test_functional_tensor.py 52.4 KB
Newer Older
1
import colorsys
2
import itertools
3
import math
4
import os
5
import re
6
from functools import partial
7
from typing import Sequence
8

vfdev's avatar
vfdev committed
9
import numpy as np
10
import pytest
vfdev's avatar
vfdev committed
11
import torch
12
import torchvision.transforms as T
13
14
15
import torchvision.transforms.functional as F
import torchvision.transforms.functional_pil as F_pil
import torchvision.transforms.functional_tensor as F_t
Nicolas Hug's avatar
Nicolas Hug committed
16
from common_utils import (
17
18
    _assert_approx_equal_tensor_to_pil,
    _assert_equal_tensor_to_pil,
Nicolas Hug's avatar
Nicolas Hug committed
19
20
21
    _create_data,
    _create_data_batch,
    _test_fn_on_batch,
22
    assert_equal,
23
24
    cpu_and_gpu,
    needs_cuda,
Nicolas Hug's avatar
Nicolas Hug committed
25
)
26
from torchvision.transforms import InterpolationMode
27

28
NEAREST, BILINEAR, BICUBIC = InterpolationMode.NEAREST, InterpolationMode.BILINEAR, InterpolationMode.BICUBIC
29
30


31
@pytest.mark.parametrize("device", cpu_and_gpu())
32
@pytest.mark.parametrize("fn", [F.get_image_size, F.get_image_num_channels, F.get_dimensions])
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
def test_image_sizes(device, fn):
    script_F = torch.jit.script(fn)

    img_tensor, pil_img = _create_data(16, 18, 3, device=device)
    value_img = fn(img_tensor)
    value_pil_img = fn(pil_img)
    assert value_img == value_pil_img

    value_img_script = script_F(img_tensor)
    assert value_img == value_img_script

    batch_tensors = _create_data_batch(16, 18, 3, num_samples=4, device=device)
    value_img_batch = fn(batch_tensors)
    assert value_img == value_img_batch


49
50
51
52
53
54
55
56
@needs_cuda
def test_scale_channel():
    """Make sure that _scale_channel gives the same results on CPU and GPU as
    histc or bincount are used depending on the device.
    """
    # TODO: when # https://github.com/pytorch/pytorch/issues/53194 is fixed,
    # only use bincount and remove that test.
    size = (1_000,)
57
    img_chan = torch.randint(0, 256, size=size).to("cpu")
58
    scaled_cpu = F_t._scale_channel(img_chan)
59
60
    scaled_cuda = F_t._scale_channel(img_chan.to("cuda"))
    assert_equal(scaled_cpu, scaled_cuda.to("cpu"))
61

62

63
64
65
66
67
68
class TestRotate:

    ALL_DTYPES = [None, torch.float32, torch.float64, torch.float16]
    scripted_rotate = torch.jit.script(F.rotate)
    IMG_W = 26

69
    @pytest.mark.parametrize("device", cpu_and_gpu())
70
    @pytest.mark.parametrize("height, width", [(7, 33), (26, IMG_W), (32, IMG_W)])
71
72
73
74
75
76
77
78
79
    @pytest.mark.parametrize(
        "center",
        [
            None,
            (int(IMG_W * 0.3), int(IMG_W * 0.4)),
            [int(IMG_W * 0.5), int(IMG_W * 0.6)],
        ],
    )
    @pytest.mark.parametrize("dt", ALL_DTYPES)
80
    @pytest.mark.parametrize("angle", range(-180, 180, 34))
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
    @pytest.mark.parametrize("expand", [True, False])
    @pytest.mark.parametrize(
        "fill",
        [
            None,
            [0, 0, 0],
            (1, 2, 3),
            [255, 255, 255],
            [
                1,
            ],
            (2.0,),
        ],
    )
    @pytest.mark.parametrize("fn", [F.rotate, scripted_rotate])
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
    def test_rotate(self, device, height, width, center, dt, angle, expand, fill, fn):
        tensor, pil_img = _create_data(height, width, device=device)

        if dt == torch.float16 and torch.device(device).type == "cpu":
            # skip float16 on CPU case
            return

        if dt is not None:
            tensor = tensor.to(dtype=dt)

        f_pil = int(fill[0]) if fill is not None and len(fill) == 1 else fill
        out_pil_img = F.rotate(pil_img, angle=angle, interpolation=NEAREST, expand=expand, center=center, fill=f_pil)
        out_pil_tensor = torch.from_numpy(np.array(out_pil_img).transpose((2, 0, 1)))

        out_tensor = fn(tensor, angle=angle, interpolation=NEAREST, expand=expand, center=center, fill=fill).cpu()

        if out_tensor.dtype != torch.uint8:
            out_tensor = out_tensor.to(torch.uint8)

115
116
117
        assert (
            out_tensor.shape == out_pil_tensor.shape
        ), f"{(height, width, NEAREST, dt, angle, expand, center)}: {out_tensor.shape} vs {out_pil_tensor.shape}"
118
119
120
121
122
123
124

        num_diff_pixels = (out_tensor != out_pil_tensor).sum().item() / 3.0
        ratio_diff_pixels = num_diff_pixels / out_tensor.shape[-1] / out_tensor.shape[-2]
        # Tolerance : less than 3% of different pixels
        assert ratio_diff_pixels < 0.03, (
            f"{(height, width, NEAREST, dt, angle, expand, center, fill)}: "
            f"{ratio_diff_pixels}\n{out_tensor[0, :7, :7]} vs \n"
125
126
            f"{out_pil_tensor[0, :7, :7]}"
        )
127

128
129
    @pytest.mark.parametrize("device", cpu_and_gpu())
    @pytest.mark.parametrize("dt", ALL_DTYPES)
130
131
132
133
134
135
136
137
138
139
    def test_rotate_batch(self, device, dt):
        if dt == torch.float16 and device == "cpu":
            # skip float16 on CPU case
            return

        batch_tensors = _create_data_batch(26, 36, num_samples=4, device=device)
        if dt is not None:
            batch_tensors = batch_tensors.to(dtype=dt)

        center = (20, 22)
140
        _test_fn_on_batch(batch_tensors, F.rotate, angle=32, interpolation=NEAREST, expand=True, center=center)
141
142
143
144

    def test_rotate_deprecation_resample(self):
        tensor, _ = _create_data(26, 26)
        # assert deprecation warning and non-BC
145
146
147
148
149
150
151
        with pytest.warns(
            UserWarning,
            match=re.escape(
                "The parameter 'resample' is deprecated since 0.12 and will be removed 0.14. "
                "Please use 'interpolation' instead."
            ),
        ):
152
153
154
155
156
157
158
            res1 = F.rotate(tensor, 45, resample=2)
            res2 = F.rotate(tensor, 45, interpolation=BILINEAR)
            assert_equal(res1, res2)

    def test_rotate_interpolation_type(self):
        tensor, _ = _create_data(26, 26)
        # assert changed type warning
159
160
161
162
163
164
165
        with pytest.warns(
            UserWarning,
            match=re.escape(
                "Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. "
                "Please use InterpolationMode enum."
            ),
        ):
166
167
168
169
170
            res1 = F.rotate(tensor, 45, interpolation=2)
            res2 = F.rotate(tensor, 45, interpolation=BILINEAR)
            assert_equal(res1, res2)


171
172
173
174
175
class TestAffine:

    ALL_DTYPES = [None, torch.float32, torch.float64, torch.float16]
    scripted_affine = torch.jit.script(F.affine)

