File size: 7,484 Bytes
a89d9fd |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 |
# 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://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.
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 numpy as np
import time
import json
import tools.infer.utility as utility
from ppocr.data import create_operators, transform
from ppocr.postprocess import build_post_process
from ppocr.utils.logging import get_logger
from ppocr.utils.utility import get_image_file_list, check_and_read
from ppocr.utils.visual import draw_rectangle
from ppstructure.utility import parse_args
logger = get_logger()
def build_pre_process_list(args):
resize_op = {'ResizeTableImage': {'max_len': args.table_max_len, }}
pad_op = {
'PaddingTableImage': {
'size': [args.table_max_len, args.table_max_len]
}
}
normalize_op = {
'NormalizeImage': {
'std': [0.229, 0.224, 0.225] if
args.table_algorithm not in ['TableMaster'] else [0.5, 0.5, 0.5],
'mean': [0.485, 0.456, 0.406] if
args.table_algorithm not in ['TableMaster'] else [0.5, 0.5, 0.5],
'scale': '1./255.',
'order': 'hwc'
}
}
to_chw_op = {'ToCHWImage': None}
keep_keys_op = {'KeepKeys': {'keep_keys': ['image', 'shape']}}
if args.table_algorithm not in ['TableMaster']:
pre_process_list = [
resize_op, normalize_op, pad_op, to_chw_op, keep_keys_op
]
else:
pre_process_list = [
resize_op, pad_op, normalize_op, to_chw_op, keep_keys_op
]
return pre_process_list
class TableStructurer(object):
def __init__(self, args):
self.args = args
self.use_onnx = args.use_onnx
pre_process_list = build_pre_process_list(args)
if args.table_algorithm not in ['TableMaster']:
postprocess_params = {
'name': 'TableLabelDecode',
"character_dict_path": args.table_char_dict_path,
'merge_no_span_structure': args.merge_no_span_structure
}
else:
postprocess_params = {
'name': 'TableMasterLabelDecode',
"character_dict_path": args.table_char_dict_path,
'box_shape': 'pad',
'merge_no_span_structure': args.merge_no_span_structure
}
self.preprocess_op = create_operators(pre_process_list)
self.postprocess_op = build_post_process(postprocess_params)
self.predictor, self.input_tensor, self.output_tensors, self.config = \
utility.create_predictor(args, 'table', logger)
if args.benchmark:
import auto_log
pid = os.getpid()
gpu_id = utility.get_infer_gpuid()
self.autolog = auto_log.AutoLogger(
model_name="table",
model_precision=args.precision,
batch_size=1,
data_shape="dynamic",
save_path=None, #args.save_log_path,
inference_config=self.config,
pids=pid,
process_name=None,
gpu_ids=gpu_id if args.use_gpu else None,
time_keys=[
'preprocess_time', 'inference_time', 'postprocess_time'
],
warmup=0,
logger=logger)
def __call__(self, img):
starttime = time.time()
if self.args.benchmark:
self.autolog.times.start()
ori_im = img.copy()
data = {'image': img}
data = transform(data, self.preprocess_op)
img = data[0]
if img is None:
return None, 0
img = np.expand_dims(img, axis=0)
img = img.copy()
if self.args.benchmark:
self.autolog.times.stamp()
if self.use_onnx:
input_dict = {}
input_dict[self.input_tensor.name] = img
outputs = self.predictor.run(self.output_tensors, input_dict)
else:
self.input_tensor.copy_from_cpu(img)
self.predictor.run()
outputs = []
for output_tensor in self.output_tensors:
output = output_tensor.copy_to_cpu()
outputs.append(output)
if self.args.benchmark:
self.autolog.times.stamp()
preds = {}
preds['structure_probs'] = outputs[1]
preds['loc_preds'] = outputs[0]
shape_list = np.expand_dims(data[-1], axis=0)
post_result = self.postprocess_op(preds, [shape_list])
structure_str_list = post_result['structure_batch_list'][0]
bbox_list = post_result['bbox_batch_list'][0]
structure_str_list = structure_str_list[0]
structure_str_list = [
'<html>', '<body>', '<table>'
] + structure_str_list + ['</table>', '</body>', '</html>']
elapse = time.time() - starttime
if self.args.benchmark:
self.autolog.times.end(stamp=True)
return (structure_str_list, bbox_list), elapse
def main(args):
image_file_list = get_image_file_list(args.image_dir)
table_structurer = TableStructurer(args)
count = 0
total_time = 0
os.makedirs(args.output, exist_ok=True)
with open(
os.path.join(args.output, 'infer.txt'), mode='w',
encoding='utf-8') as f_w:
for image_file in image_file_list:
img, flag, _ = check_and_read(image_file)
if not flag:
img = cv2.imread(image_file)
if img is None:
logger.info("error in loading image:{}".format(image_file))
continue
structure_res, elapse = table_structurer(img)
structure_str_list, bbox_list = structure_res
bbox_list_str = json.dumps(bbox_list.tolist())
logger.info("result: {}, {}".format(structure_str_list,
bbox_list_str))
f_w.write("result: {}, {}\n".format(structure_str_list,
bbox_list_str))
if len(bbox_list) > 0 and len(bbox_list[0]) == 4:
img = draw_rectangle(image_file, bbox_list)
else:
img = utility.draw_boxes(img, bbox_list)
img_save_path = os.path.join(args.output,
os.path.basename(image_file))
cv2.imwrite(img_save_path, img)
logger.info("save vis result to {}".format(img_save_path))
if count > 0:
total_time += elapse
count += 1
logger.info("Predict time of {}: {}".format(image_file, elapse))
if args.benchmark:
table_structurer.autolog.report()
if __name__ == "__main__":
main(parse_args())
|