跳至内容

参考资料 ultralytics/utils/plotting.py

备注

该文件可在https://github.com/ultralytics/ultralytics/blob/main/ ultralytics/utils/plotting .py 上获取。如果您发现问题,请通过提交 Pull Request🛠️ 帮助修复。谢谢🙏!



ultralytics.utils.plotting.Colors

Ultralytics 默认调色板 https://ultralytics.com/.

该类提供了使用Ultralytics 调色板的方法,包括将十六进制颜色代码转换为 RGB 值。

属性

名称 类型 说明
palette list of tuple

RGB 颜色值列表。

n int

调色板中颜色的数量。

pose_palette ndarray

一个特定的调色板数组,其 dtype 为 np.uint8。

源代码 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 = (
            "FF3838",
            "FF9D97",
            "FF701F",
            "FFB21D",
            "CFD231",
            "48F90A",
            "92CC17",
            "3DDB86",
            "1A9334",
            "00D4BB",
            "2C99A8",
            "00C2FF",
            "344593",
            "6473FF",
            "0018EC",
            "8438FF",
            "520085",
            "CB38FF",
            "FF95C8",
            "FF37C7",
        )
        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)

将十六进制颜色代码转换为 RGB 值。

源代码 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__()

将颜色初始化为十六进制 = matplotlib.colors.TABLEAU_COLORS.values().

源代码 ultralytics/utils/plotting.py
def __init__(self):
    """Initialize colors as hex = matplotlib.colors.TABLEAU_COLORS.values()."""
    hexs = (
        "FF3838",
        "FF9D97",
        "FF701F",
        "FFB21D",
        "CFD231",
        "48F90A",
        "92CC17",
        "3DDB86",
        "1A9334",
        "00D4BB",
        "2C99A8",
        "00C2FF",
        "344593",
        "6473FF",
        "0018EC",
        "8438FF",
        "520085",
        "CB38FF",
        "FF95C8",
        "FF37C7",
    )
    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

将十六进制颜色代码转换为 RGB 值(即默认 PIL 顺序)。

源代码 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 用于训练/评估镶嵌图和 JPG 文件以及预测注释的注释器。

属性

名称 类型 说明
im Image.Image or numpy array

要注释的图像。

pil bool

使用 PIL 还是 cv2 绘制注释。

font truetype or load_default

用于文本注释的字体。

lw float

绘图线宽。

skeleton List[List[int]]

关键点的骨架结构。

limb_color List[int]

四肢的调色板

kpt_color List[int]

关键点的调色板。

源代码 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
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]]

    def box_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), rotated=False):
        """Add one xyxy box to image with label."""
        if isinstance(box, torch.Tensor):
            box = box.tolist()
        if self.pil or not is_ascii(label):
            if rotated:
                p1 = box[0]
                # NOTE: PIL-version polygon needs tuple type.
                self.draw.polygon([tuple(b) for b in box], width=self.lw, outline=color)
            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 >= 0  # label fits outside box
                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]]
                # NOTE: cv2-version polylines needs np.asarray type.
                cv2.polylines(self.im, [np.asarray(box, dtype=int)], True, color, self.lw)
            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
                outside = p1[1] - h >= 3
                p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
                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 + 2),
                    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):
        """
        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 < 0.5:
                        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 < 0.5 or conf2 < 0.5:
                        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
                outside = xy[1] - h >= 3
                p2 = xy[0] + w, xy[1] - h - 3 if outside else xy[1] + h + 3
                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 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 count_labels(self, counts=0, count_txt_size=2, color=(255, 255, 255), txt_color=(0, 0, 0)):
        """
        Plot counts for object counter.