176
177
178
    @pytest.mark.parametrize("device", cpu_and_gpu())
    @pytest.mark.parametrize("height, width", [(26, 26), (32, 26)])
    @pytest.mark.parametrize("dt", ALL_DTYPES)
179
180
181
182
183
184
185
186
187
188
189
190
191
192
    def test_identity_map(self, device, height, width, dt):
        # Tests on square and rectangular images
        tensor, pil_img = _create_data(height, width, device=device)

        if dt == torch.float16 and device == "cpu":
            # skip float16 on CPU case
            return

        if dt is not None:
            tensor = tensor.to(dtype=dt)

        # 1) identity map
        out_tensor = F.affine(tensor, angle=0, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=NEAREST)

193
        assert_equal(tensor, out_tensor, msg=f"{out_tensor[0, :5, :5]} vs {tensor[0, :5, :5]}")
194
195
196
        out_tensor = self.scripted_affine(
            tensor, angle=0, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=NEAREST
        )
197
        assert_equal(tensor, out_tensor, msg=f"{out_tensor[0, :5, :5]} vs {tensor[0, :5, :5]}")
198

199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
    @pytest.mark.parametrize("device", cpu_and_gpu())
    @pytest.mark.parametrize("height, width", [(26, 26)])
    @pytest.mark.parametrize("dt", ALL_DTYPES)
    @pytest.mark.parametrize(
        "angle, config",
        [
            (90, {"k": 1, "dims": (-1, -2)}),
            (45, None),
            (30, None),
            (-30, None),
            (-45, None),
            (-90, {"k": -1, "dims": (-1, -2)}),
            (180, {"k": 2, "dims": (-1, -2)}),
        ],
    )
    @pytest.mark.parametrize("fn", [F.affine, scripted_affine])
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
    def test_square_rotations(self, device, height, width, dt, angle, config, fn):
        # 2) Test rotation
        tensor, pil_img = _create_data(height, width, device=device)

        if dt == torch.float16 and device == "cpu":
            # skip float16 on CPU case
            return

        if dt is not None:
            tensor = tensor.to(dtype=dt)

        out_pil_img = F.affine(
            pil_img, angle=angle, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=NEAREST
        )
        out_pil_tensor = torch.from_numpy(np.array(out_pil_img).transpose((2, 0, 1))).to(device)

231
        out_tensor = fn(tensor, angle=angle, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=NEAREST)
232
        if config is not None:
233
            assert_equal(torch.rot90(tensor, **config), out_tensor)
234
235
236
237
238
239
240

        if out_tensor.dtype != torch.uint8:
            out_tensor = out_tensor.to(torch.uint8)

        num_diff_pixels = (out_tensor != out_pil_tensor).sum().item() / 3.0
        ratio_diff_pixels = num_diff_pixels / out_tensor.shape[-1] / out_tensor.shape[-2]
        # Tolerance : less than 6% of different pixels
241
        assert ratio_diff_pixels < 0.06
242

243
244
245
246
247
    @pytest.mark.parametrize("device", cpu_and_gpu())
    @pytest.mark.parametrize("height, width", [(32, 26)])
    @pytest.mark.parametrize("dt", ALL_DTYPES)
    @pytest.mark.parametrize("angle", [90, 45, 15, -30, -60, -120])
    @pytest.mark.parametrize("fn", [F.affine, scripted_affine])
248
249
    @pytest.mark.parametrize("center", [None, [0, 0]])
    def test_rect_rotations(self, device, height, width, dt, angle, fn, center):
250
251
252
253
254
255
256
257
258
259
260
        # Tests on rectangular images
        tensor, pil_img = _create_data(height, width, device=device)

        if dt == torch.float16 and device == "cpu":
            # skip float16 on CPU case
            return

        if dt is not None:
            tensor = tensor.to(dtype=dt)

        out_pil_img = F.affine(
261
            pil_img, angle=angle, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=NEAREST, center=center
262
263
264
        )
        out_pil_tensor = torch.from_numpy(np.array(out_pil_img).transpose((2, 0, 1)))

265
266
267
        out_tensor = fn(
            tensor, angle=angle, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=NEAREST, center=center
        ).cpu()
268
269
270
271
272
273
274

        if out_tensor.dtype != torch.uint8:
            out_tensor = out_tensor.to(torch.uint8)

        num_diff_pixels = (out_tensor != out_pil_tensor).sum().item() / 3.0
        ratio_diff_pixels = num_diff_pixels / out_tensor.shape[-1] / out_tensor.shape[-2]
        # Tolerance : less than 3% of different pixels
275
        assert ratio_diff_pixels < 0.03
276

277
278
279
280
281
    @pytest.mark.parametrize("device", cpu_and_gpu())
    @pytest.mark.parametrize("height, width", [(26, 26), (32, 26)])
    @pytest.mark.parametrize("dt", ALL_DTYPES)
    @pytest.mark.parametrize("t", [[10, 12], (-12, -13)])
    @pytest.mark.parametrize("fn", [F.affine, scripted_affine])
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
    def test_translations(self, device, height, width, dt, t, fn):
        # 3) Test translation
        tensor, pil_img = _create_data(height, width, device=device)

        if dt == torch.float16 and device == "cpu":
            # skip float16 on CPU case
            return

        if dt is not None:
            tensor = tensor.to(dtype=dt)

        out_pil_img = F.affine(pil_img, angle=0, translate=t, scale=1.0, shear=[0.0, 0.0], interpolation=NEAREST)

        out_tensor = fn(tensor, angle=0, translate=t, scale=1.0, shear=[0.0, 0.0], interpolation=NEAREST)

        if out_tensor.dtype != torch.uint8:
            out_tensor = out_tensor.to(torch.uint8)

        _assert_equal_tensor_to_pil(out_tensor, out_pil_img)

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
    @pytest.mark.parametrize("device", cpu_and_gpu())
    @pytest.mark.parametrize("height, width", [(26, 26), (32, 26)])
    @pytest.mark.parametrize("dt", ALL_DTYPES)
    @pytest.mark.parametrize(
        "a, t, s, sh, f",
        [
            (45.5, [5, 6], 1.0, [0.0, 0.0], None),
            (33, (5, -4), 1.0, [0.0, 0.0], [0, 0, 0]),
            (45, [-5, 4], 1.2, [0.0, 0.0], (1, 2, 3)),
            (33, (-4, -8), 2.0, [0.0, 0.0], [255, 255, 255]),
            (
                85,
                (10, -10),
                0.7,
                [0.0, 0.0],
                [
                    1,
                ],
            ),
            (
                0,
                [0, 0],
                1.0,
                [
                    35.0,
                ],
                (2.0,),
            ),
            (-25, [0, 0], 1.2, [0.0, 15.0], None),
            (-45, [-10, 0], 0.7, [2.0, 5.0], None),
            (-45, [-10, -10], 1.2, [4.0, 5.0], None),
            (-90, [0, 0], 1.0, [0.0, 0.0], None),
        ],
    )
    @pytest.mark.parametrize("fn", [F.affine, scripted_affine])
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
    def test_all_ops(self, device, height, width, dt, a, t, s, sh, f, fn):
        # 4) Test rotation + translation + scale + shear
        tensor, pil_img = _create_data(height, width, device=device)

        if dt == torch.float16 and device == "cpu":
            # skip float16 on CPU case
            return

        if dt is not None:
            tensor = tensor.to(dtype=dt)

        f_pil = int(f[0]) if f is not None and len(f) == 1 else f
        out_pil_img = F.affine(pil_img, angle=a, translate=t, scale=s, shear=sh, interpolation=NEAREST, fill=f_pil)
        out_pil_tensor = torch.from_numpy(np.array(out_pil_img).transpose((2, 0, 1)))

        out_tensor = fn(tensor, angle=a, translate=t, scale=s, shear=sh, interpolation=NEAREST, fill=f).cpu()

        if out_tensor.dtype != torch.uint8:
            out_tensor = out_tensor.to(torch.uint8)

        num_diff_pixels = (out_tensor != out_pil_tensor).sum().item() / 3.0
        ratio_diff_pixels = num_diff_pixels / out_tensor.shape[-1] / out_tensor.shape[-2]
        # Tolerance : less than 5% (cpu), 6% (cuda) of different pixels
        tol = 0.06 if device == "cuda" else 0.05
361
        assert ratio_diff_pixels < tol
362

