test_functional_tensor.py 28.5 KB
Newer Older
1
import unittest
2
import colorsys
3
import math
4

vfdev's avatar
vfdev committed
5
import numpy as np
6
from PIL.Image import NEAREST, BILINEAR, BICUBIC
vfdev's avatar
vfdev committed
7
8
9
10
11
12

import torch
import torchvision.transforms as transforms
import torchvision.transforms.functional_tensor as F_t
import torchvision.transforms.functional_pil as F_pil
import torchvision.transforms.functional as F
13

14
from common_utils import TransformsTester
15

16

17
class Tester(TransformsTester):
vfdev's avatar
vfdev committed
18

19
    def _test_vflip(self, device):
20
        script_vflip = torch.jit.script(F_t.vflip)
21
        img_tensor = torch.randn(3, 16, 16, device=device)
22
        img_tensor_clone = img_tensor.clone()
23
24
25
26
        vflipped_img = F_t.vflip(img_tensor)
        vflipped_img_again = F_t.vflip(vflipped_img)
        self.assertEqual(vflipped_img.shape, img_tensor.shape)
        self.assertTrue(torch.equal(img_tensor, vflipped_img_again))
27
        self.assertTrue(torch.equal(img_tensor, img_tensor_clone))
28
29
30
        # scriptable function test
        vflipped_img_script = script_vflip(img_tensor)
        self.assertTrue(torch.equal(vflipped_img, vflipped_img_script))
31

32
33
34
35
36
37
38
39
    def test_vflip_cpu(self):
        self._test_vflip("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_vflip_cuda(self):
        self._test_vflip("cuda")

    def _test_hflip(self, device):
40
        script_hflip = torch.jit.script(F_t.hflip)
41
        img_tensor = torch.randn(3, 16, 16, device=device)
42
        img_tensor_clone = img_tensor.clone()
43
44
45
46
        hflipped_img = F_t.hflip(img_tensor)
        hflipped_img_again = F_t.hflip(hflipped_img)
        self.assertEqual(hflipped_img.shape, img_tensor.shape)
        self.assertTrue(torch.equal(img_tensor, hflipped_img_again))
47
        self.assertTrue(torch.equal(img_tensor, img_tensor_clone))
48
49
50
        # scriptable function test
        hflipped_img_script = script_hflip(img_tensor)
        self.assertTrue(torch.equal(hflipped_img, hflipped_img_script))
51

52
53
54
55
56
57
58
59
60
    def test_hflip_cpu(self):
        self._test_hflip("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_hflip_cuda(self):
        self._test_hflip("cuda")

    def _test_crop(self, device):
        script_crop = torch.jit.script(F.crop)
61

62
        img_tensor, pil_img = self._create_data(16, 18, device=device)
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78

        test_configs = [
            (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
        ]

        for top, left, height, width in test_configs:
            pil_img_cropped = F.crop(pil_img, top, left, height, width)

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

            img_tensor_cropped = script_crop(img_tensor, top, left, height, width)
            self.compareTensorToPIL(img_tensor_cropped, pil_img_cropped)
ekka's avatar
ekka committed
79

80
81
82
83
84
85
86
    def test_crop_cpu(self):
        self._test_crop("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_crop_cuda(self):
        self._test_crop("cuda")

87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
    def test_hsv2rgb(self):
        shape = (3, 100, 150)
        for _ in range(20):
            img = torch.rand(*shape, dtype=torch.float)
            ft_img = F_t._hsv2rgb(img).permute(1, 2, 0).flatten(0, 1)

            h, s, v, = img.unbind(0)
            h = h.flatten().numpy()
            s = s.flatten().numpy()
            v = v.flatten().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)
            max_diff = (ft_img - colorsys_img).abs().max()
            self.assertLess(max_diff, 1e-5)

    def test_rgb2hsv(self):
        shape = (3, 150, 100)
        for _ in range(20):
            img = torch.rand(*shape, dtype=torch.float)
            ft_hsv_img = F_t._rgb2hsv(img).permute(1, 2, 0).flatten(0, 1)

            r, g, b, = img.unbind(0)
            r = r.flatten().numpy()
            g = g.flatten().numpy()
            b = b.flatten().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)

