前回のブログ【モデル展開】PaddleOCRモデルopenvino展開（1）では、PaddleOCR検出モデルDBNetの展開方法を紹介します。この記事では、テキストの向きの分類と認識、同時に検出、向きの展開方法を紹介します。分類、およびテキスト認識モデルは直列に接続されています立ち上がって、完全な展開プロセスを提供します。
PaddleOCR：https ://github.com/PaddlePaddle/PaddleOCR
深層学習モデルを展開する場合、主に前処理と後処理の部分のコードを完成させます。検出、分類、識別の3つのモデルについても同じことが言え、前処理と後処理を完了するだけで済みます。
モデル展開の効果は次のとおりです（左が元の画像、右が検出結果です）。
識別結果は次のとおりです。
コンテンツ
まず、検出モデルの展開
検出モデル展開リファレンス：[モデル展開] PaddleOCRモデルopenvino展開（1）、この記事ではあまり紹介しません。
第二に、方向分類モデルの展開
1.分類モデルをダウンロードします
!wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar2.圧縮されたパッケージを解凍します
減圧後、以下に示すように、フライングパドルの静的グラフモデルが取得されます。
3.モデルを表示します
次の図に示すように、netronを使用してinference.pdmodel構造を表示します。主に、次の2つのポイントに焦点を当てます。（a）
モデルの出力（後続の後処理に関連）。
（b）入力の次元（設計後続の前処理へ）;
4.展開
openvinoデプロイメントコードは次のとおりです。
import cv2
import openvino
import argparse
import numpy as np
import pyclipper
from openvino.runtime import Core
from shapely.geometry import Polygon
def normalize(im, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]):
im = im.astype(np.float32, copy=False) / 255.0
im -= mean
im /= std
return im
def resize(im, target_size=608, interp=cv2.INTER_LINEAR):
if isinstance(target_size, list) or isinstance(target_size, tuple):
w = target_size[0]
h = target_size[1]
else:
w = target_size
h = target_size
im = cv2.resize(im, (w, h), interpolation=interp)
return im
class ClsPostProcess(object):
""" Convert between text-label and text-index """
def __init__(self, label_list=['0', '180'], threshold=0.9):
super(ClsPostProcess, self).__init__()
self.label_list = label_list
self.threshold = threshold
def __call__(self, preds, image=None):
pred_idxs = preds.argmax(axis=1)
assert pred_idxs.shape[0] == 1, "batch size must be 1, but got {}.".format(pred_idxs.shape[0])
direction = self.label_list[pred_idxs[0]]
if direction == '180' and preds[0, 1] > self.threshold:
image = cv2.rotate(image, 1)
return image
class ClsPredictor:
def __init__(self, model_path, target_size=(100, 32), mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], threshold=0.9):
self.target_size = target_size
self.mean = mean
self.std = std
self.model_path = model_path
self.post_process = ClsPostProcess(threshold=threshold)
def preprocess(self, image):
image = resize(image, target_size=self.target_size)
image = normalize(image, mean=self.mean, std=self.std)
return image
def predict(self, image):
if isinstance(image, str):
image = cv2.imread(image)
image_h, image_w, _ = image.shape
inputs = self.preprocess(image)
input_image = np.expand_dims(
inputs.transpose(2, 0, 1), 0
)
ie = Core()
model = ie.read_model(model=self.model_path)
compiled_model = ie.compile_model(model=model, device_name="CPU")
input_layer_ir = next(iter(compiled_model.inputs))
output_layer_ir = next(iter(compiled_model.outputs))
preds = compiled_model([input_image])[output_layer_ir]
image = self.post_process(preds, image)
return image
def parse_args():
parser = argparse.ArgumentParser(description='Model export.')
