarray(crop[..., ::-1]).save(f, quality=95, subsampling=0)  # save RGB
    return crop



ultralytics.utils.plotting.plot_images(images, batch_idx, cls, bboxes=np.zeros(0, dtype=np.float32), confs=None, masks=np.zeros(0, dtype=np.uint8), kpts=np.zeros((0, 51), dtype=np.float32), paths=None, fname='images.jpg', names=None, on_plot=None, max_subplots=16, save=True, conf_thres=0.25)

ラベル付きの画像グリッドをプロットする。

ソースコード ultralytics/utils/plotting.py
@threaded
def plot_images(
    images,
    batch_idx,
    cls,
    bboxes=np.zeros(0, dtype=np.float32),
    confs=None,
    masks=np.zeros(0, dtype=np.uint8),
    kpts=np.zeros((0, 51), dtype=np.float32),
    paths=None,
    fname="images.jpg",
    names=None,
    on_plot=None,
    max_subplots=16,
    save=True,
    conf_thres=0.25,
):
    """Plot image grid with labels."""
    if isinstance(images, torch.Tensor):
        images = images.cpu().float().numpy()
    if isinstance(cls, torch.Tensor):
        cls = cls.cpu().numpy()
    if isinstance(bboxes, torch.Tensor):
        bboxes = bboxes.cpu().numpy()
    if isinstance(masks, torch.Tensor):
        masks = masks.cpu().numpy().astype(int)
    if isinstance(kpts, torch.Tensor):
        kpts = kpts.cpu().numpy()
    if isinstance(batch_idx, torch.Tensor):
        batch_idx = batch_idx.cpu().numpy()

    max_size = 1920  # max image size
    bs, _, h, w = images.shape  # batch size, _, height, width
    bs = min(bs, max_subplots)  # limit plot images
    ns = np.ceil(bs**0.5)  # number of subplots (square)
    if np.max(images[0]) <= 1:
        images *= 255  # de-normalise (optional)

    # Build Image
    mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8)  # init
    for i in range(bs):
        x, y = int(w * (i // ns)), int(h * (i % ns))  # block origin
        mosaic[y : y + h, x : x + w, :] = images[i].transpose(1, 2, 0)

    # Resize (optional)
    scale = max_size / ns / max(h, w)
    if scale < 1:
        h = math.ceil(scale * h)
        w = math.ceil(scale * w)
        mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h)))

    # Annotate
    fs = int((h + w) * ns * 0.01)  # font size
    annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True, example=names)
    for i in range(bs):
        x, y = int(w * (i // ns)), int(h * (i % ns))  # block origin
        annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2)  # borders
        if paths:
            annotator.text((x + 5, y + 5), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220))  # filenames
        if len(cls) > 0:
            idx = batch_idx == i
            classes = cls[idx].astype("int")
            labels = confs is None

            if len(bboxes):
                boxes = bboxes[idx]
                conf = confs[idx] if confs is not None else None  # check for confidence presence (label vs pred)
                if len(boxes):
                    if boxes[:, :4].max() <= 1.1:  # if normalized with tolerance 0.1
                        boxes[..., [0, 2]] *= w  # scale to pixels
                        boxes[..., [1, 3]] *= h
                    elif scale < 1:  # absolute coords need scale if image scales
                        boxes[..., :4] *= scale
                boxes[..., 0] += x
                boxes[..., 1] += y
                is_obb = boxes.shape[-1] == 5  # xywhr
                boxes = ops.xywhr2xyxyxyxy(boxes) if is_obb else ops.xywh2xyxy(boxes)
                for j, box in enumerate(boxes.astype(np.int64).tolist()):
                    c = classes[j]
                    color = colors(c)
                    c = names.get(c, c) if names else c
                    if labels or conf[j] > conf_thres:
                        label = f"{c}" if labels else f"{c} {conf[j]:.1f}"
                        annotator.box_label(box, label, color=color, rotated=is_obb)

            elif len(classes):
                for c in classes:
                    color = colors(c)
                    c = names.get(c, c) if names else c
                    annotator.text((x, y), f"{c}", txt_color=color, box_style=True)

