1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
|
import random
import warnings
import numpy as np
import pytest
import torch
from common_utils import assert_equal
from torchvision.transforms import Compose
try:
from scipy import stats
except ImportError:
stats = None
with warnings.catch_warnings(record=True):
warnings.simplefilter("always")
import torchvision.transforms._transforms_video as transforms
class TestVideoTransforms:
def test_random_crop_video(self):
numFrames = random.randint(4, 128)
height = random.randint(10, 32) * 2
width = random.randint(10, 32) * 2
oheight = random.randint(5, (height - 2) // 2) * 2
owidth = random.randint(5, (width - 2) // 2) * 2
clip = torch.randint(0, 256, (numFrames, height, width, 3), dtype=torch.uint8)
result = Compose(
[
transforms.ToTensorVideo(),
transforms.RandomCropVideo((oheight, owidth)),
]
)(clip)
assert result.size(2) == oheight
assert result.size(3) == owidth
transforms.RandomCropVideo((oheight, owidth)).__repr__()
def test_random_resized_crop_video(self):
numFrames = random.randint(4, 128)
height = random.randint(10, 32) * 2
width = random.randint(10, 32) * 2
oheight = random.randint(5, (height - 2) // 2) * 2
owidth = random.randint(5, (width - 2) // 2) * 2
clip = torch.randint(0, 256, (numFrames, height, width, 3), dtype=torch.uint8)
result = Compose(
[
transforms.ToTensorVideo(),
transforms.RandomResizedCropVideo((oheight, owidth)),
]
)(clip)
assert result.size(2) == oheight
assert result.size(3) == owidth
transforms.RandomResizedCropVideo((oheight, owidth)).__repr__()
def test_center_crop_video(self):
numFrames = random.randint(4, 128)
height = random.randint(10, 32) * 2
width = random.randint(10, 32) * 2
oheight = random.randint(5, (height - 2) // 2) * 2
owidth = random.randint(5, (width - 2) // 2) * 2
clip = torch.ones((numFrames, height, width, 3), dtype=torch.uint8) * 255
oh1 = (height - oheight) // 2
ow1 = (width - owidth) // 2
clipNarrow = clip[:, oh1 : oh1 + oheight, ow1 : ow1 + owidth, :]
clipNarrow.fill_(0)
result = Compose(
[
transforms.ToTensorVideo(),
transforms.CenterCropVideo((oheight, owidth)),
]
)(clip)
msg = (
"height: " + str(height) + " width: " + str(width) + " oheight: " + str(oheight) + " owidth: " + str(owidth)
)
assert result.sum().item() == 0, msg
oheight += 1
owidth += 1
result = Compose(
[
transforms.ToTensorVideo(),
transforms.CenterCropVideo((oheight, owidth)),
]
)(clip)
sum1 = result.sum()
msg = (
"height: " + str(height) + " width: " + str(width) + " oheight: " + str(oheight) + " owidth: " + str(owidth)
)
assert sum1.item() > 1, msg
oheight += 1
owidth += 1
result = Compose(
[
transforms.ToTensorVideo(),
transforms.CenterCropVideo((oheight, owidth)),
]
)(clip)
sum2 = result.sum()
msg = (
"height: " + str(height) + " width: " + str(width) + " oheight: " + str(oheight) + " owidth: " + str(owidth)
)
assert sum2.item() > 1, msg
assert sum2.item() > sum1.item(), msg
@pytest.mark.skipif(stats is None, reason="scipy.stats is not available")
@pytest.mark.parametrize("channels", [1, 3])
def test_normalize_video(self, channels):
def samples_from_standard_normal(tensor):
p_value = stats.kstest(list(tensor.view(-1)), "norm", args=(0, 1)).pvalue
return p_value > 0.0001
random_state = random.getstate()
random.seed(42)
numFrames = random.randint(4, 128)
height = random.randint(32, 256)
width = random.randint(32, 256)
mean = random.random()
std = random.random()
clip = torch.normal(mean, std, size=(channels, numFrames, height, width))
mean = [clip[c].mean().item() for c in range(channels)]
std = [clip[c].std().item() for c in range(channels)]
normalized = transforms.NormalizeVideo(mean, std)(clip)
assert samples_from_standard_normal(normalized)
random.setstate(random_state)
# Checking the optional in-place behaviour
tensor = torch.rand((3, 128, 16, 16))
tensor_inplace = transforms.NormalizeVideo((0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)(tensor)
assert_equal(tensor, tensor_inplace)
transforms.NormalizeVideo((0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True).__repr__()
def test_to_tensor_video(self):
numFrames, height, width = 64, 4, 4
trans = transforms.ToTensorVideo()
with pytest.raises(TypeError):
np_rng = np.random.RandomState(0)
trans(np_rng.rand(numFrames, height, width, 1).tolist())
with pytest.raises(TypeError):
trans(torch.rand((numFrames, height, width, 1), dtype=torch.float))
with pytest.raises(ValueError):
trans(torch.ones((3, numFrames, height, width, 3), dtype=torch.uint8))
with pytest.raises(ValueError):
trans(torch.ones((height, width, 3), dtype=torch.uint8))
with pytest.raises(ValueError):
trans(torch.ones((width, 3), dtype=torch.uint8))
with pytest.raises(ValueError):
trans(torch.ones((3), dtype=torch.uint8))
trans.__repr__()
@pytest.mark.parametrize("p", (0, 1))
def test_random_horizontal_flip_video(self, p):
clip = torch.rand((3, 4, 112, 112), dtype=torch.float)
hclip = clip.flip(-1)
out = transforms.RandomHorizontalFlipVideo(p=p)(clip)
if p == 0:
torch.testing.assert_close(out, clip)
elif p == 1:
torch.testing.assert_close(out, hclip)
transforms.RandomHorizontalFlipVideo().__repr__()
if __name__ == "__main__":
pytest.main([__file__])
|
