File size: 7,076 Bytes
1565811
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
import cv2
import numpy as np
import random
from utils.box_utils import matrix_iof


def _crop(image, boxes, labels, landm, img_dim):
    height, width, _ = image.shape
    pad_image_flag = True

    for _ in range(250):
        """
        if random.uniform(0, 1) <= 0.2:
            scale = 1.0
        else:
            scale = random.uniform(0.3, 1.0)
        """
        PRE_SCALES = [0.3, 0.45, 0.6, 0.8, 1.0]
        scale = random.choice(PRE_SCALES)
        short_side = min(width, height)
        w = int(scale * short_side)
        h = w

        if width == w:
            l = 0
        else:
            l = random.randrange(width - w)
        if height == h:
            t = 0
        else:
            t = random.randrange(height - h)
        roi = np.array((l, t, l + w, t + h))

        value = matrix_iof(boxes, roi[np.newaxis])
        flag = (value >= 1)
        if not flag.any():
            continue

        centers = (boxes[:, :2] + boxes[:, 2:]) / 2
        mask_a = np.logical_and(roi[:2] < centers, centers < roi[2:]).all(axis=1)
        boxes_t = boxes[mask_a].copy()
        labels_t = labels[mask_a].copy()
        landms_t = landm[mask_a].copy()
        landms_t = landms_t.reshape([-1, 5, 2])

        if boxes_t.shape[0] == 0:
            continue

        image_t = image[roi[1]:roi[3], roi[0]:roi[2]]

        boxes_t[:, :2] = np.maximum(boxes_t[:, :2], roi[:2])
        boxes_t[:, :2] -= roi[:2]
        boxes_t[:, 2:] = np.minimum(boxes_t[:, 2:], roi[2:])
        boxes_t[:, 2:] -= roi[:2]

        # landm
        landms_t[:, :, :2] = landms_t[:, :, :2] - roi[:2]
        landms_t[:, :, :2] = np.maximum(landms_t[:, :, :2], np.array([0, 0]))
        landms_t[:, :, :2] = np.minimum(landms_t[:, :, :2], roi[2:] - roi[:2])
        landms_t = landms_t.reshape([-1, 10])


	# make sure that the cropped image contains at least one face > 16 pixel at training image scale
        b_w_t = (boxes_t[:, 2] - boxes_t[:, 0] + 1) / w * img_dim
        b_h_t = (boxes_t[:, 3] - boxes_t[:, 1] + 1) / h * img_dim
        mask_b = np.minimum(b_w_t, b_h_t) > 0.0
        boxes_t = boxes_t[mask_b]
        labels_t = labels_t[mask_b]
        landms_t = landms_t[mask_b]

        if boxes_t.shape[0] == 0:
            continue

        pad_image_flag = False

        return image_t, boxes_t, labels_t, landms_t, pad_image_flag
    return image, boxes, labels, landm, pad_image_flag


def _distort(image):

    def _convert(image, alpha=1, beta=0):
        tmp = image.astype(float) * alpha + beta
        tmp[tmp < 0] = 0
        tmp[tmp > 255] = 255
        image[:] = tmp

    image = image.copy()

    if random.randrange(2):

        #brightness distortion
        if random.randrange(2):
            _convert(image, beta=random.uniform(-32, 32))

        #contrast distortion
        if random.randrange(2):
            _convert(image, alpha=random.uniform(0.5, 1.5))

        image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)

        #saturation distortion
        if random.randrange(2):
            _convert(image[:, :, 1], alpha=random.uniform(0.5, 1.5))

        #hue distortion
        if random.randrange(2):
            tmp = image[:, :, 0].astype(int) + random.randint(-18, 18)
            tmp %= 180
            image[:, :, 0] = tmp

        image = cv2.cvtColor(image, cv2.COLOR_HSV2BGR)

    else:

        #brightness distortion
        if random.randrange(2):
            _convert(image, beta=random.uniform(-32, 32))

        image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)