# params of training
parser.add_argument(
'--model_path',
dest='model_path',
help='The path of pdmodel for export',
type=str,
default="ch_ppocr_mobile_v2.0_cls_infer/inference.pdmodel")
parser.add_argument(
'--image_path',
dest='image_path',
help='The path of image to predict.',
type=str,
default=None)
return parser.parse_args()
if __name__ == "__main__":
args = parse_args()
model_path = args.model_path
image_path = args.image_path
cls_predictor = ClsPredictor(model_path, target_size=(100, 32), mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], threshold=0.7)
image = cls_predictor.predict(image_path)
cv2.imwrite('cls_result.png', image)
cv2.imshow('1', image)
cv2.waitKey(0)
第三に、モデルの展開を特定します
1.モデルをダウンロードします
!wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar2.圧縮されたパッケージを解凍します
3.モデル構造を表示します
認識モデルの入力は方向分類と同じであり（方向分類が直接認識されるため）、出力次元は[？、25、6625]であることがわかります。バッチサイズを示し、25は認識された文字の長さを示し、6625は文字カテゴリの数です（認識モデルには対応する辞書があり、辞書内の文字数は文字カテゴリと一致している必要があります）。
4.展開
まず、モデルに対応する辞書を用意する必要があります。コードは次のとおりです。
import cv2
import openvino
import argparse
import numpy as np
import pyclipper
from openvino.runtime import Core
from shapely.geometry import Polygon
def normalize(im, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]):
im = im.astype(np.float32, copy=False) / 255.0
im -= mean
im /= std
return im
def resize(im, target_size=608, interp=cv2.INTER_LINEAR):
if isinstance(target_size, list) or isinstance(target_size, tuple):
w = target_size[0]
h = target_size[1]
else:
w = target_size
h = target_size
im = cv2.resize(im, (w, h), interpolation=interp)
return im
class BaseRecLabelDecode(object):
""" Convert between text-label and text-index """
def __init__(self, character_dict_path=None, use_space_char=False):
self.beg_str = "sos"
self.end_str = "eos"
self.character_str = []
if character_dict_path is None:
self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
dict_character = list(self.character_str)
else:
with open(character_dict_path, "rb") as fin:
lines = fin.readlines()
for line in lines:
line = line.decode('utf-8').strip("\n").strip("\r\n")
self.character_str.append(line)
if use_space_char:
self.character_str.append(" ")
dict_character = list(self.character_str)
dict_character = self.add_special_char(dict_character)
self.dict = {}
for i, char in enumerate(dict_character):
self.dict[char] = i
self.character = dict_character
def add_special_char(self, dict_character):
return dict_character
def decode(self, text_index, text_prob=None, is_remove_duplicate=False):
""" convert text-index into text-label. """
result_list = []
ignored_tokens = self.get_ignored_tokens()
batch_size = len(text_index)
for batch_idx in range(batch_size):
char_list = []
conf_list = []
for idx in range(len(text_index[batch_idx])):
if text_index[batch_idx][idx] in ignored_tokens:
continue
if is_remove_duplicate:
# only for predict
if idx > 0 and text_index[batch_idx][idx - 1] == text_index[
batch_idx][idx]:
continue
char_list.append(self.character[int(text_index[batch_idx][
idx])])
if text_prob is not None:
conf_list.append(text_prob[batch_idx][idx])
else:
conf_list.append(1)
text = ''.join(char_list)
result_list.append((text, np.mean(conf_list)))
return result_list
def get_ignored_tokens(self):
return [0] # for ctc blank
class CTCLabelDecode(BaseRecLabelDecode):
""" Convert between text-label and text-index """
def __init__(self, character_dict_path=None, use_space_char=False,
**kwargs):
super(CTCLabelDecode, self).__init__(character_dict_path,
use_space_char)
def __call__(self, preds, label=None, *args, **kwargs):
if isinstance(preds, (tuple, list)):
preds = preds[-1]
preds_idx = preds.argmax(axis=2)
preds_prob = preds.max(axis=2)
text = self.decode(preds_idx, preds_prob, is_remove_duplicate=True)
if label is None:
return text
label = self.decode(label)
return text, label
def add_special_char(self, dict_character):
dict_character = ['blank'] + dict_character
return dict_character
class RecPredictor:
def __init__(self, model_path, character_dict_path, target_size=(100, 32), mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], use_space_char=False):
self.target_size = target_size
self.mean = mean
self.std = std
self.model_path = model_path
self.post_process = CTCLabelDecode(character_dict_path=character_dict_path, use_space_char=use_space_char)
def preprocess(self, image):
image = resize(image, target_size=self.target_size)
#cv2.imshow('rec', image)
#cv2.waitKey(0)
image = normalize(image, mean=self.mean, std=self.std)
return image
def predict(self, image):
if isinstance(image, str):
image = cv2.imread(image)
image_h, image_w, _ = image.shape
inputs = self.preprocess(image)
input_image = np.expand_dims(
inputs.transpose(2, 0, 1), 0
)
ie = Core()
model = ie.read_model(model=self.model_path)
compiled_model = ie.compile_model(model=model, device_name="CPU")
input_layer_ir = next(iter(compiled_model.inputs))
output_layer_ir = next(iter(compiled_model.outputs))
preds = compiled_model([input_image])[output_layer_ir]
text = self.post_process(preds)
return text
def parse_args():
parser = argparse.ArgumentParser(description='Model export.')
