-
Notifications
You must be signed in to change notification settings - Fork 0
/
cv_extract_embeddings.py
109 lines (91 loc) · 4 KB
/
cv_extract_embeddings.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
# import the necessary packages
from imutils import paths
import numpy as np
import imutils
import pickle
import cv2
import os
dataset = "dataset/train"
embeddings = "output/embeddings.pickle"
detector_path = "face_detection_model"
detector_model = "res10_300x300_ssd_iter_140000.caffemodel"
embedding_model = "openface_nn4.small2.v1.t7"
CONFIDENCE_DEFAULT= 0.5
# load our serialized face detector from disk
print("[INFO] loading face detector...")
protoPath = os.path.join(detector_path, "deploy.prototxt")
modelPath = os.path.join(detector_path, detector_model)
detector = cv2.dnn.readNetFromCaffe(protoPath, modelPath)
# load our serialized face embedding model from disk
print("[INFO] loading face recognizer...")
embedder = cv2.dnn.readNetFromTorch(embedding_model)
# grab the paths to the input images in our dataset
print("[INFO] quantifying faces...")
imagePaths = list(paths.list_images(dataset))
# initialize our lists of extracted facial embeddings and
# corresponding people names
knownEmbeddings = []
knownNames = []
# initialize the total number of faces processed
total = 0
# loop over the image paths
for (i, imagePath) in enumerate(imagePaths):
# extract the person name from the image path
print("[INFO] processing image {}/{}".format(i + 1, len(imagePaths)))
name = imagePath.split(os.path.sep)[-2]
# load the image, resize it to have a width of 600 pixels (while
# maintaining the aspect ratio), and then grab the image
# dimensions
image = cv2.imread(imagePath)
image = imutils.resize(image, width=600)
(h, w) = image.shape[:2]
# construct a blob from the image
imageBlob = cv2.dnn.blobFromImage( cv2.resize(image, (300, 300)),
1.0,
(300, 300),
(104.0, 177.0, 123.0),
swapRB=False, crop=False)
# apply OpenCV's deep learning-based face detector to localize
# faces in the input image
detector.setInput(imageBlob)
detections = detector.forward()
# ensure at least one face was found
if len(detections) > 0:
# we're making the assumption that each image has only ONE
# face, so find the bounding box with the largest probability
i = np.argmax(detections[0, 0, :, 2])
confidence = detections[0, 0, i, 2]
# ensure that the detection with the largest probability also
# means our minimum probability test (thus helping filter out
# weak detections)
if confidence > CONFIDENCE_DEFAULT:
# compute the (x, y)-coordinates of the bounding box for
# the face
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# extract the face ROI and grab the ROI dimensions
face = image[startY:endY, startX:endX]
(fH, fW) = face.shape[:2]
# ensure the face width and height are sufficiently large
if fW < 20 or fH < 20:
continue
# construct a blob for the face ROI, then pass the blob
# through our face embedding model to obtain the 128-d
# quantification of the face
faceBlob = cv2.dnn.blobFromImage(face,
1.0 / 255,
(96, 96),
(0, 0, 0),
swapRB=True, crop=False)
embedder.setInput(faceBlob)
vec = embedder.forward()
# add the name of the person + corresponding face
# embedding to their respective lists
knownNames.append(name)
knownEmbeddings.append(vec.flatten())
total += 1
# dump the facial embeddings + names to disk
print("[INFO] serializing {} encodings...".format(total))
data = {"embeddings": knownEmbeddings, "names": knownNames}
with open(embeddings, "wb") as f:
f.write(pickle.dumps(data))