363
364
    @pytest.mark.parametrize("device", cpu_and_gpu())
    @pytest.mark.parametrize("dt", ALL_DTYPES)
365
366
367
368
369
370
371
372
373
    def test_batches(self, device, dt):
        if dt == torch.float16 and device == "cpu":
            # skip float16 on CPU case
            return

        batch_tensors = _create_data_batch(26, 36, num_samples=4, device=device)
        if dt is not None:
            batch_tensors = batch_tensors.to(dtype=dt)

374
        _test_fn_on_batch(batch_tensors, F.affine, angle=-43, translate=[-3, 4], scale=1.2, shear=[4.0, 5.0])
375

376
    @pytest.mark.parametrize("device", cpu_and_gpu())
377
378
379
380
    def test_warnings(self, device):
        tensor, pil_img = _create_data(26, 26, device=device)

        # assert deprecation warning and non-BC
381
382
383
384
385
386
387
        with pytest.warns(
            UserWarning,
            match=re.escape(
                "The parameter 'resample' is deprecated since 0.12 and will be removed in 0.14. "
                "Please use 'interpolation' instead."
            ),
        ):
388
389
390
391
392
            res1 = F.affine(tensor, 45, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], resample=2)
            res2 = F.affine(tensor, 45, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=BILINEAR)
            assert_equal(res1, res2)

        # assert changed type warning
393
394
395
396
397
398
399
        with pytest.warns(
            UserWarning,
            match=re.escape(
                "Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. "
                "Please use InterpolationMode enum."
            ),
        ):
400
401
402
403
            res1 = F.affine(tensor, 45, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=2)
            res2 = F.affine(tensor, 45, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], interpolation=BILINEAR)
            assert_equal(res1, res2)

404
405
406
407
408
409
410
        with pytest.warns(
            UserWarning,
            match=re.escape(
                "The parameter 'fillcolor' is deprecated since 0.12 and will be removed in 0.14. "
                "Please use 'fill' instead."
            ),
        ):
411
412
413
414
415
416
            res1 = F.affine(pil_img, 45, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], fillcolor=10)
            res2 = F.affine(pil_img, 45, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], fill=10)
            # we convert the PIL images to numpy as assert_equal doesn't work on PIL images.
            assert_equal(np.asarray(res1), np.asarray(res2))


417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
def _get_data_dims_and_points_for_perspective():
    # Ideally we would parametrize independently over data dims and points, but
    # we want to tests on some points that also depend on the data dims.
    # Pytest doesn't support covariant parametrization, so we do it somewhat manually here.

    data_dims = [(26, 34), (26, 26)]
    points = [
        [[[0, 0], [33, 0], [33, 25], [0, 25]], [[3, 2], [32, 3], [30, 24], [2, 25]]],
        [[[3, 2], [32, 3], [30, 24], [2, 25]], [[0, 0], [33, 0], [33, 25], [0, 25]]],
        [[[3, 2], [32, 3], [30, 24], [2, 25]], [[5, 5], [30, 3], [33, 19], [4, 25]]],
    ]

    dims_and_points = list(itertools.product(data_dims, points))

    # up to here, we could just have used 2 @parametrized.
    # Down below is the covarariant part as the points depend on the data dims.

    n = 10
    for dim in data_dims:
436
        points += [(dim, T.RandomPerspective.get_params(dim[1], dim[0], i / n)) for i in range(n)]
437
438
439
    return dims_and_points


440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dims_and_points", _get_data_dims_and_points_for_perspective())
@pytest.mark.parametrize("dt", [None, torch.float32, torch.float64, torch.float16])
@pytest.mark.parametrize(
    "fill",
    (
        None,
        [0, 0, 0],
        [1, 2, 3],
        [255, 255, 255],
        [
            1,
        ],
        (2.0,),
    ),
)
@pytest.mark.parametrize("fn", [F.perspective, torch.jit.script(F.perspective)])
Nicolas Hug's avatar
Nicolas Hug committed
457
def test_perspective_pil_vs_tensor(device, dims_and_points, dt, fill, fn):
458
459
460
461
462
463
464

    if dt == torch.float16 and device == "cpu":
        # skip float16 on CPU case
        return

    data_dims, (spoints, epoints) = dims_and_points

Nicolas Hug's avatar
Nicolas Hug committed
465
    tensor, pil_img = _create_data(*data_dims, device=device)
466
467
468
469
470
    if dt is not None:
        tensor = tensor.to(dtype=dt)

    interpolation = NEAREST
    fill_pil = int(fill[0]) if fill is not None and len(fill) == 1 else fill
471
472
473
    out_pil_img = F.perspective(
        pil_img, startpoints=spoints, endpoints=epoints, interpolation=interpolation, fill=fill_pil
    )
474
475
476
477
478
479
480
481
482
483
484
485
    out_pil_tensor = torch.from_numpy(np.array(out_pil_img).transpose((2, 0, 1)))
    out_tensor = fn(tensor, startpoints=spoints, endpoints=epoints, interpolation=interpolation, fill=fill).cpu()

    if out_tensor.dtype != torch.uint8:
        out_tensor = out_tensor.to(torch.uint8)

    num_diff_pixels = (out_tensor != out_pil_tensor).sum().item() / 3.0
    ratio_diff_pixels = num_diff_pixels / out_tensor.shape[-1] / out_tensor.shape[-2]
    # Tolerance : less than 5% of different pixels
    assert ratio_diff_pixels < 0.05


486
487
488
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dims_and_points", _get_data_dims_and_points_for_perspective())
@pytest.mark.parametrize("dt", [None, torch.float32, torch.float64, torch.float16])
Nicolas Hug's avatar
Nicolas Hug committed
489
def test_perspective_batch(device, dims_and_points, dt):
490
491
492
493
494
495
496

    if dt == torch.float16 and device == "cpu":
        # skip float16 on CPU case
        return

    data_dims, (spoints, epoints) = dims_and_points

Nicolas Hug's avatar
Nicolas Hug committed
497
    batch_tensors = _create_data_batch(*data_dims, num_samples=4, device=device)
498
499
500
501
502
503
    if dt is not None:
        batch_tensors = batch_tensors.to(dtype=dt)

    # Ignore the equivalence between scripted and regular function on float16 cuda. The pixels at
    # the border may be entirely different due to small rounding errors.
    scripted_fn_atol = -1 if (dt == torch.float16 and device == "cuda") else 1e-8
Nicolas Hug's avatar
Nicolas Hug committed
504
    _test_fn_on_batch(
505
506
507
508
509
510
        batch_tensors,
        F.perspective,
        scripted_fn_atol=scripted_fn_atol,
        startpoints=spoints,
        endpoints=epoints,
        interpolation=NEAREST,
511
512
513
    )


Nicolas Hug's avatar
Nicolas Hug committed
514
def test_perspective_interpolation_warning():
515
516
517
518
    # assert changed type warning
    spoints = [[0, 0], [33, 0], [33, 25], [0, 25]]
    epoints = [[3, 2], [32, 3], [30, 24], [2, 25]]
    tensor = torch.randint(0, 256, (3, 26, 26))
519
520
521
522
523
524
525
    with pytest.warns(
        UserWarning,
        match=re.escape(
            "Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. "
            "Please use InterpolationMode enum."
        ),
    ):
526
527
        res1 = F.perspective(tensor, startpoints=spoints, endpoints=epoints, interpolation=2)
        res2 = F.perspective(tensor, startpoints=spoints, endpoints=epoints, interpolation=BILINEAR)
Nicolas Hug's avatar
Nicolas Hug committed
528
        assert_equal(res1, res2)
529
530


