forked from PaddlePaddle/PaddleOCR
-
Notifications
You must be signed in to change notification settings - Fork 0
/
infer_kie.py
executable file
·176 lines (152 loc) · 6.15 KB
/
infer_kie.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
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http:https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import paddle.nn.functional as F
import os
import sys
__dir__ = os.path.dirname(os.path.abspath(__file__))
sys.path.append(__dir__)
sys.path.insert(0, os.path.abspath(os.path.join(__dir__, '..')))
os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
import cv2
import paddle
from ppocr.data import create_operators, transform
from ppocr.modeling.architectures import build_model
from ppocr.utils.save_load import load_model
import tools.program as program
import time
def read_class_list(filepath):
ret = {}
with open(filepath, "r") as f:
lines = f.readlines()
for idx, line in enumerate(lines):
ret[idx] = line.strip("\n")
return ret
def draw_kie_result(batch, node, idx_to_cls, count):
img = batch[6].copy()
boxes = batch[7]
h, w = img.shape[:2]
pred_img = np.ones((h, w * 2, 3), dtype=np.uint8) * 255
max_value, max_idx = paddle.max(node, -1), paddle.argmax(node, -1)
node_pred_label = max_idx.numpy().tolist()
node_pred_score = max_value.numpy().tolist()
for i, box in enumerate(boxes):
if i >= len(node_pred_label):
break
new_box = [[box[0], box[1]], [box[2], box[1]], [box[2], box[3]],
[box[0], box[3]]]
Pts = np.array([new_box], np.int32)
cv2.polylines(
img, [Pts.reshape((-1, 1, 2))],
True,
color=(255, 255, 0),
thickness=1)
x_min = int(min([point[0] for point in new_box]))
y_min = int(min([point[1] for point in new_box]))
pred_label = node_pred_label[i]
if pred_label in idx_to_cls:
pred_label = idx_to_cls[pred_label]
pred_score = '{:.2f}'.format(node_pred_score[i])
text = pred_label + '(' + pred_score + ')'
cv2.putText(pred_img, text, (x_min * 2, y_min),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 1)
vis_img = np.ones((h, w * 3, 3), dtype=np.uint8) * 255
vis_img[:, :w] = img
vis_img[:, w:] = pred_img
save_kie_path = os.path.dirname(config['Global'][
'save_res_path']) + "/kie_results/"
if not os.path.exists(save_kie_path):
os.makedirs(save_kie_path)
save_path = os.path.join(save_kie_path, str(count) + ".png")
cv2.imwrite(save_path, vis_img)
logger.info("The Kie Image saved in {}".format(save_path))
def write_kie_result(fout, node, data):
"""
Write infer result to output file, sorted by the predict label of each line.
The format keeps the same as the input with additional score attribute.
"""
import json
label = data['label']
annotations = json.loads(label)
max_value, max_idx = paddle.max(node, -1), paddle.argmax(node, -1)
node_pred_label = max_idx.numpy().tolist()
node_pred_score = max_value.numpy().tolist()
res = []
for i, label in enumerate(node_pred_label):
pred_score = '{:.2f}'.format(node_pred_score[i])
pred_res = {
'label': label,
'transcription': annotations[i]['transcription'],
'score': pred_score,
'points': annotations[i]['points'],
}
res.append(pred_res)
res.sort(key=lambda x: x['label'])
fout.writelines([json.dumps(res, ensure_ascii=False) + '\n'])
def main():
global_config = config['Global']
# build model
model = build_model(config['Architecture'])
load_model(config, model)
# create data ops
transforms = []
for op in config['Eval']['dataset']['transforms']:
transforms.append(op)
data_dir = config['Eval']['dataset']['data_dir']
ops = create_operators(transforms, global_config)
save_res_path = config['Global']['save_res_path']
class_path = config['Global']['class_path']
idx_to_cls = read_class_list(class_path)
os.makedirs(os.path.dirname(save_res_path), exist_ok=True)
model.eval()
warmup_times = 0
count_t = []
with open(save_res_path, "w") as fout:
with open(config['Global']['infer_img'], "rb") as f:
lines = f.readlines()
for index, data_line in enumerate(lines):
if index == 10:
warmup_t = time.time()
data_line = data_line.decode('utf-8')
substr = data_line.strip("\n").split("\t")
img_path, label = data_dir + "/" + substr[0], substr[1]
data = {'img_path': img_path, 'label': label}
with open(data['img_path'], 'rb') as f:
img = f.read()
data['image'] = img
st = time.time()
batch = transform(data, ops)
batch_pred = [0] * len(batch)
for i in range(len(batch)):
batch_pred[i] = paddle.to_tensor(
np.expand_dims(
batch[i], axis=0))
st = time.time()
node, edge = model(batch_pred)
node = F.softmax(node, -1)
count_t.append(time.time() - st)
draw_kie_result(batch, node, idx_to_cls, index)
write_kie_result(fout, node, data)
fout.close()
logger.info("success!")
logger.info("It took {} s for predict {} images.".format(
np.sum(count_t), len(count_t)))
ips = len(count_t[warmup_times:]) / np.sum(count_t[warmup_times:])
logger.info("The ips is {} images/s".format(ips))
if __name__ == '__main__':
config, device, logger, vdl_writer = program.preprocess()
main()