        Args:
            counts (int): objects counts value
            count_txt_size (int): text size for counts display
            color (tuple): background color of counts display
            txt_color (tuple): text color of counts display
        """
        self.tf = count_txt_size
        tl = self.tf or round(0.002 * (self.im.shape[0] + self.im.shape[1]) / 2) + 1
        tf = max(tl - 1, 1)

        # Get text size for in_count and out_count
        t_size_in = cv2.getTextSize(str(counts), 0, fontScale=tl / 2, thickness=tf)[0]

        # Calculate positions for counts label
        text_width = t_size_in[0]
        text_x = (self.im.shape[1] - text_width) // 2  # Center x-coordinate
        text_y = t_size_in[1]

        # Create a rounded rectangle for in_count
        cv2.rectangle(
            self.im, (text_x - 5, text_y - 5), (text_x + text_width + 7, text_y + t_size_in[1] + 7), color, -1
        )
        cv2.putText(
            self.im, str(counts), (text_x, text_y + t_size_in[1]), 0, tl / 2, txt_color, self.tf, lineType=cv2.LINE_AA
        )

    @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=[2, 5, 7], shape=(640, 640), radius=2):
        """
        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
        """
        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 < 0.5:
                            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, line_thickness=2):
        """
        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
            line_thickness (int): thickness for text display
        """
        angle_text, count_text, stage_text = (f" {angle_text:.2f}", f"Steps : {count_text}", f" {stage_text}")
        font_scale = 0.6 + (line_thickness / 10.0)

        # Draw angle
        (angle_text_width, angle_text_height), _ = cv2.getTextSize(angle_text, 0, font_scale, line_thickness)
        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 + (line_thickness * 2))
        cv2.rectangle(
            self.im,
            angle_background_position,
            (
                angle_background_position[0] + angle_background_size[0],
                angle_background_position[1] + angle_background_size[1],
            ),
            (255, 255, 255),
            -1,
        )
        cv2.putText(self.im, angle_text, angle_text_position, 0, font_scale, (0, 0, 0), line_thickness)

        # Draw Counts
        (count_text_width, count_text_height), _ = cv2.getTextSize(count_text, 0, font_scale, line_thickness)
        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 + (line_thickness * 2))

        cv2.rectangle(
            self.im,
            count_background_position,
            (
                count_background_position[0] + count_background_size[0],
                count_background_position[1] + count_background_size[1],
            ),
            (255, 255, 255),
            -1,
        )
        cv2.putText(self.im, count_text, count_text_position, 0, font_scale, (0, 0, 0), line_thickness)

        # Draw Stage
        (stage_text_width, stage_text_height), _ = cv2.getTextSize(stage_text, 0, font_scale, line_thickness)
        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],
            ),
            (255, 255, 255),
            -1,
        )
        cv2.putText(self.im, stage_text, stage_text_position, 0, font_scale, (0, 0, 0), line_thickness)

    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", cv2.FONT_HERSHEY_SIMPLEX, 0.8, 2
        )
        cv2.rectangle(self.im, (15, 25), (15 + text_width_m + 10, 25 + text_height_m + 20), (255, 255, 255), -1)
        cv2.putText(
            self.im,
            f"Distance M: {distance_m:.2f}m",
            (20, 50),
            cv2.FONT_HERSHEY_SIMPLEX,
            0.8,
            (0, 0, 0),
            2,
            cv2.LINE_AA,
        )

        (text_width_mm, text_height_mm), _ = cv2.getTextSize(
            f"Distance MM: {distance_mm:.2f}mm", cv2.FONT_HERSHEY_SIMPLEX, 0.8, 2
        )
        cv2.rectangle(self.im, (15, 75), (15 + text_width_mm + 10, 75 + text_height_mm + 20), (255, 255, 255), -1)
        cv2.putText(
            self.im,
            f"Distance MM: {distance_mm:.2f}mm",
            (20, 100),
            cv2.FONT_HERSHEY_SIMPLEX,
            0.8,
            (0, 0, 0),
            2,
            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), thickness=2, pins_radius=10):
        """
        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
            thickness (int): int value for line thickness
            pins_radius (int): visioneye point radius value
        """
        center_bbox = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
        cv2.circle(self.im, center_point, pins_radius, pin_color, -1)
        cv2.circle(self.im, center_bbox, pins_radius, color, -1)
        cv2.line(self.im, center_point, center_bbox, color, thickness)