123
124
125
126
127
128
129
            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)

130
131
            self.assertLess(max_diff, 1e-5)

132
    def _test_adjustments(self, device):
133
134
135
136
137
138
139
        script_adjust_brightness = torch.jit.script(F_t.adjust_brightness)
        script_adjust_contrast = torch.jit.script(F_t.adjust_contrast)
        script_adjust_saturation = torch.jit.script(F_t.adjust_saturation)

        fns = ((F.adjust_brightness, F_t.adjust_brightness, script_adjust_brightness),
               (F.adjust_contrast, F_t.adjust_contrast, script_adjust_contrast),
               (F.adjust_saturation, F_t.adjust_saturation, script_adjust_saturation))
140
141
142
143
144
145
146

        for _ in range(20):
            channels = 3
            dims = torch.randint(1, 50, (2,))
            shape = (channels, dims[0], dims[1])

            if torch.randint(0, 2, (1,)) == 0:
147
                img = torch.rand(*shape, dtype=torch.float, device=device)
148
            else:
149
                img = torch.randint(0, 256, shape, dtype=torch.uint8, device=device)
150

151
            factor = 3 * torch.rand(1).item()
152
            img_clone = img.clone()
153
            for f, ft, sft in fns:
154

155
156
                ft_img = ft(img, factor).cpu()
                sft_img = sft(img, factor).cpu()
157
158
                if not img.dtype.is_floating_point:
                    ft_img = ft_img.to(torch.float) / 255
159
                    sft_img = sft_img.to(torch.float) / 255
160
161
162
163
164
165
166
167

                img_pil = transforms.ToPILImage()(img)
                f_img_pil = f(img_pil, factor)
                f_img = transforms.ToTensor()(f_img_pil)

                # F uses uint8 and F_t uses float, so there is a small
                # difference in values caused by (at most 5) truncations.
                max_diff = (ft_img - f_img).abs().max()
168
                max_diff_scripted = (sft_img - f_img).abs().max()
169
                self.assertLess(max_diff, 5 / 255 + 1e-5)
170
                self.assertLess(max_diff_scripted, 5 / 255 + 1e-5)
171
                self.assertTrue(torch.equal(img, img_clone))
172

173
            # test for class interface
174
            f = transforms.ColorJitter(brightness=factor)
175
176
177
            scripted_fn = torch.jit.script(f)
            scripted_fn(img)

178
            f = transforms.ColorJitter(contrast=factor)
179
180
181
            scripted_fn = torch.jit.script(f)
            scripted_fn(img)

182
            f = transforms.ColorJitter(saturation=factor)
183
184
185
186
187
188
189
            scripted_fn = torch.jit.script(f)
            scripted_fn(img)

        f = transforms.ColorJitter(brightness=1)
        scripted_fn = torch.jit.script(f)
        scripted_fn(img)

190
191
192
193
194
195
196
    def test_adjustments(self):
        self._test_adjustments("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_adjustments_cuda(self):
        self._test_adjustments("cuda")

197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
    def _test_rgb_to_grayscale(self, device):
        script_rgb_to_grayscale = torch.jit.script(F.rgb_to_grayscale)

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

        for num_output_channels in (3, 1):
            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)

            if num_output_channels == 1:
                print(gray_tensor.shape)

            self.approxEqualTensorToPIL(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)
            self.assertTrue(s_gray_tensor.equal(gray_tensor))

214
    def test_rgb_to_grayscale(self):
215
216
217
218
219
        self._test_rgb_to_grayscale("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_rgb_to_grayscale_cuda(self):
        self._test_rgb_to_grayscale("cuda")
220

221
    def _test_center_crop(self, device):
222
223
        script_center_crop = torch.jit.script(F.center_crop)

224
        img_tensor, pil_img = self._create_data(32, 34, device=device)
225
226
227
228
229
230
231
232

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

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

        cropped_tensor = script_center_crop(img_tensor, [10, 11])
        self.compareTensorToPIL(cropped_tensor, cropped_pil_image)
233

