forked from argman/EAST
-
Notifications
You must be signed in to change notification settings - Fork 0
/
eval.py
196 lines (161 loc) · 7.33 KB
/
eval.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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
import cv2
import time
import math
import os
import numpy as np
import tensorflow as tf
import locality_aware_nms as nms_locality
import lanms
tf.app.flags.DEFINE_string('test_data_path', '/tmp/ch4_test_images/images/', '')
tf.app.flags.DEFINE_string('gpu_list', '0', '')
tf.app.flags.DEFINE_string('checkpoint_path', '/tmp/east_icdar2015_resnet_v1_50_rbox/', '')
tf.app.flags.DEFINE_string('output_dir', '/tmp/ch4_test_images/images/', '')
tf.app.flags.DEFINE_bool('no_write_images', False, 'do not write images')
import model
from icdar import restore_rectangle
FLAGS = tf.app.flags.FLAGS
def get_images():
'''
find image files in test data path
:return: list of files found
'''
files = []
exts = ['jpg', 'png', 'jpeg', 'JPG']
for parent, dirnames, filenames in os.walk(FLAGS.test_data_path):
for filename in filenames:
for ext in exts:
if filename.endswith(ext):
files.append(os.path.join(parent, filename))
break
print('Find {} images'.format(len(files)))
return files
def resize_image(im, max_side_len=2400):
'''
resize image to a size multiple of 32 which is required by the network
:param im: the resized image
:param max_side_len: limit of max image size to avoid out of memory in gpu
:return: the resized image and the resize ratio
'''
h, w, _ = im.shape
resize_w = w
resize_h = h
# limit the max side
if max(resize_h, resize_w) > max_side_len:
ratio = float(max_side_len) / resize_h if resize_h > resize_w else float(max_side_len) / resize_w
else:
ratio = 1.
resize_h = int(resize_h * ratio)
resize_w = int(resize_w * ratio)
resize_h = resize_h if resize_h % 32 == 0 else (resize_h // 32 - 1) * 32
resize_w = resize_w if resize_w % 32 == 0 else (resize_w // 32 - 1) * 32
resize_h = max(32, resize_h)
resize_w = max(32, resize_w)
im = cv2.resize(im, (int(resize_w), int(resize_h)))
ratio_h = resize_h / float(h)
ratio_w = resize_w / float(w)
return im, (ratio_h, ratio_w)
def detect(score_map, geo_map, timer, score_map_thresh=0.8, box_thresh=0.1, nms_thres=0.2):
'''
restore text boxes from score map and geo map
:param score_map:
:param geo_map:
:param timer:
:param score_map_thresh: threshhold for score map
:param box_thresh: threshhold for boxes
:param nms_thres: threshold for nms
:return:
'''
if len(score_map.shape) == 4:
score_map = score_map[0, :, :, 0]
geo_map = geo_map[0, :, :, ]
# filter the score map
xy_text = np.argwhere(score_map > score_map_thresh)
# sort the text boxes via the y axis
xy_text = xy_text[np.argsort(xy_text[:, 0])]
# restore
start = time.time()
text_box_restored = restore_rectangle(xy_text[:, ::-1]*4, geo_map[xy_text[:, 0], xy_text[:, 1], :]) # N*4*2
print('{} text boxes before nms'.format(text_box_restored.shape[0]))
boxes = np.zeros((text_box_restored.shape[0], 9), dtype=np.float32)
boxes[:, :8] = text_box_restored.reshape((-1, 8))
boxes[:, 8] = score_map[xy_text[:, 0], xy_text[:, 1]]
timer['restore'] = time.time() - start
# nms part
start = time.time()
# boxes = nms_locality.nms_locality(boxes.astype(np.float64), nms_thres)
boxes = lanms.merge_quadrangle_n9(boxes.astype('float32'), nms_thres)
timer['nms'] = time.time() - start
if boxes.shape[0] == 0:
return None, timer
# here we filter some low score boxes by the average score map, this is different from the orginal paper
for i, box in enumerate(boxes):
mask = np.zeros_like(score_map, dtype=np.uint8)
cv2.fillPoly(mask, box[:8].reshape((-1, 4, 2)).astype(np.int32) // 4, 1)
boxes[i, 8] = cv2.mean(score_map, mask)[0]
boxes = boxes[boxes[:, 8] > box_thresh]
return boxes, timer
def sort_poly(p):
min_axis = np.argmin(np.sum(p, axis=1))
p = p[[min_axis, (min_axis+1)%4, (min_axis+2)%4, (min_axis+3)%4]]
if abs(p[0, 0] - p[1, 0]) > abs(p[0, 1] - p[1, 1]):
return p
else:
return p[[0, 3, 2, 1]]
def main(argv=None):
import os
os.environ['CUDA_VISIBLE_DEVICES'] = FLAGS.gpu_list
try:
os.makedirs(FLAGS.output_dir)
except OSError as e:
if e.errno != 17:
raise
with tf.get_default_graph().as_default():
input_images = tf.placeholder(tf.float32, shape=[None, None, None, 3], name='input_images')
global_step = tf.get_variable('global_step', [], initializer=tf.constant_initializer(0), trainable=False)
f_score, f_geometry = model.model(input_images, is_training=False)
variable_averages = tf.train.ExponentialMovingAverage(0.997, global_step)
saver = tf.train.Saver(variable_averages.variables_to_restore())
with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess:
ckpt_state = tf.train.get_checkpoint_state(FLAGS.checkpoint_path)
model_path = os.path.join(FLAGS.checkpoint_path, os.path.basename(ckpt_state.model_checkpoint_path))
print('Restore from {}'.format(model_path))
saver.restore(sess, model_path)
im_fn_list = get_images()
for im_fn in im_fn_list:
im = cv2.imread(im_fn)[:, :, ::-1]
start_time = time.time()
im_resized, (ratio_h, ratio_w) = resize_image(im)
timer = {'net': 0, 'restore': 0, 'nms': 0}
start = time.time()
score, geometry = sess.run([f_score, f_geometry], feed_dict={input_images: [im_resized]})
timer['net'] = time.time() - start
boxes, timer = detect(score_map=score, geo_map=geometry, timer=timer)
print('{} : net {:.0f}ms, restore {:.0f}ms, nms {:.0f}ms'.format(
im_fn, timer['net']*1000, timer['restore']*1000, timer['nms']*1000))
if boxes is not None:
boxes = boxes[:, :8].reshape((-1, 4, 2))
boxes[:, :, 0] /= ratio_w
boxes[:, :, 1] /= ratio_h
duration = time.time() - start_time
print('[timing] {}'.format(duration))
# save to file
if boxes is not None:
res_file = os.path.join(
FLAGS.output_dir,
'{}.txt'.format(
os.path.basename(im_fn).split('.')[0]))
with open(res_file, 'w') as f:
for box in boxes:
# to avoid submitting errors
box = sort_poly(box.astype(np.int32))
if np.linalg.norm(box[0] - box[1]) < 5 or np.linalg.norm(box[3]-box[0]) < 5:
continue
f.write('{},{},{},{},{},{},{},{}\r\n'.format(
box[0, 0], box[0, 1], box[1, 0], box[1, 1], box[2, 0], box[2, 1], box[3, 0], box[3, 1],
))
cv2.polylines(im[:, :, ::-1], [box.astype(np.int32).reshape((-1, 1, 2))], True, color=(255, 255, 0), thickness=1)
if not FLAGS.no_write_images:
img_path = os.path.join(FLAGS.output_dir, os.path.basename(im_fn))
cv2.imwrite(img_path, im[:, :, ::-1])
if __name__ == '__main__':
tf.app.run()