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
|
from __future__ import print_function, division
import os
import torch
import pandas as pd #用于更容易地进行csv解析
from skimage import io, transform #用于图像的IO和变换
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
# 忽略警告
import warnings
warnings.filterwarnings("ignore")
plt.ion() # interactive mode
landmarks_frame = pd.read_csv('/home/jiajie/Downloads/data/faces/face_landmarks.csv')
n = 63
img_name = landmarks_frame.iloc[n, 0]
landmarks = landmarks_frame.iloc[n, 1:].as_matrix()
landmarks = landmarks.astype('float').reshape(-1, 2)
print('Image name: {}'.format(img_name))
print('Landmarks shape: {}'.format(landmarks.shape))
print('First 4 Landmarks: {}'.format(landmarks[:4]))
def show_landmarks(image, landmarks):
"""显示带有地标的图片"""
plt.imshow(image)
plt.scatter(landmarks[:, 0], landmarks[:, 1], s=10, marker='.', c='r')
plt.pause(0.001) # pause a bit so that plots are updated
plt.figure()
show_landmarks(io.imread(os.path.join('/home/jiajie/Downloads/data/faces/', img_name)),
landmarks)
#plt.show()
#plt.pause(100)
class FaceLandmarksDataset(Dataset):
"""面部标记数据集."""
def __init__(self, csv_file, root_dir, transform=None):
"""
csv_file（string）：带注释的csv文件的路径。
root_dir（string）：包含所有图像的目录。
transform（callable， optional）：一个样本上的可用的可选变换
"""
self.landmarks_frame = pd.read_csv(csv_file)
self.root_dir = root_dir
self.transform = transform
def __len__(self):
return len(self.landmarks_frame)
def __getitem__(self, idx):
img_name = os.path.join(self.root_dir,
self.landmarks_frame.iloc[idx, 0])
image = io.imread(img_name)
landmarks = self.landmarks_frame.iloc[idx, 1:]
landmarks = np.array([landmarks])
landmarks = landmarks.astype('float').reshape(-1, 2)
sample = {'image': image, 'landmarks': landmarks}
if self.transform:
sample = self.transform(sample)
return sample
class Rescale(object):
"""将样本中的图像重新缩放到给定大小。.
Args:
output_size（tuple或int）：所需的输出大小。 如果是元组，则输出为
与output_size匹配。 如果是int，则匹配较小的图像边缘到output_size保持纵横比相同。
"""
def __init__(self, output_size):
assert isinstance(output_size, (int, tuple))
self.output_size = output_size
def __call__(self, sample):
image, landmarks = sample['image'], sample['landmarks']
h, w = image.shape[:2]
if isinstance(self.output_size, int):
if h > w:
new_h, new_w = self.output_size * h / w, self.output_size
else:
new_h, new_w = self.output_size, self.output_size * w / h
else:
new_h, new_w = self.output_size
new_h, new_w = int(new_h), int(new_w)
img = transform.resize(image, (new_h, new_w))
# h and w are swapped for landmarks because for images,
# x and y axes are axis 1 and 0 respectively
landmarks = landmarks * [new_w / w, new_h / h]
return {'image': img, 'landmarks': landmarks}
class RandomCrop(object):
"""随机裁剪样本中的图像.
Args:
output_size（tuple或int）：所需的输出大小。 如果是int，方形裁剪是。
"""
def __init__(self, output_size):
assert isinstance(output_size, (int, tuple))
if isinstance(output_size, int):
self.output_size = (output_size, output_size)
else:
assert len(output_size) == 2
self.output_size = output_size
def __call__(self, sample):
image, landmarks = sample['image'], sample['landmarks']
h, w = image.shape[:2]
new_h, new_w = self.output_size
top = np.random.randint(0, h - new_h)
left = np.random.randint(0, w - new_w)
image = image[top: top + new_h,
left: left + new_w]
landmarks = landmarks - [left, top]
return {'image': image, 'landmarks': landmarks}
class ToTensor(object):
"""将样本中的ndarrays转换为Tensors."""
def __call__(self, sample):
image, landmarks = sample['image'], sample['landmarks']
# 交换颜色轴因为
# numpy包的图片是: H * W * C
# torch包的图片是: C * H * W
image = image.transpose((2, 0, 1))
return {'image': torch.from_numpy(image),
'landmarks': torch.from_numpy(landmarks)}
transformed_dataset = FaceLandmarksDataset(csv_file='/home/jiajie/Downloads/data/faces/face_landmarks.csv',
root_dir='/home/jiajie/Downloads/data/faces/',
transform=transforms.Compose([
Rescale(256),
RandomCrop(224),
ToTensor()
]))
dataloader = DataLoader(transformed_dataset, batch_size=4,
shuffle=True, num_workers=4)
# 辅助功能：显示批次
def show_landmarks_batch(sample_batched):
"""Show image with landmarks for a batch of samples."""
images_batch, landmarks_batch = \
sample_batched['image'], sample_batched['landmarks']
batch_size = len(images_batch)
im_size = images_batch.size(2)
grid_border_size = 2
grid = utils.make_grid(images_batch)
plt.imshow(grid.numpy().transpose((1, 2, 0)))
for i in range(batch_size):
plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size + (i + 1) * grid_border_size,
landmarks_batch[i, :, 1].numpy() + grid_border_size,
s=10, marker='.', c='r')
plt.title('Batch from dataloader')
for i_batch, sample_batched in enumerate(dataloader):
print(i_batch, sample_batched['image'].size(),
sample_batched['landmarks'].size())
# 观察第4批次并停止。
if i_batch == 3:
plt.figure()
show_landmarks_batch(sample_batched)
plt.axis('off')
plt.ioff()
plt.show()
break
|
