mirror of
https://github.com/PaddlePaddle/PaddleOCR.git
synced 2025-06-03 21:53:39 +08:00
129 lines
4.5 KiB
Python
129 lines
4.5 KiB
Python
# Copyright (c) 2021 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.
|
|
from paddle_serving_server.web_service import WebService, Op
|
|
|
|
import logging
|
|
import numpy as np
|
|
import cv2
|
|
import base64
|
|
# from paddle_serving_app.reader import OCRReader
|
|
from ocr_reader import OCRReader, DetResizeForTest
|
|
from paddle_serving_app.reader import Sequential, ResizeByFactor
|
|
from paddle_serving_app.reader import Div, Normalize, Transpose
|
|
from paddle_serving_app.reader import DBPostProcess, FilterBoxes, GetRotateCropImage, SortedBoxes
|
|
|
|
import yaml
|
|
from argparse import ArgumentParser,RawDescriptionHelpFormatter
|
|
|
|
_LOGGER = logging.getLogger()
|
|
|
|
class ArgsParser(ArgumentParser):
|
|
def __init__(self):
|
|
super(ArgsParser, self).__init__(
|
|
formatter_class=RawDescriptionHelpFormatter)
|
|
self.add_argument("-c", "--config", help="configuration file to use")
|
|
self.add_argument(
|
|
"-o", "--opt", nargs='+', help="set configuration options")
|
|
|
|
def parse_args(self, argv=None):
|
|
args = super(ArgsParser, self).parse_args(argv)
|
|
assert args.config is not None, \
|
|
"Please specify --config=configure_file_path."
|
|
args.conf_dict = self._parse_opt(args.opt, args.config)
|
|
return args
|
|
|
|
def _parse_helper(self, v):
|
|
if v.isnumeric():
|
|
if "." in v:
|
|
v = float(v)
|
|
else:
|
|
v = int(v)
|
|
elif v == "True" or v == "False":
|
|
v = (v == "True")
|
|
return v
|
|
|
|
def _parse_opt(self, opts, conf_path):
|
|
f = open(conf_path)
|
|
config = yaml.load(f, Loader=yaml.Loader)
|
|
if not opts:
|
|
return config
|
|
for s in opts:
|
|
s = s.strip()
|
|
k, v = s.split('=')
|
|
v = self._parse_helper(v)
|
|
print(k,v, type(v))
|
|
cur = config
|
|
parent = cur
|
|
for kk in k.split("."):
|
|
if kk not in cur:
|
|
cur[kk] = {}
|
|
parent = cur
|
|
cur = cur[kk]
|
|
else:
|
|
parent = cur
|
|
cur = cur[kk]
|
|
parent[k.split(".")[-1]] = v
|
|
return config
|
|
|
|
class DetOp(Op):
|
|
def init_op(self):
|
|
self.det_preprocess = Sequential([
|
|
DetResizeForTest(), Div(255),
|
|
Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]), Transpose(
|
|
(2, 0, 1))
|
|
])
|
|
self.filter_func = FilterBoxes(10, 10)
|
|
self.post_func = DBPostProcess({
|
|
"thresh": 0.3,
|
|
"box_thresh": 0.5,
|
|
"max_candidates": 1000,
|
|
"unclip_ratio": 1.5,
|
|
"min_size": 3
|
|
})
|
|
|
|
def preprocess(self, input_dicts, data_id, log_id):
|
|
(_, input_dict), = input_dicts.items()
|
|
data = base64.b64decode(input_dict["image"].encode('utf8'))
|
|
self.raw_im = data
|
|
data = np.fromstring(data, np.uint8)
|
|
# Note: class variables(self.var) can only be used in process op mode
|
|
im = cv2.imdecode(data, cv2.IMREAD_COLOR)
|
|
self.ori_h, self.ori_w, _ = im.shape
|
|
det_img = self.det_preprocess(im)
|
|
_, self.new_h, self.new_w = det_img.shape
|
|
return {"x": det_img[np.newaxis, :].copy()}, False, None, ""
|
|
|
|
def postprocess(self, input_dicts, fetch_dict, data_id, log_id):
|
|
det_out = fetch_dict["save_infer_model/scale_0.tmp_1"]
|
|
ratio_list = [
|
|
float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w
|
|
]
|
|
dt_boxes_list = self.post_func(det_out, [ratio_list])
|
|
dt_boxes = self.filter_func(dt_boxes_list[0], [self.ori_h, self.ori_w])
|
|
out_dict = {"dt_boxes": str(dt_boxes)}
|
|
|
|
return out_dict, None, ""
|
|
|
|
|
|
class OcrService(WebService):
|
|
def get_pipeline_response(self, read_op):
|
|
det_op = DetOp(name="det", input_ops=[read_op])
|
|
return det_op
|
|
|
|
|
|
uci_service = OcrService(name="ocr")
|
|
FLAGS = ArgsParser().parse_args()
|
|
uci_service.prepare_pipeline_config(yml_dict=FLAGS.conf_dict)
|
|
uci_service.run_service()
|