test_transforms_v2.py 47.4 KB
Newer Older
1
2
import itertools
import pathlib
3
import pickle
4
5
6
7
8
9
10
11
12
13
import random
import warnings

import numpy as np

import PIL.Image
import pytest
import torch
import torchvision.transforms.v2 as transforms

14
from common_utils import assert_equal, cpu_and_cuda
15
from torch.utils._pytree import tree_flatten, tree_unflatten
16
from torchvision import tv_tensors
17
18
19
from torchvision.ops.boxes import box_iou
from torchvision.transforms.functional import to_pil_image
from torchvision.transforms.v2 import functional as F
Nicolas Hug's avatar
Nicolas Hug committed
20
from torchvision.transforms.v2._utils import check_type, is_pure_tensor, query_chw
21
from transforms_v2_legacy_utils import (
22
23
24
25
    make_bounding_boxes,
    make_detection_mask,
    make_image,
    make_images,
26
    make_multiple_bounding_boxes,
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
    make_segmentation_mask,
    make_video,
    make_videos,
)


def make_vanilla_tensor_images(*args, **kwargs):
    for image in make_images(*args, **kwargs):
        if image.ndim > 3:
            continue
        yield image.data


def make_pil_images(*args, **kwargs):
    for image in make_vanilla_tensor_images(*args, **kwargs):
        yield to_pil_image(image)


def make_vanilla_tensor_bounding_boxes(*args, **kwargs):
46
    for bounding_boxes in make_multiple_bounding_boxes(*args, **kwargs):
47
        yield bounding_boxes.data
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68


def parametrize(transforms_with_inputs):
    return pytest.mark.parametrize(
        ("transform", "input"),
        [
            pytest.param(
                transform,
                input,
                id=f"{type(transform).__name__}-{type(input).__module__}.{type(input).__name__}-{idx}",
            )
            for transform, inputs in transforms_with_inputs
            for idx, input in enumerate(inputs)
        ],
    )


def auto_augment_adapter(transform, input, device):
    adapted_input = {}
    image_or_video_found = False
    for key, value in input.items():
69
        if isinstance(value, (tv_tensors.BoundingBoxes, tv_tensors.Mask)):
70
71
            # AA transforms don't support bounding boxes or masks
            continue
72
        elif check_type(value, (tv_tensors.Image, tv_tensors.Video, is_pure_tensor, PIL.Image.Image)):
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
            if image_or_video_found:
                # AA transforms only support a single image or video
                continue
            image_or_video_found = True
        adapted_input[key] = value
    return adapted_input


def linear_transformation_adapter(transform, input, device):
    flat_inputs = list(input.values())
    c, h, w = query_chw(
        [
            item
            for item, needs_transform in zip(flat_inputs, transforms.Transform()._needs_transform_list(flat_inputs))
            if needs_transform
        ]
    )
    num_elements = c * h * w
    transform.transformation_matrix = torch.randn((num_elements, num_elements), device=device)
    transform.mean_vector = torch.randn((num_elements,), device=device)
    return {key: value for key, value in input.items() if not isinstance(value, PIL.Image.Image)}


def normalize_adapter(transform, input, device):
    adapted_input = {}
    for key, value in input.items():
        if isinstance(value, PIL.Image.Image):
            # normalize doesn't support PIL images
            continue
102
        elif check_type(value, (tv_tensors.Image, tv_tensors.Video, is_pure_tensor)):
103
            # normalize doesn't support integer images
104
            value = F.to_dtype(value, torch.float32, scale=True)
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
        adapted_input[key] = value
    return adapted_input


class TestSmoke:
    @pytest.mark.parametrize(
        ("transform", "adapter"),
        [
            (transforms.RandomErasing(p=1.0), None),
            (transforms.AugMix(), auto_augment_adapter),
            (transforms.AutoAugment(), auto_augment_adapter),
            (transforms.RandAugment(), auto_augment_adapter),
            (transforms.TrivialAugmentWide(), auto_augment_adapter),
            (transforms.ColorJitter(brightness=0.1, contrast=0.2, saturation=0.3, hue=0.15), None),
            (transforms.Grayscale(), None),
            (transforms.RandomAdjustSharpness(sharpness_factor=0.5, p=1.0), None),
            (transforms.RandomAutocontrast(p=1.0), None),
            (transforms.RandomEqualize(p=1.0), None),
            (transforms.RandomGrayscale(p=1.0), None),
            (transforms.RandomInvert(p=1.0), None),
125
            (transforms.RandomChannelPermutation(), None),
126
127
128
129
130
131
132
133
134
135
            (transforms.RandomPhotometricDistort(p=1.0), None),
            (transforms.RandomPosterize(bits=4, p=1.0), None),
            (transforms.RandomSolarize(threshold=0.5, p=1.0), None),
            (transforms.CenterCrop([16, 16]), None),
            (transforms.ElasticTransform(sigma=1.0), None),
            (transforms.Pad(4), None),
            (transforms.RandomAffine(degrees=30.0), None),
            (transforms.RandomCrop([16, 16], pad_if_needed=True), None),
            (transforms.RandomHorizontalFlip(p=1.0), None),
            (transforms.RandomPerspective(p=1.0), None),
136
137
            (transforms.RandomResize(min_size=10, max_size=20, antialias=True), None),
            (transforms.RandomResizedCrop([16, 16], antialias=True), None),
138
            (transforms.RandomRotation(degrees=30), None),
139
            (transforms.RandomShortestSize(min_size=10, antialias=True), None),
140
141
142
            (transforms.RandomVerticalFlip(p=1.0), None),
            (transforms.RandomZoomOut(p=1.0), None),
            (transforms.Resize([16, 16], antialias=True), None),
143
            (transforms.ScaleJitter((16, 16), scale_range=(0.8, 1.2), antialias=True), None),
144
            (transforms.ClampBoundingBoxes(), None),
145
            (transforms.ConvertBoundingBoxFormat(tv_tensors.BoundingBoxFormat.CXCYWH), None),
146
            (transforms.ConvertImageDtype(), None),
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
            (transforms.GaussianBlur(kernel_size=3), None),
            (
                transforms.LinearTransformation(
                    # These are just dummy values that will be filled by the adapter. We can't define them upfront,
                    # because for we neither know the spatial size nor the device at this point
                    transformation_matrix=torch.empty((1, 1)),
                    mean_vector=torch.empty((1,)),
                ),
                linear_transformation_adapter,
            ),
            (transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), normalize_adapter),
            (transforms.ToDtype(torch.float64), None),
            (transforms.UniformTemporalSubsample(num_samples=2), None),
        ],
        ids=lambda transform: type(transform).__name__,
    )
    @pytest.mark.parametrize("container_type", [dict, list, tuple])
    @pytest.mark.parametrize(
        "image_or_video",
        [
            make_image(),
            make_video(),
            next(make_pil_images(color_spaces=["RGB"])),
            next(make_vanilla_tensor_images()),
        ],
    )
173
    @pytest.mark.parametrize("de_serialize", [lambda t: t, lambda t: pickle.loads(pickle.dumps(t))])
174
    @pytest.mark.parametrize("device", cpu_and_cuda())
175
176
177
    def test_common(self, transform, adapter, container_type, image_or_video, de_serialize, device):
        transform = de_serialize(transform)