234
235
236
237
238
239
240
241
    def test_center_crop(self):
        self._test_center_crop("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_center_crop_cuda(self):
        self._test_center_crop("cuda")

    def _test_five_crop(self, device):
242
243
        script_five_crop = torch.jit.script(F.five_crop)

244
        img_tensor, pil_img = self._create_data(32, 34, device=device)
245
246
247
248
249
250
251
252
253
254

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

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

        cropped_tensors = script_five_crop(img_tensor, [10, 11])
        for i in range(5):
            self.compareTensorToPIL(cropped_tensors[i], cropped_pil_images[i])
255

256
257
258
259
260
261
262
263
    def test_five_crop(self):
        self._test_five_crop("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_five_crop_cuda(self):
        self._test_five_crop("cuda")

    def _test_ten_crop(self, device):
264
265
        script_ten_crop = torch.jit.script(F.ten_crop)

266
        img_tensor, pil_img = self._create_data(32, 34, device=device)
267
268
269
270
271
272
273
274
275
276

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

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

        cropped_tensors = script_ten_crop(img_tensor, [10, 11])
        for i in range(10):
            self.compareTensorToPIL(cropped_tensors[i], cropped_pil_images[i])
277

278
279
280
281
282
283
284
285
    def test_ten_crop(self):
        self._test_ten_crop("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_ten_crop_cuda(self):
        self._test_ten_crop("cuda")

    def _test_pad(self, device):
286
        script_fn = torch.jit.script(F_t.pad)
287
        tensor, pil_img = self._create_data(7, 8, device=device)
288
289
290
291
292
293
294
295
296
297
298
299

        for dt in [None, torch.float32, torch.float64]:
            if dt is not None:
                # This is a trivial cast to float of uint8 data to test all cases
                tensor = tensor.to(dt)
            for pad in [2, [3, ], [0, 3], (3, 3), [4, 2, 4, 3]]:
                configs = [
                    {"padding_mode": "constant", "fill": 0},
                    {"padding_mode": "constant", "fill": 10},
                    {"padding_mode": "constant", "fill": 20},
                    {"padding_mode": "edge"},
                    {"padding_mode": "reflect"},
300
                    {"padding_mode": "symmetric"},
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
                ]
                for kwargs in configs:
                    pad_tensor = F_t.pad(tensor, pad, **kwargs)
                    pad_pil_img = F_pil.pad(pil_img, pad, **kwargs)

                    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)

                    self.compareTensorToPIL(pad_tensor_8b, pad_pil_img, msg="{}, {}".format(pad, kwargs))

                    if isinstance(pad, int):
                        script_pad = [pad, ]
                    else:
                        script_pad = pad
                    pad_tensor_script = script_fn(tensor, script_pad, **kwargs)
                    self.assertTrue(pad_tensor.equal(pad_tensor_script), msg="{}, {}".format(pad, kwargs))
319

320
321
322
        with self.assertRaises(ValueError, msg="Padding can not be negative for symmetric padding_mode"):
            F_t.pad(tensor, (-2, -3), padding_mode="symmetric")

323
324
325
326
327
328
329
330
331
332
    def test_pad_cpu(self):
        self._test_pad("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_pad_cuda(self):
        self._test_pad("cuda")

    def _test_adjust_gamma(self, device):
        script_fn = torch.jit.script(F.adjust_gamma)
        tensor, pil_img = self._create_data(26, 36, device=device)
333
334
335
336
337
338
339
340
341
342

        for dt in [torch.float64, torch.float32, None]:

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

            gammas = [0.8, 1.0, 1.2]
            gains = [0.7, 1.0, 1.3]
            for gamma, gain in zip(gammas, gains):

343
344
                adjusted_tensor = F.adjust_gamma(tensor, gamma, gain)
                adjusted_pil = F.adjust_gamma(pil_img, gamma, gain)
345
346
347
348
349
350
351
352
353
354
                scripted_result = script_fn(tensor, gamma, gain)
                self.assertEqual(adjusted_tensor.dtype, scripted_result.dtype)
                self.assertEqual(adjusted_tensor.size()[1:], adjusted_pil.size[::-1])

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

                self.compareTensorToPIL(rbg_tensor, adjusted_pil)

