/
extract_features.py
106 lines (90 loc) · 3.8 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
# USAGE
# python extract_features.py --dataset ../datasets/scud/images --output ../datasets/scud/hdf5/features2.hdf5
# python extract_features.py --dataset ../datasets/caltech-101/images \
# --output ../datasets/caltech-101/hdf5/features.hdf5
# python extract_features.py --dataset ../datasets/flowers17/images \
# --output ../datasets/flowers17/hdf5/features.hdf5
# import the necessary packages
from keras.applications import VGG16
from keras.applications import imagenet_utils
from keras.preprocessing.image import img_to_array
from keras.preprocessing.image import load_img
from sklearn.preprocessing import LabelEncoder
from pyimagesearch.io import HDF5DatasetWriter
from imutils import paths
import numpy as np
import progressbar
import argparse
import random
import os
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required=True,
help="path to input dataset")
ap.add_argument("-o", "--output", required=True,
help="path to output HDF5 file")
ap.add_argument("-b", "--batch-size", type=int, default=32,
help="batch size of images to be passed through network")
ap.add_argument("-s", "--buffer-size", type=int, default=1000,
help="size of feature extraction buffer")
args = vars(ap.parse_args())
# store the batch size in a convenience variable
bs = args["batch_size"]
# grab the list of images that we'll be describing then randomly
# shuffle them to allow for easy training and testing splits via
# array slicing during training time
print("[INFO] loading images...")
imagePaths = list(paths.list_images(args["dataset"]))
random.shuffle(imagePaths)
# extract the class labels from the image paths then encode the
# labels
labels = [p.split(os.path.sep)[-2] for p in imagePaths]
le = LabelEncoder()
labels = le.fit_transform(labels)
# load the VGG16 network
print("[INFO] loading network...")
model = VGG16(weights="imagenet", include_top=False)
# initialize the HDF5 dataset writer, then store the class label
# names in the dataset
dataset = HDF5DatasetWriter((len(imagePaths), 512 * 7 * 7),
args["output"], dataKey="features", bufSize=args["buffer_size"])
dataset.storeClassLabels(le.classes_)
# initialize the progress bar
widgets = ["Extracting Features: ", progressbar.Percentage(), " ",
progressbar.Bar(), " ", progressbar.ETA()]
pbar = progressbar.ProgressBar(maxval=len(imagePaths),
widgets=widgets).start()
# loop over the images in patches
for i in np.arange(0, len(imagePaths), bs):
# extract the batch of images and labels, then initialize the
# list of actual images that will be passed through the network
# for feature extraction
batchPaths = imagePaths[i:i + bs]
batchLabels = labels[i:i + bs]
batchImages = []
# loop over the images and labels in the current batch
for (j, imagePath) in enumerate(batchPaths):
# load the input image using the Keras helper utility
# while ensuring the image is resized to 224x224 pixels
image = load_img(imagePath, target_size=(224, 224))
image = img_to_array(image)
# preprocess the image by (1) expanding the dimensions and
# (2) subtracting the mean RGB pixel intensity from the
# ImageNet dataset
image = np.expand_dims(image, axis=0)
image = imagenet_utils.preprocess_input(image)
# add the image to the batch
batchImages.append(image)
# pass the images through the network and use the outputs as
# our actual features
batchImages = np.vstack(batchImages)
features = model.predict(batchImages, batch_size=bs)
# reshape the features so that each image is represented by
# a flattened feature vector of the `MaxPooling2D` outputs
features = features.reshape((features.shape[0], 512 * 7 * 7)) # Tried reshaping to 224*224*3. It didnt work!
# add the features and labels to our HDF5 dataset
dataset.add(features, batchLabels)
pbar.update(i)
# close the dataset
dataset.close()
pbar.finish()