Deci-AI
/
super-gradients
connected to https://github.com/Deci-AI/super-gradients.git


  
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

	
            import numpy as np
import unittest

from super_gradients.training.transforms.transforms import DetectionTargetsFormatTransform

from super_gradients.training.datasets.data_formats.default_formats import (
    XYXY_LABEL,
    LABEL_XYXY,
    LABEL_CXCYWH,
    LABEL_NORMALIZED_XYXY,
    LABEL_NORMALIZED_CXCYWH,
)


class DetectionTargetsTransformTest(unittest.TestCase):
    def setUp(self) -> None:
        self.image = np.zeros((3, 100, 200))

    def test_label_first_2_label_last(self):
        input = np.array([[10, 20, 30, 40, 50]], dtype=np.float32)
        output = np.array([[50, 10, 20, 30, 40]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(input_dim=self.image.shape[1:], max_targets=1, input_format=XYXY_LABEL, output_format=LABEL_XYXY)
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_xyxy_2_normalized_xyxy(self):
        input = np.array([[10, 20, 30, 40, 50]], dtype=np.float32)
        _, h, w = self.image.shape
        output = np.array([[10, 20 / w, 30 / h, 40 / w, 50 / h]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_XYXY, output_format=LABEL_NORMALIZED_XYXY)
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_xyxy_2_cxcywh(self):
        input = np.array([[10, 20, 30, 40, 50]], dtype=np.float32)
        _, h, w = self.image.shape
        output = np.array([[10, 30, 40, 20, 20]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_XYXY, output_format=LABEL_CXCYWH)
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_xyxy_2_normalized_cxcywh(self):
        input = np.array([[10, 20, 30, 40, 50]], dtype=np.float32)
        _, h, w = self.image.shape
        output = np.array([[10, 30 / w, 40 / h, 20 / w, 20 / h]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(
            input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_XYXY, output_format=LABEL_NORMALIZED_CXCYWH
        )
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_normalized_xyxy_2_cxcywh(self):
        _, h, w = self.image.shape
        input = np.array([[10, 20 / w, 30 / h, 40 / w, 50 / h]], dtype=np.float32)
        output = np.array([[10, 30, 40, 20, 20]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(
            input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_NORMALIZED_XYXY, output_format=LABEL_CXCYWH
        )
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_normalized_xyxy_2_normalized_cxcywh(self):
        _, h, w = self.image.shape
        input = np.array([[10, 20 / w, 30 / h, 40 / w, 50 / h]], dtype=np.float32)
        output = np.array([[10, 30 / w, 40 / h, 20 / w, 20 / h]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(
            input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_NORMALIZED_XYXY, output_format=LABEL_NORMALIZED_CXCYWH
        )
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_cxcywh_2_xyxy(self):
        output = np.array([[10, 20, 30, 40, 50]], dtype=np.float32)
        input = np.array([[10, 30, 40, 20, 20]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_CXCYWH, output_format=LABEL_XYXY)
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_cxcywh_2_normalized_xyxy(self):
        _, h, w = self.image.shape
        output = np.array([[10, 20 / w, 30 / h, 40 / w, 50 / h]], dtype=np.float32)
        input = np.array([[10, 30, 40, 20, 20]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(
            input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_CXCYWH, output_format=LABEL_NORMALIZED_XYXY
        )
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_normalized_cxcywh_2_xyxy(self):
        _, h, w = self.image.shape
        input = np.array([[10, 30 / w, 40 / h, 20 / w, 20 / h]], dtype=np.float32)
        output = np.array([[10, 20, 30, 40, 50]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(
            input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_NORMALIZED_CXCYWH, output_format=LABEL_XYXY
        )
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))

    def test_normalized_cxcywh_2_normalized_xyxy(self):
        _, h, w = self.image.shape
        output = np.array([[10, 20 / w, 30 / h, 40 / w, 50 / h]], dtype=np.float32)
        input = np.array([[10, 30 / w, 40 / h, 20 / w, 20 / h]], dtype=np.float32)
        sample = {"image": self.image, "target": input}

        transform = DetectionTargetsFormatTransform(
            input_dim=self.image.shape[1:], max_targets=1, input_format=LABEL_NORMALIZED_CXCYWH, output_format=LABEL_NORMALIZED_XYXY
        )
        t_output = transform(sample)["target"]
        self.assertTrue(np.allclose(output, t_output, atol=1e-6))


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