531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dt", [None, torch.float32, torch.float64, torch.float16])
@pytest.mark.parametrize(
    "size",
    [
        32,
        26,
        [
            32,
        ],
        [32, 32],
        (32, 32),
        [26, 35],
    ],
)
@pytest.mark.parametrize("max_size", [None, 34, 40, 1000])
@pytest.mark.parametrize("interpolation", [BILINEAR, BICUBIC, NEAREST])
Nicolas Hug's avatar
Nicolas Hug committed
548
def test_resize(device, dt, size, max_size, interpolation):
549
550
551
552
553
554
555
556
557
558

    if dt == torch.float16 and device == "cpu":
        # skip float16 on CPU case
        return

    if max_size is not None and isinstance(size, Sequence) and len(size) != 1:
        return  # unsupported

    torch.manual_seed(12)
    script_fn = torch.jit.script(F.resize)
Nicolas Hug's avatar
Nicolas Hug committed
559
560
    tensor, pil_img = _create_data(26, 36, device=device)
    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
561
562
563
564
565
566
567
568
569
570
571

    if dt is not None:
        # This is a trivial cast to float of uint8 data to test all cases
        tensor = tensor.to(dt)
        batch_tensors = batch_tensors.to(dt)

    resized_tensor = F.resize(tensor, size=size, interpolation=interpolation, max_size=max_size)
    resized_pil_img = F.resize(pil_img, size=size, interpolation=interpolation, max_size=max_size)

    assert resized_tensor.size()[1:] == resized_pil_img.size[::-1]

572
573
574
    if interpolation not in [
        NEAREST,
    ]:
575
576
577
578
579
580
581
582
583
        # We can not check values if mode = NEAREST, as results are different
        # E.g. resized_tensor  = [[a, a, b, c, d, d, e, ...]]
        # E.g. resized_pil_img = [[a, b, c, c, d, e, f, ...]]
        resized_tensor_f = resized_tensor
        # we need to cast to uint8 to compare with PIL image
        if resized_tensor_f.dtype == torch.uint8:
            resized_tensor_f = resized_tensor_f.to(torch.float)

        # Pay attention to high tolerance for MAE
Nicolas Hug's avatar
Nicolas Hug committed
584
        _assert_approx_equal_tensor_to_pil(resized_tensor_f, resized_pil_img, tol=8.0)
585
586

    if isinstance(size, int):
587
588
589
        script_size = [
            size,
        ]
590
591
592
    else:
        script_size = size

593
    resize_result = script_fn(tensor, size=script_size, interpolation=interpolation, max_size=max_size)
594
595
    assert_equal(resized_tensor, resize_result)

596
    _test_fn_on_batch(batch_tensors, F.resize, size=script_size, interpolation=interpolation, max_size=max_size)
597
598


599
@pytest.mark.parametrize("device", cpu_and_gpu())
Nicolas Hug's avatar
Nicolas Hug committed
600
def test_resize_asserts(device):
601

Nicolas Hug's avatar
Nicolas Hug committed
602
    tensor, pil_img = _create_data(26, 36, device=device)
603
604

    # assert changed type warning
605
606
607
608
609
610
611
    with pytest.warns(
        UserWarning,
        match=re.escape(
            "Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. "
            "Please use InterpolationMode enum."
        ),
    ):
612
613
614
615
616
617
618
619
620
621
622
623
624
        res1 = F.resize(tensor, size=32, interpolation=2)

    res2 = F.resize(tensor, size=32, interpolation=BILINEAR)
    assert_equal(res1, res2)

    for img in (tensor, pil_img):
        exp_msg = "max_size should only be passed if size specifies the length of the smaller edge"
        with pytest.raises(ValueError, match=exp_msg):
            F.resize(img, size=(32, 34), max_size=35)
        with pytest.raises(ValueError, match="max_size = 32 must be strictly greater"):
            F.resize(img, size=32, max_size=32)


625
626
627
628
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dt", [None, torch.float32, torch.float64, torch.float16])
@pytest.mark.parametrize("size", [[96, 72], [96, 420], [420, 72]])
@pytest.mark.parametrize("interpolation", [BILINEAR, BICUBIC])
Nicolas Hug's avatar
Nicolas Hug committed
629
def test_resize_antialias(device, dt, size, interpolation):
630
631
632
633
634

    if dt == torch.float16 and device == "cpu":
        # skip float16 on CPU case
        return

635
    torch.manual_seed(12)
636
    script_fn = torch.jit.script(F.resize)
Nicolas Hug's avatar
Nicolas Hug committed
637
    tensor, pil_img = _create_data(320, 290, device=device)
638
639
640
641
642
643
644
645

    if dt is not None:
        # This is a trivial cast to float of uint8 data to test all cases
        tensor = tensor.to(dt)

    resized_tensor = F.resize(tensor, size=size, interpolation=interpolation, antialias=True)
    resized_pil_img = F.resize(pil_img, size=size, interpolation=interpolation)

Nicolas Hug's avatar
Nicolas Hug committed
646
    assert resized_tensor.size()[1:] == resized_pil_img.size[::-1]
647
648
649
650
651
652

    resized_tensor_f = resized_tensor
    # we need to cast to uint8 to compare with PIL image
    if resized_tensor_f.dtype == torch.uint8:
        resized_tensor_f = resized_tensor_f.to(torch.float)

653
    _assert_approx_equal_tensor_to_pil(resized_tensor_f, resized_pil_img, tol=0.5, msg=f"{size}, {interpolation}, {dt}")
654
655
656
657
658
659
660
661
662

    accepted_tol = 1.0 + 1e-5
    if interpolation == BICUBIC:
        # this overall mean value to make the tests pass
        # High value is mostly required for test cases with
        # downsampling and upsampling where we can not exactly
        # match PIL implementation.
        accepted_tol = 15.0

Nicolas Hug's avatar
Nicolas Hug committed
663
    _assert_approx_equal_tensor_to_pil(
664
        resized_tensor_f, resized_pil_img, tol=accepted_tol, agg_method="max", msg=f"{size}, {interpolation}, {dt}"
665
666
667
    )

    if isinstance(size, int):
668
669
670
        script_size = [
            size,
        ]
671
672
673
674
    else:
        script_size = size

    resize_result = script_fn(tensor, size=script_size, interpolation=interpolation, antialias=True)
Nicolas Hug's avatar
Nicolas Hug committed
675
    assert_equal(resized_tensor, resize_result)
676
677


678
@needs_cuda
679
@pytest.mark.parametrize("interpolation", [BILINEAR, BICUBIC])
Nicolas Hug's avatar
Nicolas Hug committed
680
def test_assert_resize_antialias(interpolation):
681
682

    # Checks implementation on very large scales
683
    # and catch TORCH_CHECK inside PyTorch implementation
684
    torch.manual_seed(12)
685
    tensor, _ = _create_data(1000, 1000, device="cuda")
686

687
688
689
    # Error message is not yet updated in pytorch nightly
    # with pytest.raises(RuntimeError, match=r"Provided interpolation parameters can not be handled"):
    with pytest.raises(RuntimeError, match=r"Too much shared memory required"):
690
691
692
        F.resize(tensor, size=(5, 5), interpolation=interpolation, antialias=True)


