File size: 6,522 Bytes
c6d57da
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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

from argparse import ArgumentParser
import time
import numpy as np
import PIL
import PIL.Image
import os
import scipy
import scipy.ndimage
import insightface
import multiprocessing as mp
import math

def get_landmark(filepath, face_detector):
    """get landmark with InsightFace
    :return: np.array shape=(68, 2)
    """
    if isinstance(filepath, str):
        img = PIL.Image.open(filepath)
        img = np.array(img)
    else:
        img = filepath

    faces = face_detector.get(img)
    
    if len(faces) == 0:
        print('Error: no face detected!')
        return None
    
    # Assume the first detected face is the target
    face = faces[0]
    lm = face.landmark_2d_106[:, :2]  # Use 106-point landmarks
    return lm

def align_face(filepath, face_detector):
    """
    :param filepath: str
    :return: PIL Image
    """
    lm = get_landmark(filepath, face_detector)
    if lm is None:
        return None    
    
    # Use the same landmark indices as before
    lm_eye_left = lm[36: 42]  # left-clockwise
    lm_eye_right = lm[42: 48]  # left-clockwise
    lm_mouth_outer = lm[48: 60]  # 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
    if isinstance(filepath, str):
        img = PIL.Image.open(filepath)
    else:
        img = PIL.Image.fromarray(filepath)

    output_size = 256
    transform_size = 256
    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.BILINEAR)
    if output_size < transform_size:
        img = img.resize((output_size, output_size), PIL.Image.ANTIALIAS)

    return img

def chunks(lst, n):
    """Yield successive n-sized chunks from lst."""
    for i in range(0, len(lst), n):
        yield lst[i:i + n]

def extract_on_paths(file_paths, face_detector):
    pid = mp.current_process().name
    print('\t{} is starting to extract on #{} images'.format(pid, len(file_paths)))
    tot_count = len(file_paths)
    count = 0
    for file_path, res_path in file_paths:
        count += 1
        if count % 100 == 0:
            print('{} done with {}/{}'.format(pid, count, tot_count))
        try:
            res = align_face(file_path, face_detector)
            res = res.convert('RGB')
            os.makedirs(os.path.dirname(res_path), exist_ok=True)
            res.save(res_path)
        except Exception:
            continue
    print('\tDone!')

def parse_args():
    parser = ArgumentParser(add_help=False)
    parser.add_argument('--num_threads', type=int, default=1)
    parser.add_argument('--root_path', type=str, default='')
    args = parser.parse_args()
    return args

def run(args):
    root_path = args.root_path
    out_crops_path = root_path + '_crops'
    if not os.path.exists(out_crops_path):
        os.makedirs(out_crops_path, exist_ok=True)

    file_paths = []
    for root, dirs, files in os.walk(root_path):
        for file in files:
            file_path = os.path.join(root, file)
            fname = os.path.join(out_crops_path, os.path.relpath(file_path, root_path))
            res_path = '{}.jpg'.format(os.path.splitext(fname)[0])
            if os.path.splitext(file_path)[1] == '.txt' or os.path.exists(res_path):
                continue
            file_paths.append((file_path, res_path))

    file_chunks = list(chunks(file_paths, int(math.ceil(len(file_paths) / args.num_threads))))
    print(len(file_chunks))
    pool = mp.Pool(args.num_threads)
    print('Running on {} paths\nHere we goooo'.format(len(file_paths)))
    tic = time.time()
    pool.starmap(extract_on_paths, [(chunk, face_detector) for chunk in file_chunks])
    toc = time.time()
    print('Mischief managed in {}s'.format(toc - tic))

if __name__ == '__main__':
    # Initialize InsightFace
    face_detector = insightface.app.FaceAnalysis()
    face_detector.prepare(ctx_id=-1, det_size=(640, 640))  # ctx_id=-1 for CPU

    args = parse_args()
    run(args)