            # Plot keypoints
            if len(kpts):
                kpts_ = kpts[idx].copy()
                if len(kpts_):
                    if kpts_[..., 0].max() <= 1.01 or kpts_[..., 1].max() <= 1.01:  # if normalized with tolerance .01
                        kpts_[..., 0] *= w  # scale to pixels
                        kpts_[..., 1] *= h
                    elif scale < 1:  # absolute coords need scale if image scales
                        kpts_ *= scale
                kpts_[..., 0] += x
                kpts_[..., 1] += y
                for j in range(len(kpts_)):
                    if labels or conf[j] > conf_thres:
                        annotator.kpts(kpts_[j], conf_thres=conf_thres)

            # Plot masks
            if len(masks):
                if idx.shape[0] == masks.shape[0]:  # overlap_masks=False
                    image_masks = masks[idx]
                else:  # overlap_masks=True
                    image_masks = masks[[i]]  # (1, 640, 640)
                    nl = idx.sum()
                    index = np.arange(nl).reshape((nl, 1, 1)) + 1
                    image_masks = np.repeat(image_masks, nl, axis=0)
                    image_masks = np.where(image_masks == index, 1.0, 0.0)

                im = np.asarray(annotator.im).copy()
                for j in range(len(image_masks)):
                    if labels or conf[j] > conf_thres:
                        color = colors(classes[j])
                        mh, mw = image_masks[j].shape
                        if mh != h or mw != w:
                            mask = image_masks[j].astype(np.uint8)
                            mask = cv2.resize(mask, (w, h))
                            mask = mask.astype(bool)
                        else:
                            mask = image_masks[j].astype(bool)
                        with contextlib.suppress(Exception):
                            im[y : y + h, x : x + w, :][mask] = (
                                im[y : y + h, x : x + w, :][mask] * 0.4 + np.array(color) * 0.6
                            )
                annotator.fromarray(im)
    if not save:
        return np.asarray(annotator.im)
    annotator.im.save(fname)  # save
    if on_plot:
        on_plot(fname)



ultralytics.utils.plotting.plot_results(file='path/to/results.csv', dir='', segment=False, pose=False, classify=False, on_plot=None)

CSV ファイルからトレーニング結果をプロットします。セグメンテーション、姿勢推定、分類など様々な種類のデータをサポートしています、 をサポートします。プロットはCSVファイルのあるディレクトリにresults.pngとして保存されます。

パラメーター

名称 タイプ 説明 デフォルト
file str

トレーニング結果を含むCSVファイルへのパス。デフォルトは 'path/to/results.csv' です。

'path/to/results.csv'
dir str

file' が指定されていない場合は、CSV ファイルを置くディレクトリ。デフォルトは '' です。

''
segment bool

データがセグメンテーション用であるかどうかを示すフラグ。デフォルトは False。

False
pose bool

データがポーズ推定用かどうかを示すフラグ。デフォルトはFalse。

False
classify bool

データが分類用であるかどうかを示すフラグ。デフォルトはFalse。

False
on_plot callable

プロット後に実行されるコールバック関数。引数としてファイル名を取る。 デフォルトはNone。

None
例
from ultralytics.utils.plotting import plot_results

plot_results('path/to/results.csv', segment=True)
ソースコード ultralytics/utils/plotting.py
@plt_settings()
def plot_results(file="path/to/results.csv", dir="", segment=False, pose=False, classify=False, on_plot=None):
    """
    Plot training results from a results CSV file. The function supports various types of data including segmentation,
    pose estimation, and classification. Plots are saved as 'results.png' in the directory where the CSV is located.