Philip Meier's avatar
Philip Meier committed
178
        canvas_size = F.get_size(image_or_video)
179
180
        input = dict(
            image_or_video=image_or_video,
181
182
            image_tv_tensor=make_image(size=canvas_size),
            video_tv_tensor=make_video(size=canvas_size),
Philip Meier's avatar
Philip Meier committed
183
            image_pil=next(make_pil_images(sizes=[canvas_size], color_spaces=["RGB"])),
184
            bounding_boxes_xyxy=make_bounding_boxes(
185
                format=tv_tensors.BoundingBoxFormat.XYXY, canvas_size=canvas_size, batch_dims=(3,)
186
            ),
187
            bounding_boxes_xywh=make_bounding_boxes(
188
                format=tv_tensors.BoundingBoxFormat.XYWH, canvas_size=canvas_size, batch_dims=(4,)
189
            ),
190
            bounding_boxes_cxcywh=make_bounding_boxes(
191
                format=tv_tensors.BoundingBoxFormat.CXCYWH, canvas_size=canvas_size, batch_dims=(5,)
192
            ),
193
            bounding_boxes_degenerate_xyxy=tv_tensors.BoundingBoxes(
194
195
196
197
198
199
200
201
                [
                    [0, 0, 0, 0],  # no height or width
                    [0, 0, 0, 1],  # no height
                    [0, 0, 1, 0],  # no width
                    [2, 0, 1, 1],  # x1 > x2, y1 < y2
                    [0, 2, 1, 1],  # x1 < x2, y1 > y2
                    [2, 2, 1, 1],  # x1 > x2, y1 > y2
                ],
202
                format=tv_tensors.BoundingBoxFormat.XYXY,
Philip Meier's avatar
Philip Meier committed
203
                canvas_size=canvas_size,
204
            ),
205
            bounding_boxes_degenerate_xywh=tv_tensors.BoundingBoxes(
206
207
208
209
210
211
212
213
                [
                    [0, 0, 0, 0],  # no height or width
                    [0, 0, 0, 1],  # no height
                    [0, 0, 1, 0],  # no width
                    [0, 0, 1, -1],  # negative height
                    [0, 0, -1, 1],  # negative width
                    [0, 0, -1, -1],  # negative height and width
                ],
214
                format=tv_tensors.BoundingBoxFormat.XYWH,
Philip Meier's avatar
Philip Meier committed
215
                canvas_size=canvas_size,
216
            ),
217
            bounding_boxes_degenerate_cxcywh=tv_tensors.BoundingBoxes(
218
219
220
221
222
223
224
225
                [
                    [0, 0, 0, 0],  # no height or width
                    [0, 0, 0, 1],  # no height
                    [0, 0, 1, 0],  # no width
                    [0, 0, 1, -1],  # negative height
                    [0, 0, -1, 1],  # negative width
                    [0, 0, -1, -1],  # negative height and width
                ],
226
                format=tv_tensors.BoundingBoxFormat.CXCYWH,
Philip Meier's avatar
Philip Meier committed
227
                canvas_size=canvas_size,
228
            ),
Philip Meier's avatar
Philip Meier committed
229
230
            detection_mask=make_detection_mask(size=canvas_size),
            segmentation_mask=make_segmentation_mask(size=canvas_size),
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
            int=0,
            float=0.0,
            bool=True,
            none=None,
            str="str",
            path=pathlib.Path.cwd(),
            object=object(),
            tensor=torch.empty(5),
            array=np.empty(5),
        )
        if adapter is not None:
            input = adapter(transform, input, device)

        if container_type in {tuple, list}:
            input = container_type(input.values())

        input_flat, input_spec = tree_flatten(input)
        input_flat = [item.to(device) if isinstance(item, torch.Tensor) else item for item in input_flat]
        input = tree_unflatten(input_flat, input_spec)

        torch.manual_seed(0)
        output = transform(input)
        output_flat, output_spec = tree_flatten(output)

        assert output_spec == input_spec

        for output_item, input_item, should_be_transformed in zip(
            output_flat, input_flat, transforms.Transform()._needs_transform_list(input_flat)
        ):
            if should_be_transformed:
                assert type(output_item) is type(input_item)
            else:
                assert output_item is input_item

265
            if isinstance(input_item, tv_tensors.BoundingBoxes) and not isinstance(
266
267
268
269
270
271
272
                transform, transforms.ConvertBoundingBoxFormat
            ):
                assert output_item.format == input_item.format

        # Enforce that the transform does not turn a degenerate box marked by RandomIoUCrop (or any other future
        # transform that does this), back into a valid one.
        # TODO: we should test that against all degenerate boxes above
273
        for format in list(tv_tensors.BoundingBoxFormat):
274
            sample = dict(
275
                boxes=tv_tensors.BoundingBoxes([[0, 0, 0, 0]], format=format, canvas_size=(224, 244)),
276
277
                labels=torch.tensor([3]),
            )
278
            assert transforms.SanitizeBoundingBoxes()(sample)["boxes"].shape == (0, 4)
279
280
281
282
283
284
285
286
287
288
289
290
291

    @parametrize(
        [
            (
                transform,
                itertools.chain.from_iterable(
                    fn(
                        color_spaces=[
                            "GRAY",
                            "RGB",
                        ],
                        dtypes=[torch.uint8],
                        extra_dims=[(), (4,)],
292
                        **(dict(num_frames=[3]) if fn is make_videos else dict()),
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
                    )
                    for fn in [
                        make_images,
                        make_vanilla_tensor_images,
                        make_pil_images,
                        make_videos,
                    ]
                ),
            )
            for transform in (
                transforms.RandAugment(),
                transforms.TrivialAugmentWide(),
                transforms.AutoAugment(),
                transforms.AugMix(),
            )
        ]
    )
    def test_auto_augment(self, transform, input):
        transform(input)

    @parametrize(
        [
            (
                transforms.Normalize(mean=[0.0, 0.0, 0.0], std=[1.0, 1.0, 1.0]),
                itertools.chain.from_iterable(
                    fn(color_spaces=["RGB"], dtypes=[torch.float32])
                    for fn in [
                        make_images,
                        make_vanilla_tensor_images,
                        make_videos,
                    ]
                ),
            ),
        ]
    )
    def test_normalize(self, transform, input):
        transform(input)