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

用图像和线宽以及关键点和肢体的调色板初始化注释器类。

源代码 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]]

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

在图片上添加一个 xyxy 框,并加上标签。

源代码 ultralytics/utils/plotting.py
def box_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), rotated=False):
    """Add one xyxy box to image with label."""
    if isinstance(box, torch.Tensor):
        box = box.tolist()
    if self.pil or not is_ascii(label):
        if rotated:
            p1 = box[0]
            # NOTE: PIL-version polygon needs tuple type.
            self.draw.polygon([tuple(b) for b in box], width=self.lw, outline=color)
        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 >= 0  # label fits outside box
            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]]
            # NOTE: cv2-version polylines needs np.asarray type.
            cv2.polylines(self.im, [np.asarray(box, dtype=int)], True, color, self.lw)
        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
            outside = p1[1] - h >= 3
            p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
            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 + 2),
                0,
                self.sf,
                txt_color,
                thickness=self.tf,
                lineType=cv2.LINE_AA,
            )

count_labels(counts=0, count_txt_size=2, color=(255, 255, 255), txt_color=(0, 0, 0))

绘制对象计数器的计数图。

参数

名称 类型 说明 默认值
counts int

对象计数值

0
count_txt_size int

计数显示文字大小

2
color tuple

计数显示屏的背景色

(255, 255, 255)
txt_color tuple

计数显示的文本颜色

(0, 0, 0)
源代码 ultralytics/utils/plotting.py
def count_labels(self, counts=0, count_txt_size=2, color=(255, 255, 255), txt_color=(0, 0, 0)):
    """
    Plot counts for object counter.

    Args:
        counts (int): objects counts value
        count_txt_size (int): text size for counts display
        color (tuple): background color of counts display
        txt_color (tuple): text color of counts display
    """
    self.tf = count_txt_size
    tl = self.tf or round(0.002 * (self.im.shape[0] + self.im.shape[1]) / 2) + 1
    tf = max(tl - 1, 1)

    # Get text size for in_count and out_count
    t_size_in = cv2.getTextSize(str(counts), 0, fontScale=tl / 2, thickness=tf)[0]

    # Calculate positions for counts label
    text_width = t_size_in[0]
    text_x = (self.im.shape[1] - text_width) // 2  # Center x-coordinate
    text_y = t_size_in[1]

    # Create a rounded rectangle for in_count
    cv2.rectangle(
        self.im, (text_x - 5, text_y - 5), (text_x + text_width + 7, text_y + t_size_in[1] + 7), color, -1
    )
    cv2.putText(
        self.im, str(counts), (text_x, text_y + t_size_in[1]), 0, tl / 2, txt_color, self.tf, lineType=cv2.LINE_AA
    )

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

绘制中心点和轨迹。

参数

名称 类型 说明 默认值
track list

用于轨迹显示的物体跟踪点

所需
color tuple

轨道线颜色

(255, 0, 255)
track_thickness int

轨迹线粗细值

2
源代码 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)

绘制区域线。

参数

名称 类型 说明 默认值
reg_pts list

区域点数(2 号线点数,4 号区域点数)

None
color tuple

区域颜色值

(0, 255, 0)
thickness int

区域面积厚度值

5
源代码 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=[2, 5, 7], shape=(640, 640), radius=2)

绘制体育馆步数计数的具体关键点。

参数

名称 类型 说明 默认值
keypoints list

要绘制的关键点数据列表

所需
indices list

要绘制的关键点 id 列表

[2, 5, 7]
shape tuple

用于模型推理的 imgsz

(640, 640)
radius int

关键点半径值

2
源代码 ultralytics/utils/plotting.py
def draw_specific_points(self, keypoints, indices=[2, 5, 7], shape=(640, 640), radius=2):
    """
    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
    """
    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 < 0.5:
                        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

计算物体的姿态角

参数

名称 类型 说明 默认值
a float)

姿势点 a 的值

所需
b float

姿态点 b 的值

所需
c float

c 点的位置值

所需

返回:

名称 类型 说明
angle degree

三点间角度的度数

源代码 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)

