Skip to content

Image Utils

crop_image

supervision.utils.image.crop_image(image: ImageType, xyxy: npt.NDArray[int] | list[int] | tuple[int, int, int, int]) -> ImageType

Crop image based on bounding box coordinates.

Parameters:

Name Type Description Default

image

ImageType

The image to crop.

 required

xyxy

NDArray[int] | list[int] | tuple[int, int, int, int]

Bounding box coordinates in (x_min, y_min, x_max, y_max) format.

 required

Returns:

Type Description
ImageType

Cropped image matching input type.

Examples:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
>>> image.shape
(1080, 1920, 3)
>>> xyxy = (400, 400, 800, 800)
>>> cropped_image = sv.crop_image(image=image, xyxy=xyxy)
>>> cropped_image.shape
(400, 400, 3)

>>> image = np.zeros((1920, 1080), dtype=np.uint8)
>>> image.shape
(1920, 1080)
>>> xyxy = (400, 400, 800, 800)
>>> cropped_image = sv.crop_image(image=image, xyxy=xyxy)
>>> cropped_image.shape
(400, 400)

crop-image

Source code in src/supervision/utils/image.py 
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
@ensure_cv2_image_for_standalone_function
def crop_image(
    image: ImageType,
    xyxy: npt.NDArray[int] | list[int] | tuple[int, int, int, int],
) -> ImageType:
    """
    Crop image based on bounding box coordinates.

    Args:
        image: The image to crop.
        xyxy:
            Bounding box coordinates in `(x_min, y_min, x_max, y_max)` format.

    Returns:
        Cropped image matching input
            type.

    Examples:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
        >>> image.shape
        (1080, 1920, 3)
        >>> xyxy = (400, 400, 800, 800)
        >>> cropped_image = sv.crop_image(image=image, xyxy=xyxy)
        >>> cropped_image.shape
        (400, 400, 3)

        ```

        ```pycon
        >>> image = np.zeros((1920, 1080), dtype=np.uint8)
        >>> image.shape
        (1920, 1080)
        >>> xyxy = (400, 400, 800, 800)
        >>> cropped_image = sv.crop_image(image=image, xyxy=xyxy)
        >>> cropped_image.shape
        (400, 400)

        ```

    ![crop-image](https://media.roboflow.com/supervision-docs/supervision-docs-crop-image-2.png){ align=center width="1000" }
    """  # noqa E501 // docs
    if isinstance(xyxy, (list, tuple)):
        xyxy = np.array(xyxy)

    xyxy = np.round(xyxy).astype(int)
    x_min, y_min, x_max, y_max = xyxy.flatten()

    if isinstance(image, np.ndarray):
        return image[y_min:y_max, x_min:x_max]

    if isinstance(image, Image.Image):
        return image.crop((x_min, y_min, x_max, y_max))

    raise TypeError(
        f"`image` must be a numpy.ndarray or PIL.Image.Image. Received {type(image)}"
    )

scale_image

supervision.utils.image.scale_image(image: ImageType, scale_factor: float) -> ImageType

Scale image by given factor. Scale factor > 1.0 zooms in, < 1.0 zooms out.

Parameters:

Name Type Description Default

image

ImageType

The image to scale.

 required

scale_factor

float

Factor by which to scale the image.

 required

Returns:

Type Description
ImageType

Scaled image matching input type.

Raises:

Type Description
ValueError

If scale factor is non-positive.

Examples:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
>>> image.shape
(1080, 1920, 3)
>>> scaled_image = sv.scale_image(image=image, scale_factor=0.5)
>>> scaled_image.shape
(540, 960, 3)

>>> image = np.zeros((1920, 1080), dtype=np.uint8)
>>> image.shape
(1920, 1080)
>>> scaled_image = sv.scale_image(image=image, scale_factor=0.5)
>>> scaled_image.shape
(960, 540)

scale-image

Source code in src/supervision/utils/image.py 
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
@ensure_cv2_image_for_standalone_function
def scale_image(image: ImageType, scale_factor: float) -> ImageType:
    """
    Scale image by given factor. Scale factor > 1.0 zooms in, < 1.0 zooms out.

