-
Notifications
You must be signed in to change notification settings - Fork 0
/
align_face_multi.py
208 lines (177 loc) · 7.59 KB
/
align_face_multi.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
"""
brief: face alignment with FFHQ method (https://github.com/NVlabs/ffhq-dataset)
author: lzhbrian (https://lzhbrian.me)
date: 2020.1.5
note: code is heavily borrowed from
https://github.com/NVlabs/ffhq-dataset
http://dlib.net/face_landmark_detection.py.html
https://github.com/sczhou/CodeFormer/blob/master/scripts/crop_align_face.py
requirements:
apt install cmake
conda install Pillow numpy scipy
pip install dlib
# download face landmark model from:
# http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
"""
import numpy as np
# import PIL
# import Image
from PIL import Image
import sys
import os
import glob
import scipy
import scipy.ndimage
import dlib
import argparse
import multiprocessing
# download model from: http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
# predictor = dlib.shape_predictor('./shape_predictor_68_face_landmarks.dat')
def get_landmark(filepath, keep_largest=True):
"""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)
print("Processing: ", filepath)
print("Number of faces detected: {}".format(len(dets)))
if len(dets) == 0:
print('No face detected, saving to trash folder')
dirpath = os.path.join(input_dir, 'no_face_detected')
os.makedirs(dirpath, exist_ok=True)
os.system(f'cp {filepath} {dirpath}')
return
if len(dets) > 1:
if keep_largest:
# Find the largest face as the main subject
largest_area = 0
largest_rect = dets[0]
for rect in dets:
area = (rect.right() - rect.left()) * (rect.bottom() - rect.top())
if area > largest_area:
largest_area = area
largest_rect = rect
dets = [largest_rect]
else:
print('WARNING: keep_largest is False, but more than one face detected, saving to trash folder')
dirpath = os.path.join(input_dir, 'more_than_one_face_detected')
os.makedirs(dirpath, exist_ok=True)
os.system(f'cp {filepath} {dirpath}')
return None
shape = predictor(img, dets[0])
t = list(shape.parts())
a = []
for tt in t:
a.append([tt.x, tt.y])
lm = np.array(a)
# lm is a shape=(68,2) np.array
return lm
def align_face(filepath):
"""
:param filepath: str
:return: PIL Image
"""
lm = get_landmark(filepath)
if lm is None:
return
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 = Image.open(filepath)
output_size=1024
transform_size=4096
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, Image.LANCZOS)
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 = Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
quad += pad[:2]
# Transform.
img = img.transform((transform_size, transform_size), Image.QUAD, (quad + 0.5).flatten(), Image.BILINEAR)
if output_size < transform_size:
img = img.resize((output_size, output_size), Image.LANCZOS)
# Save aligned image.
return img
def arg_parser():
parser = argparse.ArgumentParser(description='align face')
parser.add_argument('--input_dir', type=str, required=True, help='input directory')
parser.add_argument('--output_dir', type=str, default=None, help='output directory')
parser.add_argument('--num_workers', type=int, default=32, help='number of workers')
parser.add_argument('--predictor_path', type=str, default='./shape_predictor_68_face_landmarks.dat', help='path to dlib predictor')
return parser
if __name__ == "__main__":
IMG_EXTENSIONS = ['.jpg', '.jpeg', '.png', '.webp', '.JPG', '.JPEG', '.PNG', '.WEBP']
parser = arg_parser()
args = parser.parse_args()
input_dir = args.input_dir
output_dir = args.output_dir if args.output_dir else os.path.join(input_dir, 'aligned')
os.makedirs(output_dir, exist_ok=True)
num_workers = args.num_workers
predictor_path = args.predictor_path
predictor = dlib.shape_predictor(predictor_path)
input_images = []
# walk through input_dir
for root, _, fnames in sorted(os.walk(input_dir)):
for fname in sorted(fnames):
if any(fname.endswith(extension) for extension in IMG_EXTENSIONS):
path = os.path.join(root, fname)
input_images.append(path)
# align face
def align_face_worker(filepath):
# print(filepath)
img = align_face(filepath)
if img is not None:
# img.save(os.path.join(output_dir, os.path.basename(filepath)))
# save as jpeg
img.save(os.path.join(output_dir, os.path.basename(filepath).split('.')[0] + '.jpg'), 'JPEG')
with multiprocessing.Pool(num_workers) as p:
p.map(align_face_worker, input_images)
print('done')