从一个 numpy 数组更新 self.im。

源代码 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)

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

在图像上绘制关键点

参数

名称 类型 说明 默认值
kpts tensor

预测关键点的形状 [17, 3]。每个关键点都有(x、y、置信度)。

所需
shape tuple

图像形状的元组(h, w),其中 h 是高度,w 是宽度。

(640, 640)
radius int

绘制关键点的半径。默认值为 5。

5
kpt_line bool

如果为 True,函数将为人体姿势绘制连接关键点的线条。 连接线。默认为 True。

True
备注

kpt_line=True 目前仅支持人体姿态绘图。

源代码 ultralytics/utils/plotting.py
def kpts(self, kpts, shape=(640, 640), radius=5, kpt_line=True):
    """
    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 < 0.5:
                    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 < 0.5 or conf2 < 0.5:
                    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)

在图像上绘制遮罩。

参数

名称 类型 说明 默认值
masks tensor

cuda 上的预测掩码,形状:[n, h, w]

所需
colors List[List[Int]]

预测掩码的颜色,[[r, g, b] * n]

所需
im_gpu tensor

图像为 cuda 格式,形状为[3, h, w], range:[0, 1]

所需
alpha float

遮罩透明度:0.0 完全透明,1.0 不透明

0.5
retina_masks bool

是否使用高分辨率掩码。默认为 "假"。

False
源代码 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, line_thickness=2)

绘制姿势角度、计数值和步进阶段图。

参数

名称 类型 说明 默认值
angle_text str

监测锻炼的角度值

所需
count_text str

用于监测锻炼的计数值

所需
stage_text str

锻炼监测的阶段性决定

所需
center_kpt int

用于运动监测的中心点姿势指数

所需
line_thickness int

文字显示厚度

2
源代码 ultralytics/utils/plotting.py
def plot_angle_and_count_and_stage(self, angle_text, count_text, stage_text, center_kpt, line_thickness=2):
    """
    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
        line_thickness (int): thickness for text display
    """
    angle_text, count_text, stage_text = (f" {angle_text:.2f}", f"Steps : {count_text}", f" {stage_text}")
    font_scale = 0.6 + (line_thickness / 10.0)

    # Draw angle
    (angle_text_width, angle_text_height), _ = cv2.getTextSize(angle_text, 0, font_scale, line_thickness)
    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 + (line_thickness * 2))
    cv2.rectangle(
        self.im,
        angle_background_position,
        (
            angle_background_position[0] + angle_background_size[0],
            angle_background_position[1] + angle_background_size[1],
        ),
        (255, 255, 255),
        -1,
    )
    cv2.putText(self.im, angle_text, angle_text_position, 0, font_scale, (0, 0, 0), line_thickness)

    # Draw Counts
    (count_text_width, count_text_height), _ = cv2.getTextSize(count_text, 0, font_scale, line_thickness)
    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 + (line_thickness * 2))

    cv2.rectangle(
        self.im,
        count_background_position,
        (
            count_background_position[0] + count_background_size[0],
            count_background_position[1] + count_background_size[1],
        ),
        (255, 255, 255),
        -1,
    )
    cv2.putText(self.im, count_text, count_text_position, 0, font_scale, (0, 0, 0), line_thickness)

    # Draw Stage
    (stage_text_width, stage_text_height), _ = cv2.getTextSize(stage_text, 0, font_scale, line_thickness)
    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],
        ),
        (255, 255, 255),
        -1,
    )
    cv2.putText(self.im, stage_text, stage_text_position, 0, font_scale, (0, 0, 0), line_thickness)

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

在框架上绘制距离和直线。

参数

名称 类型 说明 默认值
distance_m float

两个 bbox 中心点之间的距离(米)。

所需
distance_mm float

两个 bbox 中心点之间的距离(毫米)。

所需
centroids list

边框中心点数据

所需
line_color RGB

距离线颜色

所需
centroid_color RGB

边界框中心点颜色。

所需
源代码 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", cv2.FONT_HERSHEY_SIMPLEX, 0.8, 2
    )
    cv2.rectangle(self.im, (15, 25), (15 + text_width_m + 10, 25 + text_height_m + 20), (255, 255, 255), -1)
    cv2.putText(
        self.im,
        f"Distance M: {distance_m:.2f}m",
        (20, 50),
        cv2.FONT_HERSHEY_SIMPLEX,
        0.8,
        (0, 0, 0),
        2,
        cv2.LINE_AA,
    )