    @parametrize(
        [
            (
                transforms.RandomResizedCrop([16, 16], antialias=True),
                itertools.chain(
                    make_images(extra_dims=[(4,)]),
                    make_vanilla_tensor_images(),
                    make_pil_images(),
                    make_videos(extra_dims=[()]),
                ),
            )
        ]
    )
    def test_random_resized_crop(self, transform, input):
        transform(input)


@pytest.mark.parametrize(
    "flat_inputs",
    itertools.permutations(
        [
            next(make_vanilla_tensor_images()),
            next(make_vanilla_tensor_images()),
            next(make_pil_images()),
            make_image(),
            next(make_videos()),
        ],
        3,
    ),
)
361
362
def test_pure_tensor_heuristic(flat_inputs):
    def split_on_pure_tensor(to_split):
363
        # This takes a sequence that is structurally aligned with `flat_inputs` and splits its items into three parts:
364
365
        # 1. The first pure tensor. If none is present, this will be `None`
        # 2. A list of the remaining pure tensors
366
        # 3. A list of all other items
367
        pure_tensors = []
368
369
370
371
        others = []
        # Splitting always happens on the original `flat_inputs` to avoid any erroneous type changes by the transform to
        # affect the splitting.
        for item, inpt in zip(to_split, flat_inputs):
372
373
            (pure_tensors if is_pure_tensor(inpt) else others).append(item)
        return pure_tensors[0] if pure_tensors else None, pure_tensors[1:], others
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388

    class CopyCloneTransform(transforms.Transform):
        def _transform(self, inpt, params):
            return inpt.clone() if isinstance(inpt, torch.Tensor) else inpt.copy()

        @staticmethod
        def was_applied(output, inpt):
            identity = output is inpt
            if identity:
                return False

            # Make sure nothing fishy is going on
            assert_equal(output, inpt)
            return True

389
    first_pure_tensor_input, other_pure_tensor_inputs, other_inputs = split_on_pure_tensor(flat_inputs)
390
391
392
393

    transform = CopyCloneTransform()
    transformed_sample = transform(flat_inputs)

394
    first_pure_tensor_output, other_pure_tensor_outputs, other_outputs = split_on_pure_tensor(transformed_sample)
395

396
    if first_pure_tensor_input is not None:
397
        if other_inputs:
398
            assert not transform.was_applied(first_pure_tensor_output, first_pure_tensor_input)
399
        else:
400
            assert transform.was_applied(first_pure_tensor_output, first_pure_tensor_input)
401

402
    for output, inpt in zip(other_pure_tensor_outputs, other_pure_tensor_inputs):
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
        assert not transform.was_applied(output, inpt)

    for input, output in zip(other_inputs, other_outputs):
        assert transform.was_applied(output, input)


class TestPad:
    def test_assertions(self):
        with pytest.raises(TypeError, match="Got inappropriate padding arg"):
            transforms.Pad("abc")

        with pytest.raises(ValueError, match="Padding must be an int or a 1, 2, or 4"):
            transforms.Pad([-0.7, 0, 0.7])

        with pytest.raises(TypeError, match="Got inappropriate fill arg"):
            transforms.Pad(12, fill="abc")

        with pytest.raises(ValueError, match="Padding mode should be either"):
            transforms.Pad(12, padding_mode="abc")


class TestRandomZoomOut:
    def test_assertions(self):
        with pytest.raises(TypeError, match="Got inappropriate fill arg"):
            transforms.RandomZoomOut(fill="abc")

        with pytest.raises(TypeError, match="should be a sequence of length"):
            transforms.RandomZoomOut(0, side_range=0)

        with pytest.raises(ValueError, match="Invalid canvas side range"):
            transforms.RandomZoomOut(0, side_range=[4.0, 1.0])

    @pytest.mark.parametrize("fill", [0, [1, 2, 3], (2, 3, 4)])
    @pytest.mark.parametrize("side_range", [(1.0, 4.0), [2.0, 5.0]])
Philip Meier's avatar
Philip Meier committed
437
    def test__get_params(self, fill, side_range):
438
439
        transform = transforms.RandomZoomOut(fill=fill, side_range=side_range)

Philip Meier's avatar
Philip Meier committed
440
441
        h, w = size = (24, 32)
        image = make_image(size)
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

        params = transform._get_params([image])

        assert len(params["padding"]) == 4
        assert 0 <= params["padding"][0] <= (side_range[1] - 1) * w
        assert 0 <= params["padding"][1] <= (side_range[1] - 1) * h
        assert 0 <= params["padding"][2] <= (side_range[1] - 1) * w
        assert 0 <= params["padding"][3] <= (side_range[1] - 1) * h


class TestGaussianBlur:
    def test_assertions(self):
        with pytest.raises(ValueError, match="Kernel size should be a tuple/list of two integers"):
            transforms.GaussianBlur([10, 12, 14])

        with pytest.raises(ValueError, match="Kernel size value should be an odd and positive number"):
            transforms.GaussianBlur(4)

        with pytest.raises(
            TypeError, match="sigma should be a single int or float or a list/tuple with length 2 floats."
        ):
            transforms.GaussianBlur(3, sigma=[1, 2, 3])

        with pytest.raises(ValueError, match="If sigma is a single number, it must be positive"):
            transforms.GaussianBlur(3, sigma=-1.0)

        with pytest.raises(ValueError, match="sigma values should be positive and of the form"):
            transforms.GaussianBlur(3, sigma=[2.0, 1.0])

    @pytest.mark.parametrize("sigma", [10.0, [10.0, 12.0]])
    def test__get_params(self, sigma):
        transform = transforms.GaussianBlur(3, sigma=sigma)
        params = transform._get_params([])

        if isinstance(sigma, float):
            assert params["sigma"][0] == params["sigma"][1] == 10
        else:
            assert sigma[0] <= params["sigma"][0] <= sigma[1]
            assert sigma[0] <= params["sigma"][1] <= sigma[1]


class TestRandomPerspective:
    def test_assertions(self):
        with pytest.raises(ValueError, match="Argument distortion_scale value should be between 0 and 1"):
            transforms.RandomPerspective(distortion_scale=-1.0)

        with pytest.raises(TypeError, match="Got inappropriate fill arg"):
            transforms.RandomPerspective(0.5, fill="abc")