    Args:
        image: The image to scale.
        scale_factor: Factor by which to scale the image.

    Returns:
        Scaled image matching input
            type.

    Raises:
        ValueError: If scale factor is non-positive.

    Examples:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
        >>> image.shape
        (1080, 1920, 3)
        >>> scaled_image = sv.scale_image(image=image, scale_factor=0.5)
        >>> scaled_image.shape
        (540, 960, 3)

        ```

        ```pycon
        >>> image = np.zeros((1920, 1080), dtype=np.uint8)
        >>> image.shape
        (1920, 1080)
        >>> scaled_image = sv.scale_image(image=image, scale_factor=0.5)
        >>> scaled_image.shape
        (960, 540)

        ```

    ![scale-image](https://media.roboflow.com/supervision-docs/supervision-docs-scale-image-2.png){ align=center width="1000" }
    """  # noqa E501 // docs
    assert isinstance(image, np.ndarray)
    if scale_factor <= 0:
        raise ValueError("Scale factor must be positive.")

    width_old, height_old = image.shape[1], image.shape[0]
    width_new = int(width_old * scale_factor)
    height_new = int(height_old * scale_factor)
    return cv2.resize(image, (width_new, height_new), interpolation=cv2.INTER_LINEAR)

resize_image

supervision.utils.image.resize_image(image: ImageType, resolution_wh: tuple[int, int], keep_aspect_ratio: bool = False) -> ImageType

Resize image to specified resolution. Can optionally maintain aspect ratio.

Parameters:

Name Type Description Default

image

ImageType

The image to resize.

 required

resolution_wh

tuple[int, int]

Target resolution as (width, height).

 required

keep_aspect_ratio

bool

Flag to maintain original aspect ratio. Defaults to False.

 False

Returns:

Type Description
ImageType

Resized image matching input type.

Examples:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
>>> image.shape
(1080, 1920, 3)
>>> resized_image = sv.resize_image(
...     image=image, resolution_wh=(1000, 1000), keep_aspect_ratio=True
... )
>>> resized_image.shape
(562, 1000, 3)

>>> image = np.zeros((1920, 1080), dtype=np.uint8)
>>> image.shape
(1920, 1080)
>>> resized_image = sv.resize_image(
...     image=image, resolution_wh=(1000, 1000), keep_aspect_ratio=True
... )
>>> resized_image.shape
(1000, 562)

resize-image

Source code in src/supervision/utils/image.py 
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
@ensure_cv2_image_for_standalone_function
def resize_image(
    image: ImageType,
    resolution_wh: tuple[int, int],
    keep_aspect_ratio: bool = False,
) -> ImageType:
    """
    Resize image to specified resolution. Can optionally maintain aspect ratio.

    Args:
        image: The image to resize.
        resolution_wh: Target resolution as `(width, height)`.
        keep_aspect_ratio: Flag to maintain original aspect ratio.
            Defaults to `False`.

    Returns:
        Resized image matching input
            type.

    Examples:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
        >>> image.shape
        (1080, 1920, 3)
        >>> resized_image = sv.resize_image(
        ...     image=image, resolution_wh=(1000, 1000), keep_aspect_ratio=True
        ... )
        >>> resized_image.shape
        (562, 1000, 3)

        ```

        ```pycon
        >>> image = np.zeros((1920, 1080), dtype=np.uint8)
        >>> image.shape
        (1920, 1080)
        >>> resized_image = sv.resize_image(
        ...     image=image, resolution_wh=(1000, 1000), keep_aspect_ratio=True
        ... )
        >>> resized_image.shape
        (1000, 562)

