-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathload_face_dataset.py
89 lines (71 loc) · 3.21 KB
/
load_face_dataset.py
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
# -*- coding: utf-8 -*-
#函数名:load_face_dataset.py
#作用 :加载图片调整指定大小并标注数据到内存
#用法 :python load_face_dataset.py pathname,,只不过这里只是把它封装成一个接口
#依赖 :os ,sys ,numpy ,opencv
import os
import sys
import numpy as np
import cv2
IMAGE_SIZE = 64
#按照指定图像大小调整尺寸
def resize_image(image, height = IMAGE_SIZE, width = IMAGE_SIZE):
top, bottom, left, right = (0, 0, 0, 0)
#获取图像尺寸
h, w, _ = image.shape
#对于长宽不相等的图片,找到最长的一边
longest_edge = max(h, w)
#计算短边需要增加多上像素宽度使其与长边等长
if h < longest_edge:
dh = longest_edge - h
top = dh // 2
bottom = dh - top
elif w < longest_edge:
dw = longest_edge - w
left = dw // 2
right = dw - left
else:
pass
#RGB颜色
BLACK = [0, 0, 0]
#给图像增加边界,是图片长、宽等长,cv2.BORDER_CONSTANT指定边界颜色由value指定
constant = cv2.copyMakeBorder(image, top , bottom, left, right, cv2.BORDER_CONSTANT, value = BLACK)
#调整图像大小并返回
return cv2.resize(constant, (height, width))
#读取训练数据
images = []
labels = []
def read_path(path_name):
for dir_item in os.listdir(path_name):
#从初始路径开始叠加,合并成可识别的操作路径
full_path = os.path.abspath(os.path.join(path_name, dir_item))
if os.path.isdir(full_path): #如果是文件夹,继续递归调用
read_path(full_path)
else: #文件
if dir_item.endswith('.jpg'):
image = cv2.imread(full_path)
image = resize_image(image, IMAGE_SIZE, IMAGE_SIZE)
#放开这个代码,可以看到resize_image()函数的实际调用效果
#cv2.imwrite('1.jpg', image)
images.append(image)
labels.append(path_name)
return images,labels
#从指定路径读取训练数据
def load_dataset(path_name):
images,labels = read_path(path_name)
#将输入的所有图片转成四维数组,尺寸为(图片数量*IMAGE_SIZE*IMAGE_SIZE*3)
#将图片转化成四维的tensor,比如1200张图片,IMAGE_SIZE为64,故为1200 * 64 * 64 * 3
#图片为64 * 64像素,一个像素3个颜色值(RGB)
images = np.array(images)
print(images.shape)
#标注数据,'me'文件夹下都是我的脸部图像,全部指定为0,另外一个文件夹下是闺女的,全部指定为1
# labels = np.array([0 if label.endswith('me') else 1 for label in labels])
# tree classes
#liuhc refers to liuhangcheng while zhaoyiqun and pyf in the same way
labels = np.array([0 if label.endswith('liuhc') else 1 if label.endswith('zhaoyiqun') else 2 for label in labels])
return images, labels
if __name__ == '__main__':
if len(sys.argv) != 2:
print("Usage:python %s path_name\r\n" % (sys.argv[0]))
else:
images, labels = load_dataset(sys.argv[1])