    Args:
        file (str, optional): Path to the CSV file containing the training results. Defaults to 'path/to/results.csv'.
        dir (str, optional): Directory where the CSV file is located if 'file' is not provided. Defaults to ''.
        segment (bool, optional): Flag to indicate if the data is for segmentation. Defaults to False.
        pose (bool, optional): Flag to indicate if the data is for pose estimation. Defaults to False.
        classify (bool, optional): Flag to indicate if the data is for classification. Defaults to False.
        on_plot (callable, optional): Callback function to be executed after plotting. Takes filename as an argument.
            Defaults to None.

    Example:
        ```python
        from ultralytics.utils.plotting import plot_results

        plot_results('path/to/results.csv', segment=True)
        ```
    """
    import pandas as pd  # scope for faster 'import ultralytics'
    from scipy.ndimage import gaussian_filter1d

    save_dir = Path(file).parent if file else Path(dir)
    if classify:
        fig, ax = plt.subplots(2, 2, figsize=(6, 6), tight_layout=True)
        index = [1, 4, 2, 3]
    elif segment:
        fig, ax = plt.subplots(2, 8, figsize=(18, 6), tight_layout=True)
        index = [1, 2, 3, 4, 5, 6, 9, 10, 13, 14, 15, 16, 7, 8, 11, 12]
    elif pose:
        fig, ax = plt.subplots(2, 9, figsize=(21, 6), tight_layout=True)
        index = [1, 2, 3, 4, 5, 6, 7, 10, 11, 14, 15, 16, 17, 18, 8, 9, 12, 13]
    else:
        fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True)
        index = [1, 2, 3, 4, 5, 8, 9, 10, 6, 7]
    ax = ax.ravel()
    files = list(save_dir.glob("results*.csv"))
    assert len(files), f"No results.csv files found in {save_dir.resolve()}, nothing to plot."
    for f in files:
        try:
            data = pd.read_csv(f)
            s = [x.strip() for x in data.columns]
            x = data.values[:, 0]
            for i, j in enumerate(index):
                y = data.values[:, j].astype("float")
                # y[y == 0] = np.nan  # don't show zero values
                ax[i].plot(x, y, marker=".", label=f.stem, linewidth=2, markersize=8)  # actual results
                ax[i].plot(x, gaussian_filter1d(y, sigma=3), ":", label="smooth", linewidth=2)  # smoothing line
                ax[i].set_title(s[j], fontsize=12)
                # if j in {8, 9, 10}:  # share train and val loss y axes
                #     ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
        except Exception as e:
            LOGGER.warning(f"WARNING: Plotting error for {f}: {e}")
    ax[1].legend()
    fname = save_dir / "results.png"
    fig.savefig(fname, dpi=200)
    plt.close()
    if on_plot:
        on_plot(fname)



ultralytics.utils.plotting.plt_color_scatter(v, f, bins=20, cmap='viridis', alpha=0.8, edgecolors='none')

2次元ヒストグラムに基づいて色づけされた散布図をプロットします。

パラメーター

名称 タイプ 説明 デフォルト
v array - like

X軸の値。

必須
f array - like

Y軸の値。

必須
bins int

ヒストグラムのビンの数。デフォルトは20。

20
cmap str

散布図のカラーマップ。デフォルトは 'viridis'.

'viridis'
alpha float

散布図のアルファ値。デフォルトは0.8。

0.8
edgecolors str

散布図のエッジカラー。デフォルトは 'none'.

'none'

例を挙げよう:

>>> v = np.random.rand(100)
>>> f = np.random.rand(100)
>>> plt_color_scatter(v, f)
ソースコード ultralytics/utils/plotting.py
def plt_color_scatter(v, f, bins=20, cmap="viridis", alpha=0.8, edgecolors="none"):
    """
    Plots a scatter plot with points colored based on a 2D histogram.

    Args:
        v (array-like): Values for the x-axis.
        f (array-like): Values for the y-axis.
        bins (int, optional): Number of bins for the histogram. Defaults to 20.
        cmap (str, optional): Colormap for the scatter plot. Defaults to 'viridis'.
        alpha (float, optional): Alpha for the scatter plot. Defaults to 0.8.
        edgecolors (str, optional): Edge colors for the scatter plot. Defaults to 'none'.

