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
|
#!/usr/bin/env python2
"""
classify.py is an out-of-the-box image classifer callable from the command line.
By default it configures and runs the Caffe reference ImageNet model.
"""
import numpy as np
import os
import sys
import argparse
import glob
import time
import pandas as pd
import caffe
def main(argv):
pycaffe_dir = os.path.dirname(__file__)
parser = argparse.ArgumentParser()
# Required arguments: input and output files.
parser.add_argument(
"input_file",
help="Input image, directory, or npy."
)
parser.add_argument(
"output_file",
help="Output npy filename."
)
# Optional arguments.
parser.add_argument(
"--model_def",
default=os.path.join(pycaffe_dir,
"../models/bvlc_reference_caffenet/deploy.prototxt"),
help="Model definition file."
)
parser.add_argument(
"--pretrained_model",
default=os.path.join(
pycaffe_dir,
"../models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel"),
help="Trained model weights file.")
# parser.add_argument(
# "--gpu",
# action='store_true',
# help="Switch for gpu computation."
# )
parser.add_argument(
"--center_only",
action='store_true',
help="Switch for prediction from center crop alone instead of " +
"averaging predictions across crops (default)."
)
parser.add_argument(
"--images_dim",
default='256,256',
help="Canonical 'height,width' dimensions of input images."
)
parser.add_argument(
"--mean_file",
default=os.path.join(pycaffe_dir,
'caffe/imagenet/ilsvrc_2012_mean.npy'),
help="Data set image mean of H x W x K dimensions (numpy array). " +
"Set to '' for no mean subtraction."
)
parser.add_argument(
"--input_scale",
type=float,
help="Multiply input features by this scale to finish preprocessing."
)
parser.add_argument(
"--raw_scale",
type=float,
default=255.0,
help="Multiply raw input by this scale before preprocessing."
)
parser.add_argument(
"--channel_swap",
default='2,1,0',
help="Order to permute input channels. The default converts " +
"RGB -> BGR since BGR is the Caffe default by way of OpenCV."
)
parser.add_argument(
"--ext",
default='jpg',
help="Image file extension to take as input when a directory " +
"is given as the input file."
)
parser.add_argument(
"--labels_file",
default=os.path.join(pycaffe_dir,
"../data/ilsvrc12/synset_words.txt"),
help="Readable label definition file."
)
parser.add_argument(
"--print_results",
action='store_true',
help="Write output text to stdout rather than serializing to a file."
)
args = parser.parse_args()
image_dims = [int(s) for s in args.images_dim.split(',')]
mean, channel_swap = None, None
if args.mean_file:
mean = np.load(args.mean_file)
if args.channel_swap:
channel_swap = [int(s) for s in args.channel_swap.split(',')]
# Make classifier.
classifier = caffe.Classifier(args.model_def, args.pretrained_model,
image_dims=image_dims, mean=mean,
input_scale=args.input_scale, raw_scale=args.raw_scale,
channel_swap=channel_swap)
# # Make classifier.
# classifier = caffe.Classifier(args.model_def, args.pretrained_model,
# image_dims=image_dims, gpu=args.gpu, mean=mean,
# input_scale=args.input_scale, raw_scale=args.raw_scale,
# channel_swap=channel_swap)
# if args.gpu:
# print 'GPU mode'
# Load numpy array (.npy), directory glob (*.jpg), or image file.
args.input_file = os.path.expanduser(args.input_file)
if args.input_file.endswith('npy'):
inputs = np.load(args.input_file)
elif os.path.isdir(args.input_file):
inputs = [caffe.io.load_image(im_f)
for im_f in glob.glob(args.input_file + '/*.' + args.ext)]
else:
inputs = [caffe.io.load_image(args.input_file)]
print "Classifying %d inputs." % len(inputs)
# Classify.
start = time.time()
scores = classifier.predict(inputs, not args.center_only).flatten()
print "Done in %.2f s." % (time.time() - start)
if args.print_results:
with open(args.labels_file) as f:
labels_df = pd.DataFrame([
{
'synset_id': l.strip().split(' ')[0],
'name': ' '.join(l.strip().split(' ')[1:]).split(',')[0]
}
for l in f.readlines()
])
labels = labels_df.sort('synset_id')['name'].values
indices = (-scores).argsort()[:5]
predictions = labels[indices]
meta = [
(p, '%.5f' % scores[i])
for i, p in zip(indices, predictions)
]
print meta
# Save
np.save(args.output_file, scores)
if __name__ == '__main__':
main(sys.argv)
|