Philip Meier's avatar
Philip Meier committed
491
    def test__get_params(self):
492
493
        dscale = 0.5
        transform = transforms.RandomPerspective(dscale)
Philip Meier's avatar
Philip Meier committed
494
495

        image = make_image((24, 32))
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

        params = transform._get_params([image])

        assert "coefficients" in params
        assert len(params["coefficients"]) == 8


class TestElasticTransform:
    def test_assertions(self):

        with pytest.raises(TypeError, match="alpha should be float or a sequence of floats"):
            transforms.ElasticTransform({})

        with pytest.raises(ValueError, match="alpha is a sequence its length should be one of 2"):
            transforms.ElasticTransform([1.0, 2.0, 3.0])

        with pytest.raises(ValueError, match="alpha should be a sequence of floats"):
            transforms.ElasticTransform([1, 2])

        with pytest.raises(TypeError, match="sigma should be float or a sequence of floats"):
            transforms.ElasticTransform(1.0, {})

        with pytest.raises(ValueError, match="sigma is a sequence its length should be one of 2"):
            transforms.ElasticTransform(1.0, [1.0, 2.0, 3.0])

        with pytest.raises(ValueError, match="sigma should be a sequence of floats"):
            transforms.ElasticTransform(1.0, [1, 2])

        with pytest.raises(TypeError, match="Got inappropriate fill arg"):
            transforms.ElasticTransform(1.0, 2.0, fill="abc")

Philip Meier's avatar
Philip Meier committed
527
    def test__get_params(self):
528
529
530
        alpha = 2.0
        sigma = 3.0
        transform = transforms.ElasticTransform(alpha, sigma)
Philip Meier's avatar
Philip Meier committed
531
532
533

        h, w = size = (24, 32)
        image = make_image(size)
534
535
536
537
538
539
540
541
542
543

        params = transform._get_params([image])

        displacement = params["displacement"]
        assert displacement.shape == (1, h, w, 2)
        assert (-alpha / w <= displacement[0, ..., 0]).all() and (displacement[0, ..., 0] <= alpha / w).all()
        assert (-alpha / h <= displacement[0, ..., 1]).all() and (displacement[0, ..., 1] <= alpha / h).all()


class TestRandomErasing:
Philip Meier's avatar
Philip Meier committed
544
    def test_assertions(self):
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
        with pytest.raises(TypeError, match="Argument value should be either a number or str or a sequence"):
            transforms.RandomErasing(value={})

        with pytest.raises(ValueError, match="If value is str, it should be 'random'"):
            transforms.RandomErasing(value="abc")

        with pytest.raises(TypeError, match="Scale should be a sequence"):
            transforms.RandomErasing(scale=123)

        with pytest.raises(TypeError, match="Ratio should be a sequence"):
            transforms.RandomErasing(ratio=123)

        with pytest.raises(ValueError, match="Scale should be between 0 and 1"):
            transforms.RandomErasing(scale=[-1, 2])

Philip Meier's avatar
Philip Meier committed
560
        image = make_image((24, 32))
561
562
563
564
565
566
567

        transform = transforms.RandomErasing(value=[1, 2, 3, 4])

        with pytest.raises(ValueError, match="If value is a sequence, it should have either a single value"):
            transform._get_params([image])

    @pytest.mark.parametrize("value", [5.0, [1, 2, 3], "random"])
Philip Meier's avatar
Philip Meier committed
568
569
570
    def test__get_params(self, value):
        image = make_image((24, 32))
        num_channels, height, width = F.get_dimensions(image)
571
572
573
574
575
576
577
578
579

        transform = transforms.RandomErasing(value=value)
        params = transform._get_params([image])

        v = params["v"]
        h, w = params["h"], params["w"]
        i, j = params["i"], params["j"]
        assert isinstance(v, torch.Tensor)
        if value == "random":
Philip Meier's avatar
Philip Meier committed
580
            assert v.shape == (num_channels, h, w)
581
582
583
        elif isinstance(value, (int, float)):
            assert v.shape == (1, 1, 1)
        elif isinstance(value, (list, tuple)):
Philip Meier's avatar
Philip Meier committed
584
            assert v.shape == (num_channels, 1, 1)
585

Philip Meier's avatar
Philip Meier committed
586
587
        assert 0 <= i <= height - h
        assert 0 <= j <= width - w
588
589
590
591
592


class TestTransform:
    @pytest.mark.parametrize(
        "inpt_type",
593
        [torch.Tensor, PIL.Image.Image, tv_tensors.Image, np.ndarray, tv_tensors.BoundingBoxes, str, int],
594
595
596
597
598
599
600
601
602
603
604
605
606
607
    )
    def test_check_transformed_types(self, inpt_type, mocker):
        # This test ensures that we correctly handle which types to transform and which to bypass
        t = transforms.Transform()
        inpt = mocker.MagicMock(spec=inpt_type)

        if inpt_type in (np.ndarray, str, int):
            output = t(inpt)
            assert output is inpt
        else:
            with pytest.raises(NotImplementedError):
                t(inpt)


608
class TestToImage:
609
610
    @pytest.mark.parametrize(
        "inpt_type",
611
        [torch.Tensor, PIL.Image.Image, tv_tensors.Image, np.ndarray, tv_tensors.BoundingBoxes, str, int],
612
613
614
    )
    def test__transform(self, inpt_type, mocker):
        fn = mocker.patch(
615
            "torchvision.transforms.v2.functional.to_image",
616
617
618
619
            return_value=torch.rand(1, 3, 8, 8),
        )

        inpt = mocker.MagicMock(spec=inpt_type)
620
        transform = transforms.ToImage()
621
        transform(inpt)
622
        if inpt_type in (tv_tensors.BoundingBoxes, tv_tensors.Image, str, int):
623
624
625
626
627
628
629
630
            assert fn.call_count == 0
        else:
            fn.assert_called_once_with(inpt)


class TestToPILImage:
    @pytest.mark.parametrize(
        "inpt_type",
631
        [torch.Tensor, PIL.Image.Image, tv_tensors.Image, np.ndarray, tv_tensors.BoundingBoxes, str, int],
632
633
    )
    def test__transform(self, inpt_type, mocker):
634
        fn = mocker.patch("torchvision.transforms.v2.functional.to_pil_image")
635
636
637
638

        inpt = mocker.MagicMock(spec=inpt_type)
        transform = transforms.ToPILImage()
        transform(inpt)
639
        if inpt_type in (PIL.Image.Image, tv_tensors.BoundingBoxes, str, int):
640
641
642
643
644
645
646
647
            assert fn.call_count == 0
        else:
            fn.assert_called_once_with(inpt, mode=transform.mode)


class TestToTensor:
    @pytest.mark.parametrize(
        "inpt_type",
648
        [torch.Tensor, PIL.Image.Image, tv_tensors.Image, np.ndarray, tv_tensors.BoundingBoxes, str, int],
649
650
651
652
653
654
655
656
    )
    def test__transform(self, inpt_type, mocker):
        fn = mocker.patch("torchvision.transforms.functional.to_tensor")

        inpt = mocker.MagicMock(spec=inpt_type)
        with pytest.warns(UserWarning, match="deprecated and will be removed"):
            transform = transforms.ToTensor()
        transform(inpt)
657
        if inpt_type in (tv_tensors.Image, torch.Tensor, tv_tensors.BoundingBoxes, str, int):
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
            assert fn.call_count == 0
        else:
            fn.assert_called_once_with(inpt)


class TestContainers:
    @pytest.mark.parametrize("transform_cls", [transforms.Compose, transforms.RandomChoice, transforms.RandomOrder])
    def test_assertions(self, transform_cls):
        with pytest.raises(TypeError, match="Argument transforms should be a sequence of callables"):
            transform_cls(transforms.RandomCrop(28))

