add hubserving

deploy/hubserving/ocr_cls/config.json

@@ -0,0 +1,15 @@
+{
+ "modules_info": {
+ "ocr_cls": {
+ "init_args": {
+ "version": "1.0.0",
+ "use_gpu": true
+ },
+ "predict_args": {
+ }
+ }
+ },
+ "port": 8866,
+ "use_multiprocess": false,
+ "workers": 2
+}

deploy/hubserving/ocr_cls/module.py

@@ -0,0 +1,121 @@
+# -*- coding:utf-8 -*-
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+sys.path.insert(0, ".")
+
+from paddlehub.common.logger import logger
+from paddlehub.module.module import moduleinfo, runnable, serving
+import cv2
+import paddlehub as hub
+
+from tools.infer.utility import base64_to_cv2
+from tools.infer.predict_cls import TextClassifier
+
+
+@moduleinfo(
+ name="ocr_cls",
+ version="1.0.0",
+ summary="ocr recognition service",
+ author="paddle-dev",
+ author_email="[email protected]",
+ type="cv/text_recognition")
+class OCRCls(hub.Module):
+ def _initialize(self, use_gpu=False, enable_mkldnn=False):
+ """
+ initialize with the necessary elements
+ """
+ from ocr_cls.params import read_params
+ cfg = read_params()
+
+ cfg.use_gpu = use_gpu
+ if use_gpu:
+ try:
+ _places = os.environ["CUDA_VISIBLE_DEVICES"]
+ int(_places[0])
+ print("use gpu: ", use_gpu)
+ print("CUDA_VISIBLE_DEVICES: ", _places)
+ cfg.gpu_mem = 8000
+ except:
+ raise RuntimeError(
+ "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+ )
+ cfg.ir_optim = True
+ cfg.enable_mkldnn = enable_mkldnn
+
+ self.text_classifier = TextClassifier(cfg)
+
+ def read_images(self, paths=[]):
+ images = []
+ for img_path in paths:
+ assert os.path.isfile(
+ img_path), "The {} isn't a valid file.".format(img_path)
+ img = cv2.imread(img_path)
+ if img is None:
+ logger.info("error in loading image:{}".format(img_path))
+ continue
+ images.append(img)
+ return images
+
+ def predict(self, images=[], paths=[]):
+ """
+ Get the text angle in the predicted images.
+ Args:
+ images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
+ paths (list[str]): The paths of images. If paths not images
+ Returns:
+ res (list): The result of text detection box and save path of images.
+ """
+
+ if images != [] and isinstance(images, list) and paths == []:
+ predicted_data = images
+ elif images == [] and isinstance(paths, list) and paths != []:
+ predicted_data = self.read_images(paths)
+ else:
+ raise TypeError("The input data is inconsistent with expectations.")
+
+ assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
+
+ img_list = []
+ for img in predicted_data:
+ if img is None:
+ continue
+ img_list.append(img)
+
+ rec_res_final = []
+ try:
+ img_list, cls_res, predict_time = self.text_classifier(img_list)
+ for dno in range(len(cls_res)):
+ angle, score = cls_res[dno]
+ rec_res_final.append({
+ 'angle': angle,
+ 'confidence': float(score),
+ })
+ except Exception as e:
+ print(e)
+ return [[]]
+
+ return [rec_res_final]
+
+ @serving
+ def serving_method(self, images, **kwargs):
+ """
+ Run as a service.
+ """
+ images_decode = [base64_to_cv2(image) for image in images]
+ results = self.predict(images_decode, **kwargs)
+ return results
+
+
+if __name__ == '__main__':
+ ocr = OCRCls()
+ image_path = [
+ './doc/imgs_words/ch/word_1.jpg',
+ './doc/imgs_words/ch/word_2.jpg',
+ './doc/imgs_words/ch/word_3.jpg',
+ ]
+ res = ocr.predict(paths=image_path)
+ print(res)

deploy/hubserving/ocr_cls/params.py

@@ -0,0 +1,24 @@
+# -*- coding:utf-8 -*-
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+
+class Config(object):
+ pass
+
+
+def read_params():
+ cfg = Config()
+
+ #params for text classifier
+ cfg.cls_model_dir = "./inference/ch_ppocr_mobile_v1.1_cls_infer/"
+ cfg.cls_image_shape = "3, 48, 192"
+ cfg.label_list = ['0', '180']
+ cfg.cls_batch_num = 30
+ cfg.cls_thresh = 0.9
+
+ cfg.use_zero_copy_run = False
+ cfg.use_pdserving = False
+
+ return cfg

deploy/hubserving/ocr_det/config.json

@@ -9,7 +9,7 @@
  }
  }
  },
- "port": 8866,
+ "port": 8865,
  "use_multiprocess": false,
  "workers": 2 
 }

deploy/hubserving/ocr_det/module.py

@@ -3,20 +3,14 @@
 from __future__ import division
 from __future__ import print_function
 
-import argparse
-import ast
-import copy
-import math
 import os
-import time
+import sys
+sys.path.insert(0, ".")
 