# params of training
parser.add_argument(
'--model_path',
dest='model_path',
help='The path of pdmodel for export',
type=str,
default=None)
parser.add_argument(
'--image_path',
dest='image_path',
help='The path of image to predict.',
type=str,
default=None)
parser.add_argument(
'--use_space_char',
dest='use_space_char',
help='Whether use space char.',
type=bool,
default=False)
parser.add_argument(
'--character_dict_path',
dest='character_dict_path',
help='The path of character dict.',
type=str,
default="ppocr_keys_v1.txt")
return parser.parse_args()
if __name__ == "__main__":
args = parse_args()
model_path = args.model_path
image_path = args.image_path
use_space_char = args.use_space_char
character_dict_path = args.character_dict_path
rec_predictor = RecPredictor(model_path, character_dict_path=character_dict_path, target_size=(100, 32), mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], use_space_char=use_space_char)
text = rec_predictor.predict(image_path)
print(text)
第4に、検出+分類+識別のシリアル展開
3つのモデルのそれぞれのデプロイメントコードを使用して、次のようにそれらをつなぎ合わせます（すべてのコードについては、記事の最後を参照してください）。
import cv2
import openvino
import argparse
import numpy as np
import pyclipper
from openvino.runtime import Core
from shapely.geometry import Polygon
from ppocr_cls import ClsPredictor
from ppocr_det import DetPredictor
from ppocr_rec import RecPredictor
from PIL import Image, ImageDraw, ImageFont
class PaddleOCR:
def __init__(self, det_model_path, rec_model_path, character_dict_path, cls_model_path=None, use_space_char=False, det_image_size=[960, 960], rec_image_size=[100, 32], mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]):
self.det_predictor = DetPredictor(det_model_path, target_size=det_image_size, mean=mean, std=std)
self.cls_predictor = ClsPredictor(cls_model_path, target_size=rec_image_size, mean=mean, std=std) if cls_model_path else None
self.rec_predictor = RecPredictor(rec_model_path, character_dict_path=character_dict_path, target_size=rec_image_size, mean=mean, std=std, use_space_char=use_space_char)
def predict(self, image_path):
image = cv2.imread(image_path)
raw_image = image.copy()
boxes_batch = self.det_predictor.predict(image_path)
draw_image = self.det_predictor.draw_det(image, boxes_batch[0]['points'])
texts = []
for box in boxes_batch[0]['points']:
box = box.astype(np.int32)
left, top = box[0, 0], box[0, 1]
right, bottom = box[2, 0], box[2, 1]
sub_image = raw_image[top:bottom, left:right, :]
if self.cls_predictor is not None:
sub_image = self.cls_predictor.predict(sub_image)
text = self.rec_predictor.predict(sub_image)
texts.append(text)
return draw_image, texts
def parse_args():
parser = argparse.ArgumentParser(description='Model export.')
# params of training
parser.add_argument(
'--det_model_path',
dest='det_model_path',
help='The path of detection pdmodel for export',
type=str,
default='ch_PP-OCRv2_det_infer/inference.pdmodel')
parser.add_argument(
'--rec_model_path',
dest='rec_model_path',
help='The path of recognition pdmodel for export',
type=str,
default="ch_PP-OCRv2_rec_infer/inference.pdmodel")
parser.add_argument(
'--cls_model_path',
dest='cls_model_path',
help='The path of direction class pdmodel for export',
type=str,
default="ch_ppocr_mobile_v2.0_cls_infer/inference.pdmodel")
parser.add_argument(
'--image_path',
dest='image_path',
help='The path of image to predict.',
type=str,
default=None)
parser.add_argument(
'--save_path',
dest='save_path',
help='The image save path.',
type=str,
default="result.png")
parser.add_argument(
'--use_space_char',
dest='use_space_char',
help='Whether use space char.',
type=bool,
default=True)
parser.add_argument(
'--character_dict_path',
dest='character_dict_path',
help='The path of character dict.',
type=str,
default="ppocr_keys_v1.txt")
return parser.parse_args()
if __name__ == "__main__":
args = parse_args()
predictor = PaddleOCR(det_model_path=args.det_model_path, rec_model_path=args.rec_model_path, character_dict_path=args.character_dict_path, cls_model_path=args.cls_model_path, use_space_char=args.use_space_char)
draw_image, texts = predictor.predict(args.image_path)
cv2.imwrite(args.save_path, draw_image)
print(texts)
5.リファレンス
1.この記事のすべてのコードリンク：pp-ocrv2pythonopenvinoデプロイメントコード-ディープラーニングドキュメントリソース-CSDNダウンロード