    @pytest.mark.parametrize("transform_cls", [transforms.Compose, transforms.RandomChoice, transforms.RandomOrder])
    @pytest.mark.parametrize(
        "trfms",
        [
            [transforms.Pad(2), transforms.RandomCrop(28)],
            [lambda x: 2.0 * x, transforms.Pad(2), transforms.RandomCrop(28)],
            [transforms.Pad(2), lambda x: 2.0 * x, transforms.RandomCrop(28)],
        ],
    )
    def test_ctor(self, transform_cls, trfms):
        c = transform_cls(trfms)
        inpt = torch.rand(1, 3, 32, 32)
        output = c(inpt)
        assert isinstance(output, torch.Tensor)
        assert output.ndim == 4


class TestRandomChoice:
    def test_assertions(self):
688
        with pytest.raises(ValueError, match="Length of p doesn't match the number of transforms"):
689
            transforms.RandomChoice([transforms.Pad(2), transforms.RandomCrop(28)], p=[1])
690
691
692


class TestRandomIoUCrop:
693
    @pytest.mark.parametrize("device", cpu_and_cuda())
694
    @pytest.mark.parametrize("options", [[0.5, 0.9], [2.0]])
Philip Meier's avatar
Philip Meier committed
695
696
697
    def test__get_params(self, device, options):
        orig_h, orig_w = size = (24, 32)
        image = make_image(size)
698
        bboxes = tv_tensors.BoundingBoxes(
699
700
            torch.tensor([[1, 1, 10, 10], [20, 20, 23, 23], [1, 20, 10, 23], [20, 1, 23, 10]]),
            format="XYXY",
Philip Meier's avatar
Philip Meier committed
701
            canvas_size=size,
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
            device=device,
        )
        sample = [image, bboxes]

        transform = transforms.RandomIoUCrop(sampler_options=options)

        n_samples = 5
        for _ in range(n_samples):

            params = transform._get_params(sample)

            if options == [2.0]:
                assert len(params) == 0
                return

            assert len(params["is_within_crop_area"]) > 0
            assert params["is_within_crop_area"].dtype == torch.bool

            assert int(transform.min_scale * orig_h) <= params["height"] <= int(transform.max_scale * orig_h)
            assert int(transform.min_scale * orig_w) <= params["width"] <= int(transform.max_scale * orig_w)

            left, top = params["left"], params["top"]
            new_h, new_w = params["height"], params["width"]
            ious = box_iou(
                bboxes,
                torch.tensor([[left, top, left + new_w, top + new_h]], dtype=bboxes.dtype, device=bboxes.device),
            )
            assert ious.max() >= options[0] or ious.max() >= options[1], f"{ious} vs {options}"

    def test__transform_empty_params(self, mocker):
        transform = transforms.RandomIoUCrop(sampler_options=[2.0])
733
734
        image = tv_tensors.Image(torch.rand(1, 3, 4, 4))
        bboxes = tv_tensors.BoundingBoxes(torch.tensor([[1, 1, 2, 2]]), format="XYXY", canvas_size=(4, 4))
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
        label = torch.tensor([1])
        sample = [image, bboxes, label]
        # Let's mock transform._get_params to control the output:
        transform._get_params = mocker.MagicMock(return_value={})
        output = transform(sample)
        torch.testing.assert_close(output, sample)

    def test_forward_assertion(self):
        transform = transforms.RandomIoUCrop()
        with pytest.raises(
            TypeError,
            match="requires input sample to contain tensor or PIL images and bounding boxes",
        ):
            transform(torch.tensor(0))

    def test__transform(self, mocker):
        transform = transforms.RandomIoUCrop()

Philip Meier's avatar
Philip Meier committed
753
754
        size = (32, 24)
        image = make_image(size)
755
        bboxes = make_bounding_boxes(format="XYXY", canvas_size=size, batch_dims=(6,))
Philip Meier's avatar
Philip Meier committed
756
        masks = make_detection_mask(size, num_objects=6)
757
758
759
760
761
762
763
764
765
766
767

        sample = [image, bboxes, masks]

        is_within_crop_area = torch.tensor([0, 1, 0, 1, 0, 1], dtype=torch.bool)

        params = dict(top=1, left=2, height=12, width=12, is_within_crop_area=is_within_crop_area)
        transform._get_params = mocker.MagicMock(return_value=params)
        output = transform(sample)

        # check number of bboxes vs number of labels:
        output_bboxes = output[1]
768
        assert isinstance(output_bboxes, tv_tensors.BoundingBoxes)
769
770
771
        assert (output_bboxes[~is_within_crop_area] == 0).all()

        output_masks = output[2]
772
        assert isinstance(output_masks, tv_tensors.Mask)
773
774
775


class TestScaleJitter:
Philip Meier's avatar
Philip Meier committed
776
777
    def test__get_params(self):
        canvas_size = (24, 32)
778
779
780
781
        target_size = (16, 12)
        scale_range = (0.5, 1.5)

        transform = transforms.ScaleJitter(target_size=target_size, scale_range=scale_range)
Philip Meier's avatar
Philip Meier committed
782
783

        sample = make_image(canvas_size)
784
785
786
787
788
789
790
791
792
793
794
795

        n_samples = 5
        for _ in range(n_samples):

            params = transform._get_params([sample])

            assert "size" in params
            size = params["size"]

            assert isinstance(size, tuple) and len(size) == 2
            height, width = size

Philip Meier's avatar
Philip Meier committed
796
797
            r_min = min(target_size[1] / canvas_size[0], target_size[0] / canvas_size[1]) * scale_range[0]
            r_max = min(target_size[1] / canvas_size[0], target_size[0] / canvas_size[1]) * scale_range[1]
798

Philip Meier's avatar
Philip Meier committed
799
800
            assert int(canvas_size[0] * r_min) <= height <= int(canvas_size[0] * r_max)
            assert int(canvas_size[1] * r_min) <= width <= int(canvas_size[1] * r_max)
801
802
803
804


class TestRandomShortestSize:
    @pytest.mark.parametrize("min_size,max_size", [([5, 9], 20), ([5, 9], None)])
Philip Meier's avatar
Philip Meier committed
805
806
    def test__get_params(self, min_size, max_size):
        canvas_size = (3, 10)
807