355
356
357
358
359
360
361
362
                self.assertTrue(adjusted_tensor.allclose(scripted_result))

    def test_adjust_gamma_cpu(self):
        self._test_adjust_gamma("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_adjust_gamma_cuda(self):
        self._test_adjust_gamma("cuda")
363

364
    def _test_resize(self, device):
vfdev's avatar
vfdev committed
365
        script_fn = torch.jit.script(F_t.resize)
366
        tensor, pil_img = self._create_data(26, 36, device=device)
vfdev's avatar
vfdev committed
367
368
369
370
371

        for dt in [None, torch.float32, torch.float64]:
            if dt is not None:
                # This is a trivial cast to float of uint8 data to test all cases
                tensor = tensor.to(dt)
372
            for size in [32, 26, [32, ], [32, 32], (32, 32), [26, 35]]:
vfdev's avatar
vfdev committed
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
                for interpolation in [BILINEAR, BICUBIC, NEAREST]:
                    resized_tensor = F_t.resize(tensor, size=size, interpolation=interpolation)
                    resized_pil_img = F_pil.resize(pil_img, size=size, interpolation=interpolation)

                    self.assertEqual(
                        resized_tensor.size()[1:], resized_pil_img.size[::-1], msg="{}, {}".format(size, interpolation)
                    )

                    if interpolation != NEAREST:
                        # 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
                        self.approxEqualTensorToPIL(
                            resized_tensor_f, resized_pil_img, tol=8.0, msg="{}, {}".format(size, interpolation)
                        )

                    if isinstance(size, int):
                        script_size = [size, ]
                    else:
                        script_size = size
399
400
                    resize_result = script_fn(tensor, size=script_size, interpolation=interpolation)
                    self.assertTrue(resized_tensor.equal(resize_result), msg="{}, {}".format(size, interpolation))
vfdev's avatar
vfdev committed
401

402
403
404
405
406
407
408
409
    def test_resize_cpu(self):
        self._test_resize("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_resize_cuda(self):
        self._test_resize("cuda")

    def _test_resized_crop(self, device):
410
411
        # test values of F.resized_crop in several cases:
        # 1) resize to the same size, crop to the same size => should be identity
412
        tensor, _ = self._create_data(26, 36, device=device)
413
414
415
416
417
        for i in [0, 2, 3]:
            out_tensor = F.resized_crop(tensor, top=0, left=0, height=26, width=36, size=[26, 36], interpolation=i)
            self.assertTrue(tensor.equal(out_tensor), msg="{} vs {}".format(out_tensor[0, :5, :5], tensor[0, :5, :5]))

        # 2) resize by half and crop a TL corner
418
        tensor, _ = self._create_data(26, 36, device=device)
419
420
421
422
423
424
425
        out_tensor = F.resized_crop(tensor, top=0, left=0, height=20, width=30, size=[10, 15], interpolation=0)
        expected_out_tensor = tensor[:, :20:2, :30:2]
        self.assertTrue(
            expected_out_tensor.equal(out_tensor),
            msg="{} vs {}".format(expected_out_tensor[0, :10, :10], out_tensor[0, :10, :10])
        )

426
427
428
429
430
431
432
433
    def test_resized_crop_cpu(self):
        self._test_resized_crop("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_resized_crop_cuda(self):
        self._test_resized_crop("cuda")

    def _test_affine(self, device):
434
        # Tests on square and rectangular images
vfdev's avatar
vfdev committed
435
436
        scripted_affine = torch.jit.script(F.affine)

437
        for tensor, pil_img in [self._create_data(26, 26, device=device), self._create_data(32, 26, device=device)]:
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460

            # 1) identity map
            out_tensor = F.affine(tensor, angle=0, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], resample=0)
            self.assertTrue(
                tensor.equal(out_tensor), msg="{} vs {}".format(out_tensor[0, :5, :5], tensor[0, :5, :5])
            )
            out_tensor = scripted_affine(tensor, angle=0, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], resample=0)
            self.assertTrue(
                tensor.equal(out_tensor), msg="{} vs {}".format(out_tensor[0, :5, :5], tensor[0, :5, :5])
            )

            if pil_img.size[0] == pil_img.size[1]:
                # 2) Test rotation
                test_configs = [
                    (90, torch.rot90(tensor, k=1, dims=(-1, -2))),
                    (45, None),
                    (30, None),
                    (-30, None),
                    (-45, None),
                    (-90, torch.rot90(tensor, k=-1, dims=(-1, -2))),
                    (180, torch.rot90(tensor, k=2, dims=(-1, -2))),
                ]
                for a, true_tensor in test_configs:
461
462
463
464
465
466