    Examples:
        >>> v = np.random.rand(100)
        >>> f = np.random.rand(100)
        >>> plt_color_scatter(v, f)
    """

    # Calculate 2D histogram and corresponding colors
    hist, xedges, yedges = np.histogram2d(v, f, bins=bins)
    colors = [
        hist[
            min(np.digitize(v[i], xedges, right=True) - 1, hist.shape[0] - 1),
            min(np.digitize(f[i], yedges, right=True) - 1, hist.shape[1] - 1),
        ]
        for i in range(len(v))
    ]

    # Scatter plot
    plt.scatter(v, f, c=colors, cmap=cmap, alpha=alpha, edgecolors=edgecolors)



ultralytics.utils.plotting.plot_tune_results(csv_file='tune_results.csv')

tune_results.csv' ファイルに格納された進化結果をプロットする。この関数は、CSVの各キー の散布図を生成する。最もパフォーマンスの良いコンフィギュレーションはプロット上でハイライトされる。

パラメーター

名称 タイプ 説明 デフォルト
csv_file str

チューニング結果を含むCSVファイルへのパス。デフォルトは 'tune_results.csv' です。

'tune_results.csv'

例を挙げよう:

>>> plot_tune_results('path/to/tune_results.csv')
ソースコード ultralytics/utils/plotting.py
def plot_tune_results(csv_file="tune_results.csv"):
    """
    Plot the evolution results stored in an 'tune_results.csv' file. The function generates a scatter plot for each key
    in the CSV, color-coded based on fitness scores. The best-performing configurations are highlighted on the plots.

    Args:
        csv_file (str, optional): Path to the CSV file containing the tuning results. Defaults to 'tune_results.csv'.

    Examples:
        >>> plot_tune_results('path/to/tune_results.csv')
    """

    import pandas as pd  # scope for faster 'import ultralytics'
    from scipy.ndimage import gaussian_filter1d

    # Scatter plots for each hyperparameter
    csv_file = Path(csv_file)
    data = pd.read_csv(csv_file)
    num_metrics_columns = 1
    keys = [x.strip() for x in data.columns][num_metrics_columns:]
    x = data.values
    fitness = x[:, 0]  # fitness
    j = np.argmax(fitness)  # max fitness index
    n = math.ceil(len(keys) ** 0.5)  # columns and rows in plot
    plt.figure(figsize=(10, 10), tight_layout=True)
    for i, k in enumerate(keys):
        v = x[:, i + num_metrics_columns]
        mu = v[j]  # best single result
        plt.subplot(n, n, i + 1)
        plt_color_scatter(v, fitness, cmap="viridis", alpha=0.8, edgecolors="none")
        plt.plot(mu, fitness.max(), "k+", markersize=15)
        plt.title(f"{k} = {mu:.3g}", fontdict={"size": 9})  # limit to 40 characters
        plt.tick_params(axis="both", labelsize=8)  # Set axis label size to 8
        if i % n != 0:
            plt.yticks([])

    file = csv_file.with_name("tune_scatter_plots.png")  # filename
    plt.savefig(file, dpi=200)
    plt.close()
    LOGGER.info(f"Saved {file}")

    # Fitness vs iteration
    x = range(1, len(fitness) + 1)
    plt.figure(figsize=(10, 6), tight_layout=True)
    plt.plot(x, fitness, marker="o", linestyle="none", label="fitness")
    plt.plot(x, gaussian_filter1d(fitness, sigma=3), ":", label="smoothed", linewidth=2)  # smoothing line
    plt.title("Fitness vs Iteration")
    plt.xlabel("Iteration")
    plt.ylabel("Fitness")
    plt.grid(True)
    plt.legend()

    file = csv_file.with_name("tune_fitness.png")  # filename
    plt.savefig(file, dpi=200)
    plt.close()
    LOGGER.info(f"Saved {file}")



ultralytics.utils.plotting.output_to_target(output, max_det=300)