        ```

    ![resize-image](https://media.roboflow.com/supervision-docs/supervision-docs-resize-image-2.png){ align=center width="1000" }
    """  # noqa E501 // docs
    assert isinstance(image, np.ndarray)
    if keep_aspect_ratio:
        image_ratio = image.shape[1] / image.shape[0]
        target_ratio = resolution_wh[0] / resolution_wh[1]
        if image_ratio >= target_ratio:
            width_new = resolution_wh[0]
            height_new = int(resolution_wh[0] / image_ratio)
        else:
            height_new = resolution_wh[1]
            width_new = int(resolution_wh[1] * image_ratio)
    else:
        width_new, height_new = resolution_wh

    return cv2.resize(image, (width_new, height_new), interpolation=cv2.INTER_LINEAR)

letterbox_image

supervision.utils.image.letterbox_image(image: ImageType, resolution_wh: tuple[int, int], color: tuple[int, int, int] | Color = Color.BLACK) -> ImageType

Resize image and pad with color to achieve desired resolution while maintaining aspect ratio.

Parameters:

Name Type Description Default

image

ImageType

The image to resize and pad. Accepts BGR arrays of shape (H, W, 3), BGRA arrays of shape (H, W, 4), grayscale arrays of shape (H, W), or a PIL Image.

 required

resolution_wh

tuple[int, int]

Target resolution as (width, height).

 required

color

tuple[int, int, int] | Color

Padding color. If tuple, should be in BGR format. Defaults to Color.BLACK.

 BLACK

Returns:

Type Description
ImageType

Letterboxed image matching input type.
Note

For BGRA inputs, the alpha channel in the padding region is set to 0 (fully transparent). Grayscale inputs receive scalar padding from color[0].

Examples:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
>>> image.shape
(1080, 1920, 3)
>>> letterboxed_image = sv.letterbox_image(
...     image=image, resolution_wh=(1000, 1000)
... )
>>> letterboxed_image.shape
(1000, 1000, 3)
>>> gray = np.zeros((4, 6), dtype=np.uint8)
>>> sv.letterbox_image(image=gray, resolution_wh=(10, 10)).shape
(10, 10)

letterbox-image

Source code in src/supervision/utils/image.py 
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
@ensure_cv2_image_for_standalone_function
def letterbox_image(
    image: ImageType,
    resolution_wh: tuple[int, int],
    color: tuple[int, int, int] | Color = Color.BLACK,
) -> ImageType:
    """
    Resize image and pad with color to achieve desired resolution while
    maintaining aspect ratio.

    Args:
        image: The image to resize and pad. Accepts BGR arrays of shape
            ``(H, W, 3)``, BGRA arrays of shape ``(H, W, 4)``, grayscale
            arrays of shape ``(H, W)``, or a PIL ``Image``.
        resolution_wh: Target resolution as `(width, height)`.
        color: Padding color. If tuple, should be in BGR format.
            Defaults to `Color.BLACK`.

    Returns:
        Letterboxed image matching input type.

    Note:
        For BGRA inputs, the alpha channel in the padding region is set to
        0 (fully transparent). Grayscale inputs receive scalar padding
        from ``color[0]``.

    Examples:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
        >>> image.shape
        (1080, 1920, 3)
        >>> letterboxed_image = sv.letterbox_image(
        ...     image=image, resolution_wh=(1000, 1000)
        ... )
        >>> letterboxed_image.shape
        (1000, 1000, 3)
        >>> gray = np.zeros((4, 6), dtype=np.uint8)
        >>> sv.letterbox_image(image=gray, resolution_wh=(10, 10)).shape
        (10, 10)

        ```

    ![letterbox-image](https://media.roboflow.com/supervision-docs/supervision-docs-letterbox-image-2.png){ align=center width="1000" }
    """  # noqa E501 // docs
    assert isinstance(image, np.ndarray)
    color = unify_to_bgr(color=color)
    resized_image = resize_image(
        image=image, resolution_wh=resolution_wh, keep_aspect_ratio=True
    )
    height_new, width_new = resized_image.shape[:2]
    padding_top = (resolution_wh[1] - height_new) // 2
    padding_bottom = resolution_wh[1] - height_new - padding_top
    padding_left = (resolution_wh[0] - width_new) // 2
    padding_right = resolution_wh[0] - width_new - padding_left
    image_with_borders = cv2.copyMakeBorder(
        resized_image,
        padding_top,
        padding_bottom,
        padding_left,
        padding_right,
        cv2.BORDER_CONSTANT,
        value=color,
    )

    return image_with_borders

tint_image

supervision.utils.image.tint_image(image: ImageType, color: Color = Color.BLACK, opacity: float = 0.5) -> ImageType

Tint image with solid color overlay at specified opacity.