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

467
                    for fn in [F.affine, scripted_affine]:
468
469
470
                        out_tensor = fn(
                            tensor, angle=a, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], resample=0
                        )
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
                        if true_tensor is not None:
                            self.assertTrue(
                                true_tensor.equal(out_tensor),
                                msg="{}\n{} vs \n{}".format(a, out_tensor[0, :5, :5], true_tensor[0, :5, :5])
                            )
                        else:
                            true_tensor = out_tensor

                        num_diff_pixels = (true_tensor != out_pil_tensor).sum().item() / 3.0
                        ratio_diff_pixels = num_diff_pixels / true_tensor.shape[-1] / true_tensor.shape[-2]
                        # Tolerance : less than 6% of different pixels
                        self.assertLess(
                            ratio_diff_pixels,
                            0.06,
                            msg="{}\n{} vs \n{}".format(
                                ratio_diff_pixels, true_tensor[0, :7, :7], out_pil_tensor[0, :7, :7]
                            )
                        )
            else:
                test_configs = [
                    90, 45, 15, -30, -60, -120
                ]
                for a in test_configs:
494
495
496
497
498
499

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

500
                    for fn in [F.affine, scripted_affine]:
501
502
503
                        out_tensor = fn(
                            tensor, angle=a, translate=[0, 0], scale=1.0, shear=[0.0, 0.0], resample=0
                        ).cpu()
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520

                        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
                        self.assertLess(
                            ratio_diff_pixels,
                            0.03,
                            msg="{}: {}\n{} vs \n{}".format(
                                a, ratio_diff_pixels, out_tensor[0, :7, :7], out_pil_tensor[0, :7, :7]
                            )
                        )

            # 3) Test translation
            test_configs = [
                [10, 12], (-12, -13)
            ]
            for t in test_configs:
521
522
523

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

vfdev's avatar
vfdev committed
524
                for fn in [F.affine, scripted_affine]:
525
                    out_tensor = fn(tensor, angle=0, translate=t, scale=1.0, shear=[0.0, 0.0], resample=0)
526

527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
                    self.compareTensorToPIL(out_tensor, out_pil_img)

            # 3) Test rotation + translation + scale + share
            test_configs = [
                (45, [5, 6], 1.0, [0.0, 0.0]),
                (33, (5, -4), 1.0, [0.0, 0.0]),
                (45, [-5, 4], 1.2, [0.0, 0.0]),
                (33, (-4, -8), 2.0, [0.0, 0.0]),
                (85, (10, -10), 0.7, [0.0, 0.0]),
                (0, [0, 0], 1.0, [35.0, ]),
                (-25, [0, 0], 1.2, [0.0, 15.0]),
                (-45, [-10, 0], 0.7, [2.0, 5.0]),
                (-45, [-10, -10], 1.2, [4.0, 5.0]),
                (-90, [0, 0], 1.0, [0.0, 0.0]),
            ]
            for r in [0, ]:
                for a, t, s, sh in test_configs:
                    out_pil_img = F.affine(pil_img, angle=a, translate=t, scale=s, shear=sh, resample=r)
                    out_pil_tensor = torch.from_numpy(np.array(out_pil_img).transpose((2, 0, 1)))

                    for fn in [F.affine, scripted_affine]:
548
                        out_tensor = fn(tensor, angle=a, translate=t, scale=s, shear=sh, resample=r).cpu()
549
550
                        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]
551
552
                        # Tolerance : less than 5% (cpu), 6% (cuda) of different pixels
                        tol = 0.06 if device == "cuda" else 0.05
553
554
                        self.assertLess(
                            ratio_diff_pixels,
555
                            tol,
556
557
558
                            msg="{}: {}\n{} vs \n{}".format(
                                (r, a, t, s, sh), ratio_diff_pixels, out_tensor[0, :7, :7], out_pil_tensor[0, :7, :7]
                            )
vfdev's avatar
vfdev committed
559
560
                        )

