forked from axinc-ai/ailia-models
-
Notifications
You must be signed in to change notification settings - Fork 0
/
etl.py
executable file
·167 lines (136 loc) · 4.51 KB
/
etl.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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
import sys
import time
import codecs
import cv2
import ailia
# import original modules
sys.path.append('../../util')
from utils import get_base_parser, update_parser # noqa: E402
from model_utils import check_and_download_models # noqa: E402
import webcamera_utils # noqa: E402
# ======================
# PARAMETERS
# ======================
MODEL_PATH = 'etl_BINARY_squeezenet128_20.prototxt'
WEIGHT_PATH = 'etl_BINARY_squeezenet128_20.caffemodel'
REMOTE_PATH = 'https://storage.googleapis.com/ailia-models/etl/'
IMAGE_PATH = 'font.png'
IMAGE_HEIGHT = 28
IMAGE_WIDTH = 28
ETL_PATH = 'etl_BINARY_squeezenet128_20.txt'
MAX_CLASS_COUNT = 3
SLEEP_TIME = 0 # for webcam mode
# ======================
# Arguemnt Parser Config
# ======================
parser = get_base_parser(
'Japanese character classification model.', IMAGE_PATH, None
)
args = update_parser(parser)
# ======================
# Utils
# ======================
def preprocess_image(img):
if img.shape[2] == 3:
img = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA)
elif img.shape[2] == 1:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGRA)
img = cv2.bitwise_not(img)
return img
# ======================
# Main functions
# ======================
def recognize_from_image():
# prepare input data
etl_word = codecs.open(ETL_PATH, 'r', 'utf-8').readlines()
img = cv2.imread(args.input, cv2.IMREAD_UNCHANGED)
img = preprocess_image(img)
# net initialize
classifier = ailia.Classifier(
MODEL_PATH,
WEIGHT_PATH,
env_id=args.env_id,
format=ailia.NETWORK_IMAGE_FORMAT_GRAY,
range=ailia.NETWORK_IMAGE_RANGE_U_FP32,
)
# inference
print('Start inference...')
if args.benchmark:
print('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
classifier.compute(img, MAX_CLASS_COUNT)
end = int(round(time.time() * 1000))
print(f'\tailia processing time {end - start} ms')
else:
classifier.compute(img, MAX_CLASS_COUNT)
# get result
count = classifier.get_class_count()
print(f'class_count: {count}')
for idx in range(count):
print(f"+ idx={idx}")
info = classifier.get_class(idx)
print(f" category={info.category} [ {etl_word[info.category]} ]")
print(f" prob={info.prob}")
def recognize_from_video():
etl_word = codecs.open(ETL_PATH, 'r', 'utf-8').readlines()
# net initialize
classifier = ailia.Classifier(
MODEL_PATH,
WEIGHT_PATH,
env_id=args.env_id,
format=ailia.NETWORK_IMAGE_FORMAT_GRAY,
range=ailia.NETWORK_IMAGE_RANGE_U_FP32,
)
capture = webcamera_utils.get_capture(args.video)
# create video writer if savepath is specified as video format
if args.savepath is not None:
f_h = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
f_w = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
save_h, save_w = webcamera_utils.calc_adjust_fsize(
f_h, f_w, IMAGE_HEIGHT, IMAGE_WIDTH
)
writer = webcamera_utils.get_writer(args.savepath, save_h, save_w)
else:
writer = None
while(True):
ret, frame = capture.read()
if (cv2.waitKey(1) & 0xFF == ord('q')) or not ret:
break
in_frame, frame = webcamera_utils.adjust_frame_size(
frame, IMAGE_HEIGHT, IMAGE_WIDTH
)
frame = preprocess_image(frame)
# inference
# compute execution time
classifier.compute(frame, MAX_CLASS_COUNT)
# get result
count = classifier.get_class_count()
print('==============================================================')
print(f'class_count: {count}')
for idx in range(count):
print(f"+ idx={idx}")
info = classifier.get_class(idx)
print(f" category={info.category} [ {etl_word[info.category]} ]")
print(f" prob={info.prob}")
cv2.imshow('frame', in_frame)
# save results
if writer is not None:
writer.write(in_frame)
time.sleep(SLEEP_TIME)
capture.release()
cv2.destroyAllWindows()
if writer is not None:
writer.release()
print('Script finished successfully.')
def main():
# model files check and download
check_and_download_models(WEIGHT_PATH, MODEL_PATH, REMOTE_PATH)
if args.video is not None:
# video mode
recognize_from_video()
else:
# image mode
recognize_from_image()
if __name__ == '__main__':
main()