Parameters:

Name Type Description Default

image

ImageType

The image to tint.

 required

color

Color

Overlay tint color. Defaults to Color.BLACK.

 BLACK

opacity

float

Blend ratio between overlay and image (0.0-1.0). Defaults to 0.5.

 0.5

Returns:

Type Description
ImageType

Tinted image matching input type.

Raises:

Type Description
ValueError

If opacity is outside range [0.0, 1.0].

Examples:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((100, 100, 3), dtype=np.uint8)
>>> tinted_image = sv.tint_image(
...     image=image, color=sv.Color.ROBOFLOW, opacity=0.5
... )
>>> tinted_image.shape
(100, 100, 3)

tint-image

Source code in src/supervision/utils/image.py 
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
@ensure_cv2_image_for_standalone_function
def tint_image(
    image: ImageType,
    color: Color = Color.BLACK,
    opacity: float = 0.5,
) -> ImageType:
    """
    Tint image with solid color overlay at specified opacity.

    Args:
        image: The image to tint.
        color: Overlay tint color. Defaults to `Color.BLACK`.
        opacity: Blend ratio between overlay and image (0.0-1.0).
            Defaults to `0.5`.

    Returns:
        Tinted image matching input
            type.

    Raises:
        ValueError: If opacity is outside range [0.0, 1.0].

    Examples:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((100, 100, 3), dtype=np.uint8)
        >>> tinted_image = sv.tint_image(
        ...     image=image, color=sv.Color.ROBOFLOW, opacity=0.5
        ... )
        >>> tinted_image.shape
        (100, 100, 3)

        ```

    ![tint-image](https://media.roboflow.com/supervision-docs/supervision-docs-tint-image-2.png){ align=center width="1000" }
    """  # noqa E501 // docs
    assert isinstance(image, np.ndarray)
    if not 0.0 <= opacity <= 1.0:
        raise ValueError("opacity must be between 0.0 and 1.0")

    overlay = np.full_like(image, fill_value=color.as_bgr(), dtype=image.dtype)
    cv2.addWeighted(
        src1=overlay, alpha=opacity, src2=image, beta=1 - opacity, gamma=0, dst=image
    )
    return image

grayscale_image

supervision.utils.image.grayscale_image(image: ImageType) -> ImageType

Convert image to 3-channel grayscale. Luminance channel is broadcast to all three channels for compatibility with color-based drawing helpers.

Parameters:

Name Type Description Default

image

ImageType

The image to convert to grayscale.

 required

Returns:

Type Description
ImageType

3-channel grayscale image matching input type.

Examples:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.ones((100, 100, 3), dtype=np.uint8) * 128
>>> grayscale_image = sv.grayscale_image(image=image)
>>> grayscale_image.shape
(100, 100, 3)

grayscale-image

Source code in src/supervision/utils/image.py 
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
@ensure_cv2_image_for_standalone_function
def grayscale_image(image: ImageType) -> ImageType:
    """
    Convert image to 3-channel grayscale. Luminance channel is broadcast to
    all three channels for compatibility with color-based drawing helpers.

    Args:
        image: The image to convert to
            grayscale.

    Returns:
        3-channel grayscale image
            matching input type.

