File size: 6,386 Bytes
aa24fe8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import cv2
import numpy as np
import torch
from PIL import Image
from torch.utils.data.dataset import Dataset

from utils.utils import cvtColor, preprocess_input


class FRCNNDataset(Dataset):
    def __init__(self, annotation_lines, input_shape = [600, 600], train = True):
        self.annotation_lines   = annotation_lines
        self.length             = len(annotation_lines)
        self.input_shape        = input_shape
        self.train              = train

    def __len__(self):
        return self.length

    def __getitem__(self, index):
        index       = index % self.length
        #---------------------------------------------------#
        #   训练时进行数据的随机增强
        #   验证时不进行数据的随机增强
        #---------------------------------------------------#
        image, y    = self.get_random_data(self.annotation_lines[index], self.input_shape[0:2], random = self.train)
        image       = np.transpose(preprocess_input(np.array(image, dtype=np.float32)), (2, 0, 1))
        box_data    = np.zeros((len(y), 5))
        if len(y) > 0:
            box_data[:len(y)] = y

        box         = box_data[:, :4]
        label       = box_data[:, -1]
        return image, box, label

    def rand(self, a=0, b=1):
        return np.random.rand()*(b-a) + a

    def get_random_data(self, annotation_line, input_shape, jitter=.3, hue=.1, sat=0.7, val=0.4, random=True):
        line = annotation_line.split()
        #------------------------------#
        #   读取图像并转换成RGB图像
        #------------------------------#
        image   = Image.open(line[0])
        image   = cvtColor(image)
        #------------------------------#
        #   获得图像的高宽与目标高宽
        #------------------------------#
        iw, ih  = image.size
        h, w    = input_shape
        #------------------------------#
        #   获得预测框
        #------------------------------#
        box     = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])

        if not random:
            scale = min(w/iw, h/ih)
            nw = int(iw*scale)
            nh = int(ih*scale)
            dx = (w-nw)//2
            dy = (h-nh)//2

            #---------------------------------#
            #   将图像多余的部分加上灰条
            #---------------------------------#
            image       = image.resize((nw,nh), Image.BICUBIC)
            new_image   = Image.new('RGB', (w,h), (128,128,128))
            new_image.paste(image, (dx, dy))
            image_data  = np.array(new_image, np.float32)

            #---------------------------------#
            #   对真实框进行调整
            #---------------------------------#
            if len(box)>0:
                np.random.shuffle(box)
                box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
                box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
                box[:, 0:2][box[:, 0:2]<0] = 0
                box[:, 2][box[:, 2]>w] = w
                box[:, 3][box[:, 3]>h] = h
                box_w = box[:, 2] - box[:, 0]
                box_h = box[:, 3] - box[:, 1]
                box = box[np.logical_and(box_w>1, box_h>1)] # discard invalid box

            return image_data, box
                
        #------------------------------------------#
        #   对图像进行缩放并且进行长和宽的扭曲
        #------------------------------------------#
        new_ar = iw/ih * self.rand(1-jitter,1+jitter) / self.rand(1-jitter,1+jitter)
        scale = self.rand(.25, 2)
        if new_ar < 1:
            nh = int(scale*h)
            nw = int(nh*new_ar)
        else:
            nw = int(scale*w)
            nh = int(nw/new_ar)
        image = image.resize((nw,nh), Image.BICUBIC)

        #------------------------------------------#
        #   将图像多余的部分加上灰条
        #------------------------------------------#
        dx = int(self.rand(0, w-nw))
        dy = int(self.rand(0, h-nh))
        new_image = Image.new('RGB', (w,h), (128,128,128))
        new_image.paste(image, (dx, dy))
        image = new_image

        #------------------------------------------#
        #   翻转图像
        #------------------------------------------#
        flip = self.rand()<.5
        if flip: image = image.transpose(Image.FLIP_LEFT_RIGHT)

        image_data      = np.array(image, np.uint8)
        #---------------------------------#
        #   对图像进行色域变换
        #   计算色域变换的参数
        #---------------------------------#
        r               = np.random.uniform(-1, 1, 3) * [hue, sat, val] + 1
        #---------------------------------#
        #   将图像转到HSV上
        #---------------------------------#
        hue, sat, val   = cv2.split(cv2.cvtColor(image_data, cv2.COLOR_RGB2HSV))
        dtype           = image_data.dtype
        #---------------------------------#
        #   应用变换
        #---------------------------------#
        x       = np.arange(0, 256, dtype=r.dtype)
        lut_hue = ((x * r[0]) % 180).astype(dtype)
        lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
        lut_val = np.clip(x * r[2], 0, 255).astype(dtype)

        image_data = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
        image_data = cv2.cvtColor(image_data, cv2.COLOR_HSV2RGB)

        #---------------------------------#
        #   对真实框进行调整
        #---------------------------------#
        if len(box)>0:
            np.random.shuffle(box)
            box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
            box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
            if flip: box[:, [0,2]] = w - box[:, [2,0]]
            box[:, 0:2][box[:, 0:2]<0] = 0
            box[:, 2][box[:, 2]>w] = w
            box[:, 3][box[:, 3]>h] = h
            box_w = box[:, 2] - box[:, 0]
            box_h = box[:, 3] - box[:, 1]
            box = box[np.logical_and(box_w>1, box_h>1)] 
        
        return image_data, box

# DataLoader中collate_fn使用
def frcnn_dataset_collate(batch):
    images = []
    bboxes = []
    labels = []
    for img, box, label in batch:
        images.append(img)
        bboxes.append(box)
        labels.append(label)
    images = torch.from_numpy(np.array(images))
    return images, bboxes, labels