-
Notifications
You must be signed in to change notification settings - Fork 0
/
loader_configs.py
225 lines (184 loc) · 6.65 KB
/
loader_configs.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
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
import datasets
import io
import os
from glob import glob
from tqdm import tqdm
import numpy as np
import PIL
from PIL import Image
import scipy
import dlib
from datasets import Sequence
preprocessing_target_size = 256
# landmark detector
dlib_landmark_detector_path = os.getenv("LP_DLIB_PREDICTOR")
naming_splitter = "~"
######################## Specs ###########################
male = "male"
female = "female"
race_map = {
"asian": "asian",
"black": "black",
"african": "black",
"caucasian": "white",
"white": "white",
"middleeastern": "middleeastern",
"indian": "indian",
"hispanic": "hispanic",
"unknown": "unknown",
"O": "unkown",
"A": "asian",
"B": "black",
"H": "hispanic",
"W": "white",
"East Asian": "asian", # TODO
"Indian": "indian",
"Black": "black",
"Middle Eastern": "middleeastern",
"White": "white",
"Latino_Hispanic": "hispanic",
"Southeast Asian": "asian", #TODO
# From https://susanqq.github.io/UTKFace/
# utkface
"0": "white",
"1": "black",
"2": "asian",
"3": "indian",
"4": "unknown"
}
gender_map = {
"m": "male",
"f": "female",
"M": "male",
"male": "male",
"man": "male",
"F": "female",
"women": "female",
"female": "female",
"unknown": "unknown",
"Male": "male",
"Female": "female",
# From https://susanqq.github.io/UTKFace/
# utkface
"0": "male",
"1": "female",
}
# TODO: add some kind of versioning of sort
dataset_features = {
"person_id": datasets.Value("string"), # Unique Id that will be used to identify if the persons are from the same identity or not ...
"image": datasets.Value("binary"),
"dlib_align_status": datasets.Value("bool"),
"image_dlib_aligned": datasets.Value("binary"),
"gender": datasets.Value("string"),
"race": datasets.Value("string"),
"age": datasets.Value("string"),
"human": datasets.Value("bool"), # Used for human non-human stuff ...
}
def pre_process_images(raw_image_path, output_path, predictor):
current_directory = os.getcwd()
print(current_directory)
aligned_images = []
try:
aligned_image = align_face(filepath=raw_image_path,
predictor=predictor, output_size=preprocessing_target_size)
aligned_images.append(aligned_image)
except Exception as e:
print(e)
os.makedirs(output_path, exist_ok=True)
images_names = [raw_image_path.split('/')[-1]]
for image, name in zip(aligned_images, images_names):
# Name without extensions
real_name = name.split('.')[0]
image.save(f'{output_path}/{real_name}.jpeg')
os.chdir(current_directory)
## Borrowed from Insightfaces repository
def get_landmark(filepath, predictor):
"""get landmark with dlib
:return: np.array shape=(68, 2)
"""
detector = dlib.get_frontal_face_detector()
img = dlib.load_rgb_image(filepath)
dets = detector(img, 1)
for k, d in enumerate(dets):
shape = predictor(img, d)
t = list(shape.parts())
a = []
for tt in t:
a.append([tt.x, tt.y])
lm = np.array(a)
return lm
def align_face(filepath, predictor, output_size):
"""
:param filepath: str
:return: PIL Image
"""
lm = get_landmark(filepath, predictor)
lm_chin = lm[0: 17] # left-right
lm_eyebrow_left = lm[17: 22] # left-right
lm_eyebrow_right = lm[22: 27] # left-right
lm_nose = lm[27: 31] # top-down
lm_nostrils = lm[31: 36] # top-down
lm_eye_left = lm[36: 42] # left-clockwise
lm_eye_right = lm[42: 48] # left-clockwise
lm_mouth_outer = lm[48: 60] # left-clockwise
lm_mouth_inner = lm[60: 68] # left-clockwise
# Calculate auxiliary vectors.
eye_left = np.mean(lm_eye_left, axis=0)
eye_right = np.mean(lm_eye_right, axis=0)
eye_avg = (eye_left + eye_right) * 0.5
eye_to_eye = eye_right - eye_left
mouth_left = lm_mouth_outer[0]
mouth_right = lm_mouth_outer[6]
mouth_avg = (mouth_left + mouth_right) * 0.5
eye_to_mouth = mouth_avg - eye_avg
# Choose oriented crop rectangle.
x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]
x /= np.hypot(*x)
x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
y = np.flipud(x) * [-1, 1]
c = eye_avg + eye_to_mouth * 0.1
quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
qsize = np.hypot(*x) * 2
# read image
img = PIL.Image.open(filepath)
transform_size = output_size
enable_padding = True
# Shrink.
shrink = int(np.floor(qsize / output_size * 0.5))
if shrink > 1:
rsize = (int(np.rint(float(img.size[0]) / shrink)), int(np.rint(float(img.size[1]) / shrink)))
img = img.resize(rsize, PIL.Image.ANTIALIAS)
quad /= shrink
qsize /= shrink
# Crop.
border = max(int(np.rint(qsize * 0.1)), 3)
crop = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))), int(np.ceil(max(quad[:, 0]))),
int(np.ceil(max(quad[:, 1]))))
crop = (max(crop[0] - border, 0), max(crop[1] - border, 0), min(crop[2] + border, img.size[0]),
min(crop[3] + border, img.size[1]))
if crop[2] - crop[0] < img.size[0] or crop[3] - crop[1] < img.size[1]:
img = img.crop(crop)
quad -= crop[0:2]
# Pad.
pad = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))), int(np.ceil(max(quad[:, 0]))),
int(np.ceil(max(quad[:, 1]))))
pad = (max(-pad[0] + border, 0), max(-pad[1] + border, 0), max(pad[2] - img.size[0] + border, 0),
max(pad[3] - img.size[1] + border, 0))
if enable_padding and max(pad) > border - 4:
pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
img = np.pad(np.float32(img), ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'reflect')
h, w, _ = img.shape
y, x, _ = np.ogrid[:h, :w, :1]
mask = np.maximum(1.0 - np.minimum(np.float32(x) / pad[0], np.float32(w - 1 - x) / pad[2]),
1.0 - np.minimum(np.float32(y) / pad[1], np.float32(h - 1 - y) / pad[3]))
blur = qsize * 0.02
img += (scipy.ndimage.gaussian_filter(img, [blur, blur, 0]) - img) * np.clip(mask * 3.0 + 1.0, 0.0, 1.0)
img += (np.median(img, axis=(0, 1)) - img) * np.clip(mask, 0.0, 1.0)
img = PIL.Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
quad += pad[:2]
# Transform.
img = img.transform((transform_size, transform_size), PIL.Image.QUAD, (quad + 0.5).flatten(), PIL.Image.BICUBIC)
if output_size < transform_size:
img = img.resize((output_size, output_size), PIL.Image.ANTIALIAS)
# Return aligned image.
return img