    Examples:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.ones((100, 100, 3), dtype=np.uint8) * 128
        >>> grayscale_image = sv.grayscale_image(image=image)
        >>> grayscale_image.shape
        (100, 100, 3)

        ```

    ![grayscale-image](https://media.roboflow.com/supervision-docs/supervision-docs-grayscale-image-2.png){ align=center width="1000" }
    """  # noqa E501 // docs
    grayscaled = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    return cv2.cvtColor(grayscaled, cv2.COLOR_GRAY2BGR)

get_image_resolution_wh

supervision.utils.image.get_image_resolution_wh(image: ImageType) -> tuple[int, int]

Get image width and height as a tuple (width, height) for various image formats.

Supports both numpy.ndarray images (with shape (H, W, ...)) and PIL.Image.Image inputs.

Parameters:

Name Type Description Default

image

ImageType

Input image.

 required

Returns:

Type Description
tuple[int, int]

Image resolution as (width, height).

Raises:

Type Description
ValueError

If a numpy.ndarray image has fewer than 2 dimensions.
TypeError

If image is not a supported type (numpy.ndarray or PIL.Image.Image).

Examples:

>>> import numpy as np
>>> import supervision as sv
>>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
>>> sv.get_image_resolution_wh(image)
(1920, 1080)
Source code in src/supervision/utils/image.py 
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
def get_image_resolution_wh(image: ImageType) -> tuple[int, int]:
    """
    Get image width and height as a tuple `(width, height)` for various image formats.

    Supports both `numpy.ndarray` images (with shape `(H, W, ...)`) and
    `PIL.Image.Image` inputs.

    Args:
        image: Input image.

    Returns:
        Image resolution as `(width, height)`.

    Raises:
        ValueError: If a `numpy.ndarray` image has fewer than 2 dimensions.
        TypeError: If `image` is not a supported type (`numpy.ndarray` or
            `PIL.Image.Image`).

    Examples:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> image = np.zeros((1080, 1920, 3), dtype=np.uint8)
        >>> sv.get_image_resolution_wh(image)
        (1920, 1080)

        ```
    """
    if isinstance(image, np.ndarray):
        if image.ndim < 2:
            raise ValueError(
                "NumPy image must have at least 2 dimensions (H, W, ...). "
                f"Received shape: {image.shape}"
            )
        height, width = image.shape[:2]
        return int(width), int(height)

    if isinstance(image, Image.Image):
        width, height = image.size
        return int(width), int(height)

    raise TypeError(
        "`image` must be a numpy.ndarray or PIL.Image.Image. "
        f"Received type: {type(image)}"
    )

ImageSink

supervision.utils.image.ImageSink

Source code in src/supervision/utils/image.py 
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
class ImageSink:
    def __init__(
        self,
        target_dir_path: str,
        overwrite: bool = False,
        image_name_pattern: str = "image_{:05d}.png",
    ):
        """
        Initialize context manager for saving images to directory.

        Args:
            target_dir_path: Target directory path where images will be
                saved.
            overwrite: Whether to overwrite existing directory.
                Defaults to `False`.
            image_name_pattern: File name pattern for saved images.
                Defaults to `"image_{:05d}.png"`.

        Examples:
            ```pycon
            >>> import numpy as np
            >>> import supervision as sv
            >>> import tempfile
            >>> import os
            >>> with tempfile.TemporaryDirectory() as tmpdir:
            ...     image = np.zeros((100, 100, 3), dtype=np.uint8)
            ...     with sv.ImageSink(target_dir_path=tmpdir, overwrite=True) as sink:
            ...         sink.save_image(image=image)
            ...         sink.save_image(image=image)
            ...     files = sorted(os.listdir(tmpdir))
            ...     len(files)
            2

            ```
        """
        self.target_dir_path = target_dir_path
        self.overwrite = overwrite
        self.image_name_pattern = image_name_pattern
        self.image_count = 0

    def __enter__(self) -> ImageSink:
        if os.path.exists(self.target_dir_path):
            if self.overwrite:
                shutil.rmtree(self.target_dir_path)
                os.makedirs(self.target_dir_path)
        else:
            os.makedirs(self.target_dir_path)

        return self

    def save_image(
        self, image: npt.NDArray[np.uint8], image_name: str | None = None
    ) -> None:
        """
        Save image to target directory with optional custom filename.