        #saturation distortion
        if random.randrange(2):
            _convert(image[:, :, 1], alpha=random.uniform(0.5, 1.5))

        #hue distortion
        if random.randrange(2):
            tmp = image[:, :, 0].astype(int) + random.randint(-18, 18)
            tmp %= 180
            image[:, :, 0] = tmp

        image = cv2.cvtColor(image, cv2.COLOR_HSV2BGR)

        #contrast distortion
        if random.randrange(2):
            _convert(image, alpha=random.uniform(0.5, 1.5))

    return image


def _expand(image, boxes, fill, p):
    if random.randrange(2):
        return image, boxes

    height, width, depth = image.shape

    scale = random.uniform(1, p)
    w = int(scale * width)
    h = int(scale * height)

    left = random.randint(0, w - width)
    top = random.randint(0, h - height)

    boxes_t = boxes.copy()
    boxes_t[:, :2] += (left, top)
    boxes_t[:, 2:] += (left, top)
    expand_image = np.empty(
        (h, w, depth),
        dtype=image.dtype)
    expand_image[:, :] = fill
    expand_image[top:top + height, left:left + width] = image
    image = expand_image

    return image, boxes_t


def _mirror(image, boxes, landms):
    _, width, _ = image.shape
    if random.randrange(2):
        image = image[:, ::-1]
        boxes = boxes.copy()
        boxes[:, 0::2] = width - boxes[:, 2::-2]

        # landm
        landms = landms.copy()
        landms = landms.reshape([-1, 5, 2])
        landms[:, :, 0] = width - landms[:, :, 0]
        tmp = landms[:, 1, :].copy()
        landms[:, 1, :] = landms[:, 0, :]
        landms[:, 0, :] = tmp
        tmp1 = landms[:, 4, :].copy()
        landms[:, 4, :] = landms[:, 3, :]
        landms[:, 3, :] = tmp1
        landms = landms.reshape([-1, 10])

    return image, boxes, landms


def _pad_to_square(image, rgb_mean, pad_image_flag):
    if not pad_image_flag:
        return image
    height, width, _ = image.shape
    long_side = max(width, height)
    image_t = np.empty((long_side, long_side, 3), dtype=image.dtype)
    image_t[:, :] = rgb_mean
    image_t[0:0 + height, 0:0 + width] = image
    return image_t


def _resize_subtract_mean(image, insize, rgb_mean):
    interp_methods = [cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_NEAREST, cv2.INTER_LANCZOS4]
    interp_method = interp_methods[random.randrange(5)]
    image = cv2.resize(image, (insize, insize), interpolation=interp_method)
    image = image.astype(np.float32)
    image -= rgb_mean
    return image.transpose(2, 0, 1)


class preproc(object):

    def __init__(self, img_dim, rgb_means):
        self.img_dim = img_dim
        self.rgb_means = rgb_means

    def __call__(self, image, targets):
        assert targets.shape[0] > 0, "this image does not have gt"

        boxes = targets[:, :4].copy()
        labels = targets[:, -1].copy()
        landm = targets[:, 4:-1].copy()

        image_t, boxes_t, labels_t, landm_t, pad_image_flag = _crop(image, boxes, labels, landm, self.img_dim)
        image_t = _distort(image_t)
        image_t = _pad_to_square(image_t,self.rgb_means, pad_image_flag)
        image_t, boxes_t, landm_t = _mirror(image_t, boxes_t, landm_t)
        height, width, _ = image_t.shape
        image_t = _resize_subtract_mean(image_t, self.img_dim, self.rgb_means)
        boxes_t[:, 0::2] /= width
        boxes_t[:, 1::2] /= height

        landm_t[:, 0::2] /= width
        landm_t[:, 1::2] /= height

        labels_t = np.expand_dims(labels_t, 1)
        targets_t = np.hstack((boxes_t, landm_t, labels_t))

        return image_t, targets_t