-
Notifications
You must be signed in to change notification settings - Fork 101
/
extract_features.py
145 lines (125 loc) · 4.81 KB
/
extract_features.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
# filter warnings
import warnings
warnings.simplefilter(action="ignore", category=FutureWarning)
# keras imports
from keras.applications.vgg16 import VGG16, preprocess_input
from keras.applications.vgg19 import VGG19, preprocess_input
from keras.applications.xception import Xception, preprocess_input
from keras.applications.resnet50 import ResNet50, preprocess_input
from keras.applications.inception_resnet_v2 import InceptionResNetV2, preprocess_input
from keras.applications.mobilenet import MobileNet, preprocess_input
from keras.applications.inception_v3 import InceptionV3, preprocess_input
from keras.preprocessing import image
from keras.models import Model
from keras.models import model_from_json
from keras.layers import Input
# other imports
from sklearn.preprocessing import LabelEncoder
import numpy as np
import glob
import cv2
import h5py
import os
import json
import datetime
import time
# load the user configs
with open('conf/conf.json') as f:
config = json.load(f)
# config variables
model_name = config["model"]
weights = config["weights"]
include_top = config["include_top"]
train_path = config["train_path"]
features_path = config["features_path"]
labels_path = config["labels_path"]
test_size = config["test_size"]
results = config["results"]
model_path = config["model_path"]
# start time
print ("[STATUS] start time - {}".format(datetime.datetime.now().strftime("%Y-%m-%d %H:%M")))
start = time.time()
# create the pretrained models
# check for pretrained weight usage or not
# check for top layers to be included or not
if model_name == "vgg16":
base_model = VGG16(weights=weights)
model = Model(input=base_model.input, output=base_model.get_layer('fc1').output)
image_size = (224, 224)
elif model_name == "vgg19":
base_model = VGG19(weights=weights)
model = Model(input=base_model.input, output=base_model.get_layer('fc1').output)
image_size = (224, 224)
elif model_name == "resnet50":
base_model = ResNet50(weights=weights)
model = Model(input=base_model.input, output=base_model.get_layer('flatten').output)
image_size = (224, 224)
elif model_name == "inceptionv3":
base_model = InceptionV3(include_top=include_top, weights=weights, input_tensor=Input(shape=(299,299,3)))
model = Model(input=base_model.input, output=base_model.get_layer('custom').output)
image_size = (299, 299)
elif model_name == "inceptionresnetv2":
base_model = InceptionResNetV2(include_top=include_top, weights=weights, input_tensor=Input(shape=(299,299,3)))
model = Model(input=base_model.input, output=base_model.get_layer('custom').output)
image_size = (299, 299)
elif model_name == "mobilenet":
base_model = MobileNet(include_top=include_top, weights=weights, input_tensor=Input(shape=(224,224,3)), input_shape=(224,224,3))
model = Model(input=base_model.input, output=base_model.get_layer('custom').output)
image_size = (224, 224)
elif model_name == "xception":
base_model = Xception(weights=weights)
model = Model(input=base_model.input, output=base_model.get_layer('avg_pool').output)
image_size = (299, 299)
else:
base_model = None
print ("[INFO] successfully loaded base model and model...")
# path to training dataset
train_labels = os.listdir(train_path)
# encode the labels
print ("[INFO] encoding labels...")
le = LabelEncoder()
le.fit([tl for tl in train_labels])
# variables to hold features and labels
features = []
labels = []
# loop over all the labels in the folder
count = 1
for i, label in enumerate(train_labels):
cur_path = train_path + "/" + label
count = 1
for image_path in glob.glob(cur_path + "/*.jpg"):
img = image.load_img(image_path, target_size=image_size)
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
feature = model.predict(x)
flat = feature.flatten()
features.append(flat)
labels.append(label)
print ("[INFO] processed - " + str(count))
count += 1
print ("[INFO] completed label - " + label)
# encode the labels using LabelEncoder
le = LabelEncoder()
le_labels = le.fit_transform(labels)
# get the shape of training labels
print ("[STATUS] training labels: {}".format(le_labels))
print ("[STATUS] training labels shape: {}".format(le_labels.shape))
# save features and labels
h5f_data = h5py.File(features_path, 'w')
h5f_data.create_dataset('dataset_1', data=np.array(features))
h5f_label = h5py.File(labels_path, 'w')
h5f_label.create_dataset('dataset_1', data=np.array(le_labels))
h5f_data.close()
h5f_label.close()
# save model and weights
model_json = model.to_json()
with open(model_path + str(test_size) + ".json", "w") as json_file:
json_file.write(model_json)
# save weights
model.save_weights(model_path + str(test_size) + ".h5")
print("[STATUS] saved model and weights to disk..")
print ("[STATUS] features and labels saved..")
# end time
end = time.time()
print ("[STATUS] end time - {}".format(datetime.datetime.now().strftime("%Y-%m-%d %H:%M")))