693
694
695
696
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dt", [torch.float32, torch.float64, torch.float16])
@pytest.mark.parametrize("size", [[10, 7], [10, 42], [42, 7]])
@pytest.mark.parametrize("interpolation", [BILINEAR, BICUBIC])
697
def test_interpolate_antialias_backward(device, dt, size, interpolation):
698
699
700
701
702
703

    if dt == torch.float16 and device == "cpu":
        # skip float16 on CPU case
        return

    torch.manual_seed(12)
704
    x = (torch.rand(1, 32, 29, 3, dtype=torch.double, device=device).permute(0, 3, 1, 2).requires_grad_(True),)
705
706
    resize = partial(F.resize, size=size, interpolation=interpolation, antialias=True)
    assert torch.autograd.gradcheck(resize, x, eps=1e-8, atol=1e-6, rtol=1e-6, fast_mode=False)
707

708
    x = (torch.rand(1, 3, 32, 29, dtype=torch.double, device=device, requires_grad=True),)
709
    assert torch.autograd.gradcheck(resize, x, eps=1e-8, atol=1e-6, rtol=1e-6, fast_mode=False)
710
711


712
713
714
def check_functional_vs_PIL_vs_scripted(
    fn, fn_pil, fn_t, config, device, dtype, channels=3, tol=2.0 + 1e-10, agg_method="max"
):
715
716
717

    script_fn = torch.jit.script(fn)
    torch.manual_seed(15)
718
719
    tensor, pil_img = _create_data(26, 34, channels=channels, device=device)
    batch_tensors = _create_data_batch(16, 18, num_samples=4, channels=channels, device=device)
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737

    if dtype is not None:
        tensor = F.convert_image_dtype(tensor, dtype)
        batch_tensors = F.convert_image_dtype(batch_tensors, dtype)

    out_fn_t = fn_t(tensor, **config)
    out_pil = fn_pil(pil_img, **config)
    out_scripted = script_fn(tensor, **config)
    assert out_fn_t.dtype == out_scripted.dtype
    assert out_fn_t.size()[1:] == out_pil.size[::-1]

    rbg_tensor = out_fn_t

    if out_fn_t.dtype != torch.uint8:
        rbg_tensor = F.convert_image_dtype(out_fn_t, torch.uint8)

    # Check that max difference does not exceed 2 in [0, 255] range
    # Exact matching is not possible due to incompatibility convert_image_dtype and PIL results
Nicolas Hug's avatar
Nicolas Hug committed
738
    _assert_approx_equal_tensor_to_pil(rbg_tensor.float(), out_pil, tol=tol, agg_method=agg_method)
739
740
741
742
743
744
745

    atol = 1e-6
    if out_fn_t.dtype == torch.uint8 and "cuda" in torch.device(device).type:
        atol = 1.0
    assert out_fn_t.allclose(out_scripted, atol=atol)

    # FIXME: fn will be scripted again in _test_fn_on_batch. We could avoid that.
Nicolas Hug's avatar
Nicolas Hug committed
746
    _test_fn_on_batch(batch_tensors, fn, scripted_fn_atol=atol, **config)
747
748


749
750
751
752
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("config", [{"brightness_factor": f} for f in (0.1, 0.5, 1.0, 1.34, 2.5)])
@pytest.mark.parametrize("channels", [1, 3])
753
def test_adjust_brightness(device, dtype, config, channels):
754
755
756
757
758
759
760
    check_functional_vs_PIL_vs_scripted(
        F.adjust_brightness,
        F_pil.adjust_brightness,
        F_t.adjust_brightness,
        config,
        device,
        dtype,
761
        channels,
762
763
764
    )


765
766
767
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("channels", [1, 3])
768
def test_invert(device, dtype, channels):
769
    check_functional_vs_PIL_vs_scripted(
770
        F.invert, F_pil.invert, F_t.invert, {}, device, dtype, channels, tol=1.0, agg_method="max"
771
772
773
    )


774
775
776
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("config", [{"bits": bits} for bits in range(0, 8)])
@pytest.mark.parametrize("channels", [1, 3])
777
def test_posterize(device, config, channels):
778
779
780
781
782
783
784
    check_functional_vs_PIL_vs_scripted(
        F.posterize,
        F_pil.posterize,
        F_t.posterize,
        config,
        device,
        dtype=None,
785
        channels=channels,
786
787
788
789
790
        tol=1.0,
        agg_method="max",
    )


791
792
793
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("config", [{"threshold": threshold} for threshold in [0, 64, 128, 192, 255]])
@pytest.mark.parametrize("channels", [1, 3])
794
def test_solarize1(device, config, channels):
795
796
797
798
799
800
801
    check_functional_vs_PIL_vs_scripted(
        F.solarize,
        F_pil.solarize,
        F_t.solarize,
        config,
        device,
        dtype=None,
802
        channels=channels,
803
804
805
806
807
        tol=1.0,
        agg_method="max",
    )


808
809
810
811
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (torch.float32, torch.float64))
@pytest.mark.parametrize("config", [{"threshold": threshold} for threshold in [0.0, 0.25, 0.5, 0.75, 1.0]])
@pytest.mark.parametrize("channels", [1, 3])
812
def test_solarize2(device, dtype, config, channels):
813
814
815
816
817
818
819
    check_functional_vs_PIL_vs_scripted(
        F.solarize,
        lambda img, threshold: F_pil.solarize(img, 255 * threshold),
        F_t.solarize,
        config,
        device,
        dtype,
820
        channels,
821
822
823
824
825
        tol=1.0,
        agg_method="max",
    )


puhuk's avatar
puhuk committed
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("threshold", [0.0, 0.25, 0.5, 0.75, 1.0])
def test_solarize_threshold1_bound(threshold, device):
    img = torch.rand((3, 12, 23)).to(device)
    F_t.solarize(img, threshold)


@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("threshold", [1.5])
def test_solarize_threshold1_upper_bound(threshold, device):
    img = torch.rand((3, 12, 23)).to(device)
    with pytest.raises(TypeError, match="Threshold should be less than bound of img."):
        F_t.solarize(img, threshold)


@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("threshold", [0, 64, 128, 192, 255])
def test_solarize_threshold2_bound(threshold, device):
    img = torch.randint(0, 256, (3, 12, 23)).to(device)
    F_t.solarize(img, threshold)


@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("threshold", [260])
def test_solarize_threshold2_upper_bound(threshold, device):
    img = torch.randint(0, 256, (3, 12, 23)).to(device)
    with pytest.raises(TypeError, match="Threshold should be less than bound of img."):
        F_t.solarize(img, threshold)


856
857
858
859
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("config", [{"sharpness_factor": f} for f in [0.2, 0.5, 1.0, 1.5, 2.0]])
@pytest.mark.parametrize("channels", [1, 3])
860
def test_adjust_sharpness(device, dtype, config, channels):
861
862
863
864
865
866
867
    check_functional_vs_PIL_vs_scripted(
        F.adjust_sharpness,
        F_pil.adjust_sharpness,
        F_t.adjust_sharpness,
        config,
        device,
        dtype,
868
        channels,
869
870
871
    )


872
873
874
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("channels", [1, 3])
875
def test_autocontrast(device, dtype, channels):
876
    check_functional_vs_PIL_vs_scripted(
877
        F.autocontrast, F_pil.autocontrast, F_t.autocontrast, {}, device, dtype, channels, tol=1.0, agg_method="max"
878
879
880
    )


881
882
883
884
885
886
887
888
889
890
891
892
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("channels", [1, 3])
def test_autocontrast_equal_minmax(device, dtype, channels):
    a = _create_data_batch(32, 32, num_samples=1, channels=channels, device=device)
    a = a / 2.0 + 0.3
    assert (F.autocontrast(a)[0] == F.autocontrast(a[0])).all()

    a[0, 0] = 0.7
    assert (F.autocontrast(a)[0] == F.autocontrast(a[0])).all()