808
        transform = transforms.RandomShortestSize(min_size=min_size, max_size=max_size, antialias=True)
809

Philip Meier's avatar
Philip Meier committed
810
        sample = make_image(canvas_size)
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
        params = transform._get_params([sample])

        assert "size" in params
        size = params["size"]

        assert isinstance(size, tuple) and len(size) == 2

        longer = max(size)
        shorter = min(size)
        if max_size is not None:
            assert longer <= max_size
            assert shorter <= max_size
        else:
            assert shorter in min_size


class TestLinearTransformation:
    def test_assertions(self):
        with pytest.raises(ValueError, match="transformation_matrix should be square"):
            transforms.LinearTransformation(torch.rand(2, 3), torch.rand(5))

        with pytest.raises(ValueError, match="mean_vector should have the same length"):
            transforms.LinearTransformation(torch.rand(3, 3), torch.rand(5))

    @pytest.mark.parametrize(
        "inpt",
        [
            122 * torch.ones(1, 3, 8, 8),
            122.0 * torch.ones(1, 3, 8, 8),
840
            tv_tensors.Image(122 * torch.ones(1, 3, 8, 8)),
841
842
843
844
845
846
847
848
849
850
            PIL.Image.new("RGB", (8, 8), (122, 122, 122)),
        ],
    )
    def test__transform(self, inpt):

        v = 121 * torch.ones(3 * 8 * 8)
        m = torch.ones(3 * 8 * 8, 3 * 8 * 8)
        transform = transforms.LinearTransformation(m, v)

        if isinstance(inpt, PIL.Image.Image):
851
            with pytest.raises(TypeError, match="does not support PIL images"):
852
853
854
855
856
857
858
859
860
861
862
863
864
                transform(inpt)
        else:
            output = transform(inpt)
            assert isinstance(output, torch.Tensor)
            assert output.unique() == 3 * 8 * 8
            assert output.dtype == inpt.dtype


class TestRandomResize:
    def test__get_params(self):
        min_size = 3
        max_size = 6

865
        transform = transforms.RandomResize(min_size=min_size, max_size=max_size, antialias=True)
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881

        for _ in range(10):
            params = transform._get_params([])

            assert isinstance(params["size"], list) and len(params["size"]) == 1
            size = params["size"][0]

            assert min_size <= size < max_size


class TestUniformTemporalSubsample:
    @pytest.mark.parametrize(
        "inpt",
        [
            torch.zeros(10, 3, 8, 8),
            torch.zeros(1, 10, 3, 8, 8),
882
            tv_tensors.Video(torch.zeros(1, 10, 3, 8, 8)),
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
        ],
    )
    def test__transform(self, inpt):
        num_samples = 5
        transform = transforms.UniformTemporalSubsample(num_samples)

        output = transform(inpt)
        assert type(output) is type(inpt)
        assert output.shape[-4] == num_samples
        assert output.dtype == inpt.dtype


# TODO: remove this test in 0.17 when the default of antialias changes to True
def test_antialias_warning():
    pil_img = PIL.Image.new("RGB", size=(10, 10), color=127)
    tensor_img = torch.randint(0, 256, size=(3, 10, 10), dtype=torch.uint8)
    tensor_video = torch.randint(0, 256, size=(2, 3, 10, 10), dtype=torch.uint8)

    match = "The default value of the antialias parameter"
    with pytest.warns(UserWarning, match=match):
        transforms.RandomResizedCrop((20, 20))(tensor_img)
    with pytest.warns(UserWarning, match=match):
        transforms.ScaleJitter((20, 20))(tensor_img)
    with pytest.warns(UserWarning, match=match):
        transforms.RandomShortestSize((20, 20))(tensor_img)
    with pytest.warns(UserWarning, match=match):
        transforms.RandomResize(10, 20)(tensor_img)

    with pytest.warns(UserWarning, match=match):
912
        F.resized_crop(tv_tensors.Image(tensor_img), 0, 0, 10, 10, (20, 20))
913
914

    with pytest.warns(UserWarning, match=match):
915
        F.resize(tv_tensors.Video(tensor_video), (20, 20))
916
    with pytest.warns(UserWarning, match=match):
917
        F.resized_crop(tv_tensors.Video(tensor_video), 0, 0, 10, 10, (20, 20))
918
919
920
921
922
923
924
925
926
927
928
929
930

    with warnings.catch_warnings():
        warnings.simplefilter("error")
        transforms.RandomResizedCrop((20, 20))(pil_img)
        transforms.ScaleJitter((20, 20))(pil_img)
        transforms.RandomShortestSize((20, 20))(pil_img)
        transforms.RandomResize(10, 20)(pil_img)

        transforms.RandomResizedCrop((20, 20), antialias=True)(tensor_img)
        transforms.ScaleJitter((20, 20), antialias=True)(tensor_img)
        transforms.RandomShortestSize((20, 20), antialias=True)(tensor_img)
        transforms.RandomResize(10, 20, antialias=True)(tensor_img)

931
932
        F.resized_crop(tv_tensors.Image(tensor_img), 0, 0, 10, 10, (20, 20), antialias=True)
        F.resized_crop(tv_tensors.Video(tensor_video), 0, 0, 10, 10, (20, 20), antialias=True)
933
934


935
@pytest.mark.parametrize("image_type", (PIL.Image, torch.Tensor, tv_tensors.Image))
936
937
@pytest.mark.parametrize("label_type", (torch.Tensor, int))
@pytest.mark.parametrize("dataset_return_type", (dict, tuple))
938
@pytest.mark.parametrize("to_tensor", (transforms.ToTensor, transforms.ToImage))
939
940
def test_classif_preset(image_type, label_type, dataset_return_type, to_tensor):

941
    image = tv_tensors.Image(torch.randint(0, 256, size=(1, 3, 250, 250), dtype=torch.uint8))
942
943
944
945
    if image_type is PIL.Image:
        image = to_pil_image(image[0])
    elif image_type is torch.Tensor:
        image = image.as_subclass(torch.Tensor)
946
        assert is_pure_tensor(image)
947
948
949
950
951
952
953
954
955
956
957

    label = 1 if label_type is int else torch.tensor([1])

    if dataset_return_type is dict:
        sample = {
            "image": image,
            "label": label,
        }
    else:
        sample = image, label

958
959
960
961
962
963
    if to_tensor is transforms.ToTensor:
        with pytest.warns(UserWarning, match="deprecated and will be removed"):
            to_tensor = to_tensor()
    else:
        to_tensor = to_tensor()