    (text_width_mm, text_height_mm), _ = cv2.getTextSize(
        f"Distance MM: {distance_mm:.2f}mm", cv2.FONT_HERSHEY_SIMPLEX, 0.8, 2
    )
    cv2.rectangle(self.im, (15, 75), (15 + text_width_mm + 10, 75 + text_height_mm + 20), (255, 255, 255), -1)
    cv2.putText(
        self.im,
        f"Distance MM: {distance_mm:.2f}mm",
        (20, 100),
        cv2.FONT_HERSHEY_SIMPLEX,
        0.8,
        (0, 0, 0),
        2,
        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)

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

为图像添加矩形(仅限 PIL)。

源代码 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()

以数组形式返回注释图像。

源代码 ultralytics/utils/plotting.py
def result(self):
    """Return annotated image as array."""
    return np.asarray(self.im)

save(filename='image.jpg')

将注释图像保存到 "文件名 "中。

源代码 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)

用于以边界框形状绘制分割对象的函数。

参数

名称 类型 说明 默认值
mask list

用于实例分割区域绘图的掩码数据列表

所需
mask_color tuple

蒙版前景色

(255, 0, 255)
det_label str

检测标签文本

None
track_label str

跟踪标签文本

None
源代码 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)

显示带注释的图像。

源代码 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)

使用 PIL 或 cv2 为图像添加文字。

源代码 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
            outside = xy[1] - h >= 3
            p2 = xy[0] + w, xy[1] - h - 3 if outside else xy[1] + h + 3
            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)

visioneye(box, center_point, color=(235, 219, 11), pin_color=(255, 0, 255), thickness=2, pins_radius=10)

具有精确的人眼视力测绘和绘图功能。

参数

名称 类型 说明 默认值
box list

边界框坐标

所需
center_point tuple

视觉中心点

所需
color tuple

对象中心点和线条颜色值

(235, 219, 11)
pin_color tuple

视觉点颜色值

(255, 0, 255)
thickness int

线条粗细的 int 值

2
pins_radius int

视觉点半径值

10
源代码 ultralytics/utils/plotting.py
def visioneye(self, box, center_point, color=(235, 219, 11), pin_color=(255, 0, 255), thickness=2, pins_radius=10):
    """
    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
        thickness (int): int value for line thickness
        pins_radius (int): visioneye point radius value
    """
    center_bbox = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
    cv2.circle(self.im, center_point, pins_radius, pin_color, -1)
    cv2.circle(self.im, center_bbox, pins_radius, color, -1)
    cv2.line(self.im, center_point, center_bbox, color, thickness)



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

绘制训练标签,包括类直方图和方框统计图。

源代码 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 as pd
    import seaborn as sn

    # 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 = pd.DataFrame(boxes, columns=["x", "y", "width", "height"])

    # Seaborn correlogram
    sn.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")
    sn.histplot(x, x="x", y="y", ax=ax[2], bins=50, pmax=0.9)
    sn.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)

将图像裁剪保存为{文件},裁剪尺寸为多个{gain}和{pad}像素。保存和/或返回裁剪。

该函数获取一个边界框和一幅图像,然后根据边界框保存图像的裁剪部分。 保存图像的裁剪部分。可选择裁剪成正方形,该函数还允许对边界框进行增益和填充调整。 调整边界框。