        Args:
            image: Image to save with shape `(height, width, 3)`
                in BGR format.
            image_name: Custom filename for saved image. If
                `None`, generates name using `image_name_pattern`. Defaults to
                `None`.
        """
        if image_name is None:
            image_name = self.image_name_pattern.format(self.image_count)

        image_path = os.path.join(self.target_dir_path, image_name)
        cv2.imwrite(image_path, image)
        self.image_count += 1

    def __exit__(
        self,
        exc_type: type[BaseException] | None,
        exc_value: BaseException | None,
        exc_traceback: Any,
    ) -> None:
        pass

Functions

__init__(target_dir_path: str, overwrite: bool = False, image_name_pattern: str = 'image_{:05d}.png')

Initialize context manager for saving images to directory.

Parameters:

Name Type Description Default
target_dir_path
str

Target directory path where images will be saved.

 required
overwrite
bool

Whether to overwrite existing directory. Defaults to False.

 False
image_name_pattern
str

File name pattern for saved images. Defaults to "image_{:05d}.png".

 'image_{:05d}.png'

Examples:

>>> import numpy as np
>>> import supervision as sv
>>> import tempfile
>>> import os
>>> with tempfile.TemporaryDirectory() as tmpdir:
...     image = np.zeros((100, 100, 3), dtype=np.uint8)
...     with sv.ImageSink(target_dir_path=tmpdir, overwrite=True) as sink:
...         sink.save_image(image=image)
...         sink.save_image(image=image)
...     files = sorted(os.listdir(tmpdir))
...     len(files)
2
Source code in src/supervision/utils/image.py 
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
def __init__(
    self,
    target_dir_path: str,
    overwrite: bool = False,
    image_name_pattern: str = "image_{:05d}.png",
):
    """
    Initialize context manager for saving images to directory.

    Args:
        target_dir_path: Target directory path where images will be
            saved.
        overwrite: Whether to overwrite existing directory.
            Defaults to `False`.
        image_name_pattern: File name pattern for saved images.
            Defaults to `"image_{:05d}.png"`.

    Examples:
        ```pycon
        >>> import numpy as np
        >>> import supervision as sv
        >>> import tempfile
        >>> import os
        >>> with tempfile.TemporaryDirectory() as tmpdir:
        ...     image = np.zeros((100, 100, 3), dtype=np.uint8)
        ...     with sv.ImageSink(target_dir_path=tmpdir, overwrite=True) as sink:
        ...         sink.save_image(image=image)
        ...         sink.save_image(image=image)
        ...     files = sorted(os.listdir(tmpdir))
        ...     len(files)
        2

        ```
    """
    self.target_dir_path = target_dir_path
    self.overwrite = overwrite
    self.image_name_pattern = image_name_pattern
    self.image_count = 0

save_image(image: npt.NDArray[np.uint8], image_name: str | None = None) -> None

Save image to target directory with optional custom filename.

Parameters:

Name Type Description Default
image
NDArray[uint8]

Image to save with shape (height, width, 3) in BGR format.

 required
image_name
str | None

Custom filename for saved image. If None, generates name using image_name_pattern. Defaults to None.

 None
Source code in src/supervision/utils/image.py 
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
def save_image(
    self, image: npt.NDArray[np.uint8], image_name: str | None = None
) -> None:
    """
    Save image to target directory with optional custom filename.

    Args:
        image: Image to save with shape `(height, width, 3)`
            in BGR format.
        image_name: Custom filename for saved image. If
            `None`, generates name using `image_name_pattern`. Defaults to
            `None`.
    """
    if image_name is None:
        image_name = self.image_name_pattern.format(self.image_count)

    image_path = os.path.join(self.target_dir_path, image_name)
    cv2.imwrite(image_path, image)
    self.image_count += 1

Comments