964
965
    t = transforms.Compose(
        [
966
            transforms.RandomResizedCrop((224, 224), antialias=True),
967
968
969
970
971
            transforms.RandomHorizontalFlip(p=1),
            transforms.RandAugment(),
            transforms.TrivialAugmentWide(),
            transforms.AugMix(),
            transforms.AutoAugment(),
972
            to_tensor,
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
            # TODO: ConvertImageDtype is a pass-through on PIL images, is that
            # intended?  This results in a failure if we convert to tensor after
            # it, because the image would still be uint8 which make Normalize
            # fail.
            transforms.ConvertImageDtype(torch.float),
            transforms.Normalize(mean=[0, 0, 0], std=[1, 1, 1]),
            transforms.RandomErasing(p=1),
        ]
    )

    out = t(sample)

    assert type(out) == type(sample)

    if dataset_return_type is tuple:
        out_image, out_label = out
    else:
        assert out.keys() == sample.keys()
        out_image, out_label = out.values()

    assert out_image.shape[-2:] == (224, 224)
    assert out_label == label


997
@pytest.mark.parametrize("image_type", (PIL.Image, torch.Tensor, tv_tensors.Image))
998
@pytest.mark.parametrize("data_augmentation", ("hflip", "lsj", "multiscale", "ssd", "ssdlite"))
999
@pytest.mark.parametrize("to_tensor", (transforms.ToTensor, transforms.ToImage))
1000
1001
1002
@pytest.mark.parametrize("sanitize", (True, False))
def test_detection_preset(image_type, data_augmentation, to_tensor, sanitize):
    torch.manual_seed(0)
1003
1004
1005
1006
1007
1008
1009

    if to_tensor is transforms.ToTensor:
        with pytest.warns(UserWarning, match="deprecated and will be removed"):
            to_tensor = to_tensor()
    else:
        to_tensor = to_tensor()

1010
1011
1012
    if data_augmentation == "hflip":
        t = [
            transforms.RandomHorizontalFlip(p=1),
1013
            to_tensor,
1014
1015
1016
1017
1018
1019
1020
1021
1022
            transforms.ConvertImageDtype(torch.float),
        ]
    elif data_augmentation == "lsj":
        t = [
            transforms.ScaleJitter(target_size=(1024, 1024), antialias=True),
            # Note: replaced FixedSizeCrop with RandomCrop, becuase we're
            # leaving FixedSizeCrop in prototype for now, and it expects Label
            # classes which we won't release yet.
            # transforms.FixedSizeCrop(
1023
            #     size=(1024, 1024), fill=defaultdict(lambda: (123.0, 117.0, 104.0), {tv_tensors.Mask: 0})
1024
1025
1026
            # ),
            transforms.RandomCrop((1024, 1024), pad_if_needed=True),
            transforms.RandomHorizontalFlip(p=1),
1027
            to_tensor,
1028
1029
1030
1031
1032
1033
1034
1035
            transforms.ConvertImageDtype(torch.float),
        ]
    elif data_augmentation == "multiscale":
        t = [
            transforms.RandomShortestSize(
                min_size=(480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800), max_size=1333, antialias=True
            ),
            transforms.RandomHorizontalFlip(p=1),
1036
            to_tensor,
1037
1038
1039
1040
1041
            transforms.ConvertImageDtype(torch.float),
        ]
    elif data_augmentation == "ssd":
        t = [
            transforms.RandomPhotometricDistort(p=1),
1042
            transforms.RandomZoomOut(fill={"others": (123.0, 117.0, 104.0), tv_tensors.Mask: 0}, p=1),
1043
1044
            transforms.RandomIoUCrop(),
            transforms.RandomHorizontalFlip(p=1),
1045
            to_tensor,
1046
1047
1048
1049
1050
1051
            transforms.ConvertImageDtype(torch.float),
        ]
    elif data_augmentation == "ssdlite":
        t = [
            transforms.RandomIoUCrop(),
            transforms.RandomHorizontalFlip(p=1),
1052
            to_tensor,
1053
1054
1055
            transforms.ConvertImageDtype(torch.float),
        ]
    if sanitize:
1056
        t += [transforms.SanitizeBoundingBoxes()]
1057
1058
1059
1060
1061
    t = transforms.Compose(t)

    num_boxes = 5
    H = W = 250

1062
    image = tv_tensors.Image(torch.randint(0, 256, size=(1, 3, H, W), dtype=torch.uint8))
1063
1064
1065
1066
    if image_type is PIL.Image:
        image = to_pil_image(image[0])
    elif image_type is torch.Tensor:
        image = image.as_subclass(torch.Tensor)
1067
        assert is_pure_tensor(image)
1068
1069
1070
1071
1072
1073

    label = torch.randint(0, 10, size=(num_boxes,))

    boxes = torch.randint(0, min(H, W) // 2, size=(num_boxes, 4))
    boxes[:, 2:] += boxes[:, :2]
    boxes = boxes.clamp(min=0, max=min(H, W))
1074
    boxes = tv_tensors.BoundingBoxes(boxes, format="XYXY", canvas_size=(H, W))
1075

1076
    masks = tv_tensors.Mask(torch.randint(0, 2, size=(num_boxes, H, W), dtype=torch.uint8))
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086

    sample = {
        "image": image,
        "label": label,
        "boxes": boxes,
        "masks": masks,
    }

    out = t(sample)

1087
    if isinstance(to_tensor, transforms.ToTensor) and image_type is not tv_tensors.Image:
1088
        assert is_pure_tensor(out["image"])
1089
    else:
1090
        assert isinstance(out["image"], tv_tensors.Image)
1091
1092
1093
1094
1095
1096
    assert isinstance(out["label"], type(sample["label"]))

    num_boxes_expected = {
        # ssd and ssdlite contain RandomIoUCrop which may "remove" some bbox. It
        # doesn't remove them strictly speaking, it just marks some boxes as
        # degenerate and those boxes will be later removed by
1097
        # SanitizeBoundingBoxes(), which we add to the pipelines if the sanitize
1098
1099
1100
        # param is True.
        # Note that the values below are probably specific to the random seed
        # set above (which is fine).
1101
        (True, "ssd"): 5,
1102
1103
1104
1105
1106
1107
1108
        (True, "ssdlite"): 4,
    }.get((sanitize, data_augmentation), num_boxes)

    assert out["boxes"].shape[0] == out["masks"].shape[0] == out["label"].shape[0] == num_boxes_expected