-from paddle.fluid.core import AnalysisConfig, create_paddle_predictor, PaddleTensor
 from paddlehub.common.logger import logger
 from paddlehub.module.module import moduleinfo, runnable, serving
-from PIL import Image
 import cv2
 import numpy as np
-import paddle.fluid as fluid
 import paddlehub as hub
 
 from tools.infer.utility import base64_to_cv2
@@ -67,9 +61,7 @@ def read_images(self, paths=[]):
  images.append(img)
  return images
 
- def predict(self,
- images=[],
- paths=[]):
+ def predict(self, images=[], paths=[]):
  """
  Get the text box in the predicted images.
  Args:
@@ -87,7 +79,7 @@ def predict(self,
  raise TypeError("The input data is inconsistent with expectations.")
 
  assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
- 
+
  all_results = []
  for img in predicted_data:
  if img is None:
@@ -99,11 +91,9 @@ def predict(self,
 
  rec_res_final = []
  for dno in range(len(dt_boxes)):
- rec_res_final.append(
- {
- 'text_region': dt_boxes[dno].astype(np.int).tolist()
- }
- )
+ rec_res_final.append({
+ 'text_region': dt_boxes[dno].astype(np.int).tolist()
+ })
  all_results.append(rec_res_final)
  return all_results
 
@@ -116,12 +106,12 @@ def serving_method(self, images, **kwargs):
  results = self.predict(images_decode, **kwargs)
  return results
 
- 
+
 if __name__ == '__main__':
  ocr = OCRDet()
  image_path = [
  './doc/imgs/11.jpg',
  './doc/imgs/12.jpg',
  ]
  res = ocr.predict(paths=image_path)
- print(res)
+ print(res)

deploy/hubserving/ocr_det/params.py

@@ -10,16 +10,17 @@ class Config(object):
 
 def read_params():
  cfg = Config()
- 
+
  #params for text detector
  cfg.det_algorithm = "DB"
- cfg.det_model_dir = "./inference/ch_det_mv3_db/"
- cfg.det_max_side_len = 960
+ cfg.det_model_dir = "./inference/ch_ppocr_mobile_v1.1_det_infer/"
+ cfg.det_limit_side_len = 960
+ cfg.det_limit_type = 'max'
 
  #DB parmas
- cfg.det_db_thresh =0.3
- cfg.det_db_box_thresh =0.5
- cfg.det_db_unclip_ratio =2.0
+ cfg.det_db_thresh = 0.3
+ cfg.det_db_box_thresh = 0.5
+ cfg.det_db_unclip_ratio = 2.0
 
  # #EAST parmas
  # cfg.det_east_score_thresh = 0.8
@@ -37,5 +38,6 @@ def read_params():
  # cfg.use_space_char = True
 
  cfg.use_zero_copy_run = False
+ cfg.use_pdserving = False
 
  return cfg

deploy/hubserving/ocr_rec/module.py

@@ -3,20 +3,13 @@
 from __future__ import division
 from __future__ import print_function
 
-import argparse
-import ast
-import copy
-import math
 import os
-import time
+import sys
+sys.path.insert(0, ".")
 
-from paddle.fluid.core import AnalysisConfig, create_paddle_predictor, PaddleTensor
 from paddlehub.common.logger import logger
 from paddlehub.module.module import moduleinfo, runnable, serving
-from PIL import Image
 import cv2
-import numpy as np
-import paddle.fluid as fluid
 import paddlehub as hub
 
 from tools.infer.utility import base64_to_cv2
@@ -67,9 +60,7 @@ def read_images(self, paths=[]):
  images.append(img)
  return images
 
- def predict(self,
- images=[],
- paths=[]):
+ def predict(self, images=[], paths=[]):
  """
  Get the text box in the predicted images.
  Args:
@@ -87,31 +78,28 @@ def predict(self,
  raise TypeError("The input data is inconsistent with expectations.")
 
  assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
- 
+
  img_list = []
  for img in predicted_data:
  if img is None:
  continue
  img_list.append(img)
- 
+
  rec_res_final = []
  try:
  rec_res, predict_time = self.text_recognizer(img_list)
  for dno in range(len(rec_res)):
  text, score = rec_res[dno]
- rec_res_final.append(
- {
- 'text': text,
- 'confidence': float(score),
- }
- )
+ rec_res_final.append({
+ 'text': text,
+ 'confidence': float(score),
+ })
  except Exception as e:
  print(e)
  return [[]]
 
  return [rec_res_final]
 
-
  @serving
  def serving_method(self, images, **kwargs):
  """
@@ -121,7 +109,7 @@ def serving_method(self, images, **kwargs):
  results = self.predict(images_decode, **kwargs)
  return results
 
- 
+
 if __name__ == '__main__':
  ocr = OCRRec()
  image_path = [
@@ -130,4 +118,4 @@ def serving_method(self, images, **kwargs):
  './doc/imgs_words/ch/word_3.jpg',
  ]
  res = ocr.predict(paths=image_path)
- print(res)
+ print(res)

deploy/hubserving/ocr_rec/params.py

@@ -10,25 +10,10 @@ class Config(object):
 
 def read_params():
  cfg = Config()
-
- # #params for text detector
- # cfg.det_algorithm = "DB"
- # cfg.det_model_dir = "./inference/ch_det_mv3_db/"
- # cfg.det_max_side_len = 960
-
- # #DB parmas
- # cfg.det_db_thresh =0.3
- # cfg.det_db_box_thresh =0.5
- # cfg.det_db_unclip_ratio =2.0
-
- # #EAST parmas
- # cfg.det_east_score_thresh = 0.8
- # cfg.det_east_cover_thresh = 0.1
- # cfg.det_east_nms_thresh = 0.2
 
  #params for text recognizer
  cfg.rec_algorithm = "CRNN"
- cfg.rec_model_dir = "./inference/ch_rec_mv3_crnn/"
+ cfg.rec_model_dir = "./inference/ch_ppocr_mobile_v1.1_rec_infer/"
 
  cfg.rec_image_shape = "3, 32, 320"
  cfg.rec_char_type = 'ch'
@@ -39,5 +24,6 @@ def read_params():
  cfg.use_space_char = True
 
  cfg.use_zero_copy_run = False
+ cfg.use_pdserving = False
 
  return cfg