モデル出力をプロット用のターゲットフォーマット[batch_id, class_id, x, y, w, h, conf]に変換する。

ソースコード ultralytics/utils/plotting.py
def output_to_target(output, max_det=300):
    """Convert model output to target format [batch_id, class_id, x, y, w, h, conf] for plotting."""
    targets = []
    for i, o in enumerate(output):
        box, conf, cls = o[:max_det, :6].cpu().split((4, 1, 1), 1)
        j = torch.full((conf.shape[0], 1), i)
        targets.append(torch.cat((j, cls, ops.xyxy2xywh(box), conf), 1))
    targets = torch.cat(targets, 0).numpy()
    return targets[:, 0], targets[:, 1], targets[:, 2:-1], targets[:, -1]



ultralytics.utils.plotting.output_to_rotated_target(output, max_det=300)

モデル出力をプロット用のターゲットフォーマット[batch_id, class_id, x, y, w, h, conf]に変換する。

ソースコード ultralytics/utils/plotting.py
def output_to_rotated_target(output, max_det=300):
    """Convert model output to target format [batch_id, class_id, x, y, w, h, conf] for plotting."""
    targets = []
    for i, o in enumerate(output):
        box, conf, cls, angle = o[:max_det].cpu().split((4, 1, 1, 1), 1)
        j = torch.full((conf.shape[0], 1), i)
        targets.append(torch.cat((j, cls, box, angle, conf), 1))
    targets = torch.cat(targets, 0).numpy()
    return targets[:, 0], targets[:, 1], targets[:, 2:-1], targets[:, -1]



ultralytics.utils.plotting.feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp'))

推論中に与えられたモデルモジュールの特徴マップを可視化する。

パラメーター

名称 タイプ 説明 デフォルト
x Tensor

可視化される機能。

必須
module_type str

モジュールタイプ。

必須
stage int

モデル内のモジュール段階。

必須
n int

プロットするフィーチャーマップの最大数。デフォルトは32。

32
save_dir Path

結果を保存するディレクトリ。デフォルトはPath('runs/detect/exp')です。

Path('runs/detect/exp')
ソースコード ultralytics/utils/plotting.py
def feature_visualization(x, module_type, stage, n=32, save_dir=Path("runs/detect/exp")):
    """
    Visualize feature maps of a given model module during inference.

    Args:
        x (torch.Tensor): Features to be visualized.
        module_type (str): Module type.
        stage (int): Module stage within the model.
        n (int, optional): Maximum number of feature maps to plot. Defaults to 32.
        save_dir (Path, optional): Directory to save results. Defaults to Path('runs/detect/exp').
    """
    for m in {"Detect", "Segment", "Pose", "Classify", "OBB", "RTDETRDecoder"}:  # all model heads
        if m in module_type:
            return
    if isinstance(x, torch.Tensor):
        _, channels, height, width = x.shape  # batch, channels, height, width
        if height > 1 and width > 1:
            f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png"  # filename

            blocks = torch.chunk(x[0].cpu(), channels, dim=0)  # select batch index 0, block by channels
            n = min(n, channels)  # number of plots
            _, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True)  # 8 rows x n/8 cols
            ax = ax.ravel()
            plt.subplots_adjust(wspace=0.05, hspace=0.05)
            for i in range(n):
                ax[i].imshow(blocks[i].squeeze())  # cmap='gray'
                ax[i].axis("off")

            LOGGER.info(f"Saving {f}... ({n}/{channels})")
            plt.savefig(f, dpi=300, bbox_inches="tight")
            plt.close()
            np.save(str(f.with_suffix(".npy")), x[0].cpu().numpy())  # npy save





Created 2023-11-12, Updated 2024-06-02
Authors: glenn-jocher (6), Burhan-Q (1), Laughing-q (1)