@pytest.mark.parametrize("min_size", (1, 10))
1109
@pytest.mark.parametrize("labels_getter", ("default", lambda inputs: inputs["labels"], None, lambda inputs: None))
1110
1111
1112
1113
1114
1115
1116
1117
@pytest.mark.parametrize("sample_type", (tuple, dict))
def test_sanitize_bounding_boxes(min_size, labels_getter, sample_type):

    if sample_type is tuple and not isinstance(labels_getter, str):
        # The "lambda inputs: inputs["labels"]" labels_getter used in this test
        # doesn't work if the input is a tuple.
        return

1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
    H, W = 256, 128

    boxes_and_validity = [
        ([0, 1, 10, 1], False),  # Y1 == Y2
        ([0, 1, 0, 20], False),  # X1 == X2
        ([0, 0, min_size - 1, 10], False),  # H < min_size
        ([0, 0, 10, min_size - 1], False),  # W < min_size
        ([0, 0, 10, H + 1], False),  # Y2 > H
        ([0, 0, W + 1, 10], False),  # X2 > W
        ([-1, 1, 10, 20], False),  # any < 0
        ([0, 0, -1, 20], False),  # any < 0
        ([0, 0, -10, -1], False),  # any < 0
        ([0, 0, min_size, 10], True),  # H < min_size
        ([0, 0, 10, min_size], True),  # W < min_size
        ([0, 0, W, H], True),  # TODO: Is that actually OK?? Should it be -1?
        ([1, 1, 30, 20], True),
        ([0, 0, 10, 10], True),
        ([1, 1, 30, 20], True),
    ]

    random.shuffle(boxes_and_validity)  # For test robustness: mix order of wrong and correct cases
    boxes, is_valid_mask = zip(*boxes_and_validity)
    valid_indices = [i for (i, is_valid) in enumerate(is_valid_mask) if is_valid]

    boxes = torch.tensor(boxes)
    labels = torch.arange(boxes.shape[0])

1145
    boxes = tv_tensors.BoundingBoxes(
1146
        boxes,
1147
        format=tv_tensors.BoundingBoxFormat.XYXY,
Philip Meier's avatar
Philip Meier committed
1148
        canvas_size=(H, W),
1149
1150
    )

1151
    masks = tv_tensors.Mask(torch.randint(0, 2, size=(boxes.shape[0], H, W)))
1152
1153
    whatever = torch.rand(10)
    input_img = torch.randint(0, 256, size=(1, 3, H, W), dtype=torch.uint8)
1154
    sample = {
1155
        "image": input_img,
1156
1157
        "labels": labels,
        "boxes": boxes,
1158
        "whatever": whatever,
1159
1160
1161
1162
        "None": None,
        "masks": masks,
    }

1163
1164
1165
1166
    if sample_type is tuple:
        img = sample.pop("image")
        sample = (img, sample)

1167
    out = transforms.SanitizeBoundingBoxes(min_size=min_size, labels_getter=labels_getter)(sample)
1168

1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
    if sample_type is tuple:
        out_image = out[0]
        out_labels = out[1]["labels"]
        out_boxes = out[1]["boxes"]
        out_masks = out[1]["masks"]
        out_whatever = out[1]["whatever"]
    else:
        out_image = out["image"]
        out_labels = out["labels"]
        out_boxes = out["boxes"]
        out_masks = out["masks"]
        out_whatever = out["whatever"]

    assert out_image is input_img
    assert out_whatever is whatever
1184

1185
1186
    assert isinstance(out_boxes, tv_tensors.BoundingBoxes)
    assert isinstance(out_masks, tv_tensors.Mask)
1187

1188
    if labels_getter is None or (callable(labels_getter) and labels_getter({"labels": "blah"}) is None):
1189
        assert out_labels is labels
1190
    else:
1191
1192
        assert isinstance(out_labels, torch.Tensor)
        assert out_boxes.shape[0] == out_labels.shape[0] == out_masks.shape[0]
1193
        # This works because we conveniently set labels to arange(num_boxes)
1194
        assert out_labels.tolist() == valid_indices
1195
1196


1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
def test_sanitize_bounding_boxes_no_label():
    # Non-regression test for https://github.com/pytorch/vision/issues/7878

    img = make_image()
    boxes = make_bounding_boxes()

    with pytest.raises(ValueError, match="or a two-tuple whose second item is a dict"):
        transforms.SanitizeBoundingBoxes()(img, boxes)

    out_img, out_boxes = transforms.SanitizeBoundingBoxes(labels_getter=None)(img, boxes)
1207
1208
    assert isinstance(out_img, tv_tensors.Image)
    assert isinstance(out_boxes, tv_tensors.BoundingBoxes)
1209
1210


1211
1212
def test_sanitize_bounding_boxes_errors():

1213
    good_bbox = tv_tensors.BoundingBoxes(
1214
        [[0, 0, 10, 10]],
1215
        format=tv_tensors.BoundingBoxFormat.XYXY,
Philip Meier's avatar
Philip Meier committed
1216
        canvas_size=(20, 20),
1217
1218
1219
    )

    with pytest.raises(ValueError, match="min_size must be >= 1"):
1220
        transforms.SanitizeBoundingBoxes(min_size=0)
1221
    with pytest.raises(ValueError, match="labels_getter should either be 'default'"):
1222
        transforms.SanitizeBoundingBoxes(labels_getter=12)
1223
1224
1225

    with pytest.raises(ValueError, match="Could not infer where the labels are"):
        bad_labels_key = {"bbox": good_bbox, "BAD_KEY": torch.arange(good_bbox.shape[0])}
1226
        transforms.SanitizeBoundingBoxes()(bad_labels_key)
1227
1228
1229

    with pytest.raises(ValueError, match="must be a tensor"):
        not_a_tensor = {"bbox": good_bbox, "labels": torch.arange(good_bbox.shape[0]).tolist()}
1230
        transforms.SanitizeBoundingBoxes()(not_a_tensor)
1231
1232
1233

    with pytest.raises(ValueError, match="Number of boxes"):
        different_sizes = {"bbox": good_bbox, "labels": torch.arange(good_bbox.shape[0] + 3)}
1234
        transforms.SanitizeBoundingBoxes()(different_sizes)
1235

1236

Philip Meier's avatar
Philip Meier committed
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
class TestLambda:
    inputs = pytest.mark.parametrize("input", [object(), torch.empty(()), np.empty(()), "string", 1, 0.0])

    @inputs
    def test_default(self, input):
        was_applied = False

        def was_applied_fn(input):
            nonlocal was_applied
            was_applied = True
            return input

        transform = transforms.Lambda(was_applied_fn)

        transform(input)

        assert was_applied

    @inputs
    def test_with_types(self, input):
        was_applied = False

        def was_applied_fn(input):
            nonlocal was_applied
            was_applied = True
            return input

        types = (torch.Tensor, np.ndarray)
        transform = transforms.Lambda(was_applied_fn, *types)

        transform(input)

        assert was_applied is isinstance(input, types)