561
562
563
564
565
566
567
568
    def test_affine_cpu(self):
        self._test_affine("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_affine_cuda(self):
        self._test_affine("cuda")

    def _test_rotate(self, device):
vfdev's avatar
vfdev committed
569
570
571
        # Tests on square image
        scripted_rotate = torch.jit.script(F.rotate)

572
        for tensor, pil_img in [self._create_data(26, 26, device=device), self._create_data(32, 26, device=device)]:
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588

            img_size = pil_img.size
            centers = [
                None,
                (int(img_size[0] * 0.3), int(img_size[0] * 0.4)),
                [int(img_size[0] * 0.5), int(img_size[0] * 0.6)]
            ]

            for r in [0, ]:
                for a in range(-180, 180, 17):
                    for e in [True, False]:
                        for c in centers:

                            out_pil_img = F.rotate(pil_img, angle=a, resample=r, expand=e, center=c)
                            out_pil_tensor = torch.from_numpy(np.array(out_pil_img).transpose((2, 0, 1)))
                            for fn in [F.rotate, scripted_rotate]:
589
                                out_tensor = fn(tensor, angle=a, resample=r, expand=e, center=c).cpu()
590
591
592
593
594
595
596

                                self.assertEqual(
                                    out_tensor.shape,
                                    out_pil_tensor.shape,
                                    msg="{}: {} vs {}".format(
                                        (img_size, r, a, e, c), out_tensor.shape, out_pil_tensor.shape
                                    )
vfdev's avatar
vfdev committed
597
                                )
598
599
600
601
602
603
604
605
606
607
608
609
                                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 2% of different pixels
                                self.assertLess(
                                    ratio_diff_pixels,
                                    0.02,
                                    msg="{}: {}\n{} vs \n{}".format(
                                        (img_size, r, a, e, c),
                                        ratio_diff_pixels,
                                        out_tensor[0, :7, :7],
                                        out_pil_tensor[0, :7, :7]
                                    )
vfdev's avatar
vfdev committed
610
611
                                )

612
613
614
615
616
617
618
619
    def test_rotate_cpu(self):
        self._test_rotate("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_rotate_cuda(self):
        self._test_rotate("cuda")

    def _test_perspective(self, device):
620
621
622

        from torchvision.transforms import RandomPerspective

623
        for tensor, pil_img in [self._create_data(26, 34, device=device), self._create_data(26, 26, device=device)]:
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642

            scripted_tranform = torch.jit.script(F.perspective)

            test_configs = [
                [[[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]]],
            ]
            n = 10
            test_configs += [
                RandomPerspective.get_params(pil_img.size[0], pil_img.size[1], i / n) for i in range(n)
            ]

            for r in [0, ]:
                for spoints, epoints in test_configs:
                    out_pil_img = F.perspective(pil_img, startpoints=spoints, endpoints=epoints, interpolation=r)
                    out_pil_tensor = torch.from_numpy(np.array(out_pil_img).transpose((2, 0, 1)))

                    for fn in [F.perspective, scripted_tranform]:
643
                        out_tensor = fn(tensor, startpoints=spoints, endpoints=epoints, interpolation=r).cpu()
644
645
646

                        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]
647
                        # Tolerance : less than 5% of different pixels
648
649
                        self.assertLess(
                            ratio_diff_pixels,
650
                            0.05,
651
652
653
654
655
656
657
658
                            msg="{}: {}\n{} vs \n{}".format(
                                (r, spoints, epoints),
                                ratio_diff_pixels,
                                out_tensor[0, :7, :7],
                                out_pil_tensor[0, :7, :7]
                            )
                        )

659
660
661
662
663
664
665
    def test_perspective_cpu(self):
        self._test_perspective("cpu")

    @unittest.skipIf(not torch.cuda.is_available(), reason="Skip if no CUDA device")
    def test_perspective_cuda(self):
        self._test_perspective("cuda")

666
667
668

if __name__ == '__main__':
    unittest.main()