893
894
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("channels", [1, 3])
895
def test_equalize(device, channels):
896
    torch.use_deterministic_algorithms(False)
897
898
899
900
901
902
903
    check_functional_vs_PIL_vs_scripted(
        F.equalize,
        F_pil.equalize,
        F_t.equalize,
        {},
        device,
        dtype=None,
904
        channels=channels,
905
906
907
908
909
        tol=1.0,
        agg_method="max",
    )


910
911
912
913
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("config", [{"contrast_factor": f} for f in [0.2, 0.5, 1.0, 1.5, 2.0]])
@pytest.mark.parametrize("channels", [1, 3])
914
def test_adjust_contrast(device, dtype, config, channels):
915
    check_functional_vs_PIL_vs_scripted(
916
        F.adjust_contrast, F_pil.adjust_contrast, F_t.adjust_contrast, config, device, dtype, channels
917
918
919
    )


920
921
922
923
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("config", [{"saturation_factor": f} for f in [0.5, 0.75, 1.0, 1.5, 2.0]])
@pytest.mark.parametrize("channels", [1, 3])
924
def test_adjust_saturation(device, dtype, config, channels):
925
    check_functional_vs_PIL_vs_scripted(
926
        F.adjust_saturation, F_pil.adjust_saturation, F_t.adjust_saturation, config, device, dtype, channels
927
928
929
    )


930
931
932
933
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("config", [{"hue_factor": f} for f in [-0.45, -0.25, 0.0, 0.25, 0.45]])
@pytest.mark.parametrize("channels", [1, 3])
934
def test_adjust_hue(device, dtype, config, channels):
935
    check_functional_vs_PIL_vs_scripted(
936
        F.adjust_hue, F_pil.adjust_hue, F_t.adjust_hue, config, device, dtype, channels, tol=16.1, agg_method="max"
937
938
939
    )


940
941
942
943
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dtype", (None, torch.float32, torch.float64))
@pytest.mark.parametrize("config", [{"gamma": g1, "gain": g2} for g1, g2 in zip([0.8, 1.0, 1.2], [0.7, 1.0, 1.3])])
@pytest.mark.parametrize("channels", [1, 3])
944
def test_adjust_gamma(device, dtype, config, channels):
945
946
947
948
949
950
951
    check_functional_vs_PIL_vs_scripted(
        F.adjust_gamma,
        F_pil.adjust_gamma,
        F_t.adjust_gamma,
        config,
        device,
        dtype,
952
        channels,
953
954
955
    )


956
957
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("dt", [None, torch.float32, torch.float64, torch.float16])
958
@pytest.mark.parametrize("pad", [2, [3], [0, 3], (3, 3), [4, 2, 4, 3]])
959
960
961
962
963
@pytest.mark.parametrize(
    "config",
    [
        {"padding_mode": "constant", "fill": 0},
        {"padding_mode": "constant", "fill": 10},
964
        {"padding_mode": "constant", "fill": 20.2},
965
966
967
968
969
        {"padding_mode": "edge"},
        {"padding_mode": "reflect"},
        {"padding_mode": "symmetric"},
    ],
)
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
def test_pad(device, dt, pad, config):
    script_fn = torch.jit.script(F.pad)
    tensor, pil_img = _create_data(7, 8, device=device)
    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)

    if dt == torch.float16 and device == "cpu":
        # skip float16 on CPU case
        return

    if dt is not None:
        # This is a trivial cast to float of uint8 data to test all cases
        tensor = tensor.to(dt)
        batch_tensors = batch_tensors.to(dt)

    pad_tensor = F_t.pad(tensor, pad, **config)
    pad_pil_img = F_pil.pad(pil_img, pad, **config)

    pad_tensor_8b = pad_tensor
    # we need to cast to uint8 to compare with PIL image
    if pad_tensor_8b.dtype != torch.uint8:
        pad_tensor_8b = pad_tensor_8b.to(torch.uint8)

992
    _assert_equal_tensor_to_pil(pad_tensor_8b, pad_pil_img, msg=f"{pad}, {config}")
993
994

    if isinstance(pad, int):
995
996
997
        script_pad = [
            pad,
        ]
998
999
1000
    else:
        script_pad = pad
    pad_tensor_script = script_fn(tensor, script_pad, **config)
1001
    assert_equal(pad_tensor, pad_tensor_script, msg=f"{pad}, {config}")
1002
1003
1004
1005

    _test_fn_on_batch(batch_tensors, F.pad, padding=script_pad, **config)


1006
1007
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("mode", [NEAREST, BILINEAR, BICUBIC])
1008
1009
1010
1011
1012
1013
def test_resized_crop(device, mode):
    # test values of F.resized_crop in several cases:
    # 1) resize to the same size, crop to the same size => should be identity
    tensor, _ = _create_data(26, 36, device=device)

    out_tensor = F.resized_crop(tensor, top=0, left=0, height=26, width=36, size=[26, 36], interpolation=mode)
1014
    assert_equal(tensor, out_tensor, msg=f"{out_tensor[0, :5, :5]} vs {tensor[0, :5, :5]}")
1015
1016
1017
1018
1019
1020
1021
1022

    # 2) resize by half and crop a TL corner
    tensor, _ = _create_data(26, 36, device=device)
    out_tensor = F.resized_crop(tensor, top=0, left=0, height=20, width=30, size=[10, 15], interpolation=NEAREST)
    expected_out_tensor = tensor[:, :20:2, :30:2]
    assert_equal(
        expected_out_tensor,
        out_tensor,
1023
        msg=f"{expected_out_tensor[0, :10, :10]} vs {out_tensor[0, :10, :10]}",
1024
1025
1026
1027
1028
1029
1030
1031
    )

    batch_tensors = _create_data_batch(26, 36, num_samples=4, device=device)
    _test_fn_on_batch(
        batch_tensors, F.resized_crop, top=1, left=2, height=20, width=30, size=[10, 15], interpolation=NEAREST
    )


1032
1033
1034
1035
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize(
    "func, args",
    [
1036
        (F_t.get_dimensions, ()),
1037
        (F_t.get_image_size, ()),
1038
        (F_t.get_image_num_channels, ()),
1039
1040
1041
1042
1043
1044
1045
        (F_t.vflip, ()),
        (F_t.hflip, ()),
        (F_t.crop, (1, 2, 4, 5)),
        (F_t.adjust_brightness, (0.0,)),
        (F_t.adjust_contrast, (1.0,)),
        (F_t.adjust_hue, (-0.5,)),
        (F_t.adjust_saturation, (2.0,)),
1046
        (F_t.pad, ([2], 2, "constant")),
1047
        (F_t.resize, ([10, 11],)),
1048
        (F_t.perspective, ([0.2])),
1049
1050
1051
1052
1053
1054
1055
1056
1057
        (F_t.gaussian_blur, ((2, 2), (0.7, 0.5))),
        (F_t.invert, ()),
        (F_t.posterize, (0,)),
        (F_t.solarize, (0.3,)),
        (F_t.adjust_sharpness, (0.3,)),
        (F_t.autocontrast, ()),
        (F_t.equalize, ()),
    ],
)
1058
1059
1060
1061
1062
1063
1064
def test_assert_image_tensor(device, func, args):
    shape = (100,)
    tensor = torch.rand(*shape, dtype=torch.float, device=device)
    with pytest.raises(Exception, match=r"Tensor is not a torch image."):
        func(tensor, *args)


1065
@pytest.mark.parametrize("device", cpu_and_gpu())
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
def test_vflip(device):
    script_vflip = torch.jit.script(F.vflip)

    img_tensor, pil_img = _create_data(16, 18, device=device)
    vflipped_img = F.vflip(img_tensor)
    vflipped_pil_img = F.vflip(pil_img)
    _assert_equal_tensor_to_pil(vflipped_img, vflipped_pil_img)

    # scriptable function test
    vflipped_img_script = script_vflip(img_tensor)
    assert_equal(vflipped_img, vflipped_img_script)