参数

名称 类型 说明 默认值
xyxy Tensor or list

tensor 或列表,以 xyxy 格式表示边界框。

所需
im ndarray

输入图像。

所需
file Path

保存裁剪图像的路径。默认为 "im.jpg"。

Path('im.jpg')
gain float

用于增大边界框大小的乘法因子。默认为 1.02。

1.02
pad int

边框宽度和高度的像素数。默认为 10。

10
square bool

如果为 True,边框将转换为正方形。默认为 "假"。

False
BGR bool

如果为 True,图像将以 BGR 格式保存,否则将以 RGB 格式保存。默认为 "假"。

False
save bool

如果为 True,裁剪后的图像将保存到磁盘。默认为 True。

True

返回:

类型 说明
ndarray

裁剪后的图片。

示例
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)
源代码 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)

绘制带标签的图像网格

源代码 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)
                is_obb = boxes.shape[-1] == 5  # xywhr
                boxes = ops.xywhr2xyxyxyxy(boxes) if is_obb else ops.xywh2xyxy(boxes)
                if len(boxes):
                    if boxes[:, :4].max() <= 1.1:  # if normalized with tolerance 0.1
                        boxes[..., 0::2] *= w  # scale to pixels
                        boxes[..., 1::2] *= h
                    elif scale < 1:  # absolute coords need scale if image scales
                        boxes[..., :4] *= scale
                boxes[..., 0::2] += x
                boxes[..., 1::2] += y
                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])

            # 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)

绘制 CSV 结果文件中的训练结果。该功能支持各种类型的数据,包括分割、姿态估计和分类、 姿势估计和分类。绘图以 "results.png "的形式保存在 CSV 所在的目录中。

参数

名称 类型 说明 默认值
file str

包含训练结果的 CSV 文件的路径。默认为 "path/to/results.csv"。

'path/to/results.csv'
dir str

如果未提供 "file",则 CSV 文件所在的目录。默认为""。

''
segment bool

指示数据是否用于分割的标志。默认为 "假"。

False
pose bool

指示数据是否用于姿态估计的标志。默认为 "假"。

False
classify bool

指示数据是否用于分类的标志。默认为 "假"。

False
on_plot callable

绘图后执行的回调函数。以文件名为参数。 默认为 "无"。

None
示例
from ultralytics.utils.plotting import plot_results

plot_results('path/to/results.csv', segment=True)
源代码 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
    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')

根据二维直方图绘制点着色的散点图。

参数

名称 类型 说明 默认值
v array - like

X 轴的数值。

所需
f array - like

y 轴的数值。

所需
bins int

直方图的箱数。默认为 20。

20
cmap str

散点图的颜色图。默认为 "viridis"。

'viridis'
alpha float

散点图的 Alpha 值。默认值为 0.8。

0.8
edgecolors str

散点图的边缘颜色。默认为 "无"。

'none'

例如

>>> v = np.random.rand(100)
>>> f = np.random.rand(100)
>>> plt_color_scatter(v, f)
源代码 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')

绘制存储在 "tune_results.csv "文件中的演化结果。该函数会为 CSV 文件中的每个键 中的每个关键字生成散点图,并根据适合度得分进行颜色编码。表现最好的配置会在图中突出显示。

参数

名称 类型 说明 默认值
csv_file str

包含调整结果的 CSV 文件的路径。默认为 "tune_results.csv"。

'tune_results.csv'

例如

>>> plot_tune_results('path/to/tune_results.csv')
源代码 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
    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)

将模型输出转换为目标格式 [batch_id、class_id、x、y、w、h、conf],以便绘图。

源代码 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)

将模型输出转换为目标格式 [batch_id、class_id、x、y、w、h、conf],以便绘图。

源代码 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'))

在推理过程中可视化给定模型模块的特征图。

参数

名称 类型 说明 默认值
x Tensor

可视化特征。

所需
module_type str

模块类型。

所需
stage int

模型中的模块阶段。

所需
n int

绘制的最大特征图数量。默认为 32。

32
save_dir Path

保存结果的目录。默认为 Path('runs/detect/exp')。

Path('runs/detect/exp')
源代码 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", "Pose", "Segment"]:
        if m in module_type:
            return
    _, 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





创建于 2023-11-12,更新于 2024-01-05
作者:glenn-jocher(4),Laughing-q(1)