    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
    _test_fn_on_batch(batch_tensors, F.vflip)


1082
@pytest.mark.parametrize("device", cpu_and_gpu())
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
def test_hflip(device):
    script_hflip = torch.jit.script(F.hflip)

    img_tensor, pil_img = _create_data(16, 18, device=device)
    hflipped_img = F.hflip(img_tensor)
    hflipped_pil_img = F.hflip(pil_img)
    _assert_equal_tensor_to_pil(hflipped_img, hflipped_pil_img)

    # scriptable function test
    hflipped_img_script = script_hflip(img_tensor)
    assert_equal(hflipped_img, hflipped_img_script)

    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
    _test_fn_on_batch(batch_tensors, F.hflip)


1099
1100
1101
1102
1103
1104
1105
1106
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize(
    "top, left, height, width",
    [
        (1, 2, 4, 5),  # crop inside top-left corner
        (2, 12, 3, 4),  # crop inside top-right corner
        (8, 3, 5, 6),  # crop inside bottom-left corner
        (8, 11, 4, 3),  # crop inside bottom-right corner
1107
1108
        (50, 50, 10, 10),  # crop outside the image
        (-50, -50, 10, 10),  # crop outside the image
1109
1110
    ],
)
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
def test_crop(device, top, left, height, width):
    script_crop = torch.jit.script(F.crop)

    img_tensor, pil_img = _create_data(16, 18, device=device)

    pil_img_cropped = F.crop(pil_img, top, left, height, width)

    img_tensor_cropped = F.crop(img_tensor, top, left, height, width)
    _assert_equal_tensor_to_pil(img_tensor_cropped, pil_img_cropped)

    img_tensor_cropped = script_crop(img_tensor, top, left, height, width)
    _assert_equal_tensor_to_pil(img_tensor_cropped, pil_img_cropped)

    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
    _test_fn_on_batch(batch_tensors, F.crop, top=top, left=left, height=height, width=width)


1128
1129
1130
1131
1132
1133
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("image_size", ("small", "large"))
@pytest.mark.parametrize("dt", [None, torch.float32, torch.float64, torch.float16])
@pytest.mark.parametrize("ksize", [(3, 3), [3, 5], (23, 23)])
@pytest.mark.parametrize("sigma", [[0.5, 0.5], (0.5, 0.5), (0.8, 0.8), (1.7, 1.7)])
@pytest.mark.parametrize("fn", [F.gaussian_blur, torch.jit.script(F.gaussian_blur)])
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
def test_gaussian_blur(device, image_size, dt, ksize, sigma, fn):

    # true_cv2_results = {
    #     # np_img = np.arange(3 * 10 * 12, dtype="uint8").reshape((10, 12, 3))
    #     # cv2.GaussianBlur(np_img, ksize=(3, 3), sigmaX=0.8)
    #     "3_3_0.8": ...
    #     # cv2.GaussianBlur(np_img, ksize=(3, 3), sigmaX=0.5)
    #     "3_3_0.5": ...
    #     # cv2.GaussianBlur(np_img, ksize=(3, 5), sigmaX=0.8)
    #     "3_5_0.8": ...
    #     # cv2.GaussianBlur(np_img, ksize=(3, 5), sigmaX=0.5)
    #     "3_5_0.5": ...
    #     # np_img2 = np.arange(26 * 28, dtype="uint8").reshape((26, 28))
    #     # cv2.GaussianBlur(np_img2, ksize=(23, 23), sigmaX=1.7)
    #     "23_23_1.7": ...
    # }
1150
    p = os.path.join(os.path.dirname(os.path.abspath(__file__)), "assets", "gaussian_blur_opencv_results.pt")
1151
1152
    true_cv2_results = torch.load(p)

1153
1154
1155
1156
    if image_size == "small":
        tensor = (
            torch.from_numpy(np.arange(3 * 10 * 12, dtype="uint8").reshape((10, 12, 3))).permute(2, 0, 1).to(device)
        )
1157
    else:
1158
        tensor = torch.from_numpy(np.arange(26 * 28, dtype="uint8").reshape((1, 26, 28))).to(device)
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169

    if dt == torch.float16 and device == "cpu":
        # skip float16 on CPU case
        return

    if dt is not None:
        tensor = tensor.to(dtype=dt)

    _ksize = (ksize, ksize) if isinstance(ksize, int) else ksize
    _sigma = sigma[0] if sigma is not None else None
    shape = tensor.shape
1170
    gt_key = f"{shape[-2]}_{shape[-1]}_{shape[-3]}__{_ksize[0]}_{_ksize[1]}_{_sigma}"
1171
1172
1173
    if gt_key not in true_cv2_results:
        return

1174
1175
1176
    true_out = (
        torch.tensor(true_cv2_results[gt_key]).reshape(shape[-2], shape[-1], shape[-3]).permute(2, 0, 1).to(tensor)
    )
1177
1178

    out = fn(tensor, kernel_size=ksize, sigma=sigma)
1179
    torch.testing.assert_close(out, true_out, rtol=0.0, atol=1.0, msg=f"{ksize}, {sigma}")
1180
1181


1182
@pytest.mark.parametrize("device", cpu_and_gpu())
1183
1184
1185
1186
1187
1188
1189
1190
def test_hsv2rgb(device):
    scripted_fn = torch.jit.script(F_t._hsv2rgb)
    shape = (3, 100, 150)
    for _ in range(10):
        hsv_img = torch.rand(*shape, dtype=torch.float, device=device)
        rgb_img = F_t._hsv2rgb(hsv_img)
        ft_img = rgb_img.permute(1, 2, 0).flatten(0, 1)

1191
1192
1193
1194
1195
        (
            h,
            s,
            v,
        ) = hsv_img.unbind(0)
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
        h = h.flatten().cpu().numpy()
        s = s.flatten().cpu().numpy()
        v = v.flatten().cpu().numpy()

        rgb = []
        for h1, s1, v1 in zip(h, s, v):
            rgb.append(colorsys.hsv_to_rgb(h1, s1, v1))
        colorsys_img = torch.tensor(rgb, dtype=torch.float32, device=device)
        torch.testing.assert_close(ft_img, colorsys_img, rtol=0.0, atol=1e-5)

        s_rgb_img = scripted_fn(hsv_img)
        torch.testing.assert_close(rgb_img, s_rgb_img)

    batch_tensors = _create_data_batch(120, 100, num_samples=4, device=device).float()
    _test_fn_on_batch(batch_tensors, F_t._hsv2rgb)


1213
@pytest.mark.parametrize("device", cpu_and_gpu())
1214
1215
1216
1217
1218
1219
1220
1221
def test_rgb2hsv(device):
    scripted_fn = torch.jit.script(F_t._rgb2hsv)
    shape = (3, 150, 100)
    for _ in range(10):
        rgb_img = torch.rand(*shape, dtype=torch.float, device=device)
        hsv_img = F_t._rgb2hsv(rgb_img)
        ft_hsv_img = hsv_img.permute(1, 2, 0).flatten(0, 1)

1222
1223
1224
1225
1226
        (
            r,
            g,
            b,
        ) = rgb_img.unbind(dim=-3)
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
        r = r.flatten().cpu().numpy()
        g = g.flatten().cpu().numpy()
        b = b.flatten().cpu().numpy()

        hsv = []
        for r1, g1, b1 in zip(r, g, b):
            hsv.append(colorsys.rgb_to_hsv(r1, g1, b1))

        colorsys_img = torch.tensor(hsv, dtype=torch.float32, device=device)

        ft_hsv_img_h, ft_hsv_img_sv = torch.split(ft_hsv_img, [1, 2], dim=1)
        colorsys_img_h, colorsys_img_sv = torch.split(colorsys_img, [1, 2], dim=1)

        max_diff_h = ((colorsys_img_h * 2 * math.pi).sin() - (ft_hsv_img_h * 2 * math.pi).sin()).abs().max()
        max_diff_sv = (colorsys_img_sv - ft_hsv_img_sv).abs().max()
        max_diff = max(max_diff_h, max_diff_sv)
        assert max_diff < 1e-5

        s_hsv_img = scripted_fn(rgb_img)
        torch.testing.assert_close(hsv_img, s_hsv_img, rtol=1e-5, atol=1e-7)

    batch_tensors = _create_data_batch(120, 100, num_samples=4, device=device).float()
    _test_fn_on_batch(batch_tensors, F_t._rgb2hsv)


1252
1253
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("num_output_channels", (3, 1))
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
def test_rgb_to_grayscale(device, num_output_channels):
    script_rgb_to_grayscale = torch.jit.script(F.rgb_to_grayscale)

    img_tensor, pil_img = _create_data(32, 34, device=device)

    gray_pil_image = F.rgb_to_grayscale(pil_img, num_output_channels=num_output_channels)
    gray_tensor = F.rgb_to_grayscale(img_tensor, num_output_channels=num_output_channels)

    _assert_approx_equal_tensor_to_pil(gray_tensor.float(), gray_pil_image, tol=1.0 + 1e-10, agg_method="max")

    s_gray_tensor = script_rgb_to_grayscale(img_tensor, num_output_channels=num_output_channels)
    assert_equal(s_gray_tensor, gray_tensor)

    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
    _test_fn_on_batch(batch_tensors, F.rgb_to_grayscale, num_output_channels=num_output_channels)


1271
@pytest.mark.parametrize("device", cpu_and_gpu())
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
def test_center_crop(device):
    script_center_crop = torch.jit.script(F.center_crop)

    img_tensor, pil_img = _create_data(32, 34, device=device)

    cropped_pil_image = F.center_crop(pil_img, [10, 11])

    cropped_tensor = F.center_crop(img_tensor, [10, 11])
    _assert_equal_tensor_to_pil(cropped_tensor, cropped_pil_image)

    cropped_tensor = script_center_crop(img_tensor, [10, 11])
    _assert_equal_tensor_to_pil(cropped_tensor, cropped_pil_image)

    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
    _test_fn_on_batch(batch_tensors, F.center_crop, output_size=[10, 11])


1289
@pytest.mark.parametrize("device", cpu_and_gpu())
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
def test_five_crop(device):
    script_five_crop = torch.jit.script(F.five_crop)

    img_tensor, pil_img = _create_data(32, 34, device=device)

    cropped_pil_images = F.five_crop(pil_img, [10, 11])

    cropped_tensors = F.five_crop(img_tensor, [10, 11])
    for i in range(5):
        _assert_equal_tensor_to_pil(cropped_tensors[i], cropped_pil_images[i])

    cropped_tensors = script_five_crop(img_tensor, [10, 11])
    for i in range(5):
        _assert_equal_tensor_to_pil(cropped_tensors[i], cropped_pil_images[i])

    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
    tuple_transformed_batches = F.five_crop(batch_tensors, [10, 11])
    for i in range(len(batch_tensors)):
        img_tensor = batch_tensors[i, ...]
        tuple_transformed_imgs = F.five_crop(img_tensor, [10, 11])
        assert len(tuple_transformed_imgs) == len(tuple_transformed_batches)

        for j in range(len(tuple_transformed_imgs)):
            true_transformed_img = tuple_transformed_imgs[j]
            transformed_img = tuple_transformed_batches[j][i, ...]
            assert_equal(true_transformed_img, transformed_img)

    # scriptable function test
    s_tuple_transformed_batches = script_five_crop(batch_tensors, [10, 11])
    for transformed_batch, s_transformed_batch in zip(tuple_transformed_batches, s_tuple_transformed_batches):
        assert_equal(transformed_batch, s_transformed_batch)


1323
@pytest.mark.parametrize("device", cpu_and_gpu())
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
def test_ten_crop(device):
    script_ten_crop = torch.jit.script(F.ten_crop)

    img_tensor, pil_img = _create_data(32, 34, device=device)

    cropped_pil_images = F.ten_crop(pil_img, [10, 11])

    cropped_tensors = F.ten_crop(img_tensor, [10, 11])
    for i in range(10):
        _assert_equal_tensor_to_pil(cropped_tensors[i], cropped_pil_images[i])

    cropped_tensors = script_ten_crop(img_tensor, [10, 11])
    for i in range(10):
        _assert_equal_tensor_to_pil(cropped_tensors[i], cropped_pil_images[i])

    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
    tuple_transformed_batches = F.ten_crop(batch_tensors, [10, 11])
    for i in range(len(batch_tensors)):
        img_tensor = batch_tensors[i, ...]
        tuple_transformed_imgs = F.ten_crop(img_tensor, [10, 11])
        assert len(tuple_transformed_imgs) == len(tuple_transformed_batches)

        for j in range(len(tuple_transformed_imgs)):
            true_transformed_img = tuple_transformed_imgs[j]
            transformed_img = tuple_transformed_batches[j][i, ...]
            assert_equal(true_transformed_img, transformed_img)

    # scriptable function test
    s_tuple_transformed_batches = script_ten_crop(batch_tensors, [10, 11])
    for transformed_batch, s_transformed_batch in zip(tuple_transformed_batches, s_tuple_transformed_batches):
        assert_equal(transformed_batch, s_transformed_batch)


1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
def test_elastic_transform_asserts():
    with pytest.raises(TypeError, match="Argument displacement should be a Tensor"):
        _ = F.elastic_transform("abc", displacement=None)

    with pytest.raises(TypeError, match="img should be PIL Image or Tensor"):
        _ = F.elastic_transform("abc", displacement=torch.rand(1))

    img_tensor = torch.rand(1, 3, 32, 24)
    with pytest.raises(ValueError, match="Argument displacement shape should"):
        _ = F.elastic_transform(img_tensor, displacement=torch.rand(1, 2))


1369
1370
1371
1372
1373
@pytest.mark.parametrize("device", cpu_and_gpu())
@pytest.mark.parametrize("interpolation", [NEAREST, BILINEAR, BICUBIC])
@pytest.mark.parametrize("dt", [None, torch.float32, torch.float64, torch.float16])
@pytest.mark.parametrize(
    "fill",
1374
    [None, [255, 255, 255], (2.0,)],
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
)
def test_elastic_transform_consistency(device, interpolation, dt, fill):
    script_elastic_transform = torch.jit.script(F.elastic_transform)
    img_tensor, _ = _create_data(32, 34, device=device)
    # As there is no PIL implementation for elastic_transform,
    # thus we do not run tests tensor vs pillow

    if dt is not None:
        img_tensor = img_tensor.to(dt)

    displacement = T.ElasticTransform.get_params([1.5, 1.5], [2.0, 2.0], [32, 34])
    kwargs = dict(
        displacement=displacement,
        interpolation=interpolation,
        fill=fill,
    )

    out_tensor1 = F.elastic_transform(img_tensor, **kwargs)
    out_tensor2 = script_elastic_transform(img_tensor, **kwargs)
    assert_equal(out_tensor1, out_tensor2)

    batch_tensors = _create_data_batch(16, 18, num_samples=4, device=device)
    displacement = T.ElasticTransform.get_params([1.5, 1.5], [2.0, 2.0], [16, 18])
    kwargs["displacement"] = displacement
    if dt is not None:
        batch_tensors = batch_tensors.to(dt)
    _test_fn_on_batch(batch_tensors, F.elastic_transform, **kwargs)


1404
if __name__ == "__main__":
1405
    pytest.main([__file__])