def __init__(self):
self.m = pymongo.MongoClient(c.getConfig("mongo", "mongouri"))
self.demo = self.m.get_database("test").get_collection("demo")
self.data = {}
def build_network(image_height=128, image_width=32):
hidden_unit = int(mod_config.getConfig("train", "hidden_unit"))
inputs = Input(shape=(image_height, image_width, 1), name='the_input')
x = Conv2D(64, (3, 3),
strides=1,
padding="same",
kernel_initializer='he_normal',
name="C0")(inputs)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=2, name="P0")(x)
x = Conv2D(128, (3, 3),
strides=1,
padding="same",
kernel_initializer='he_normal',
name="C1")(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=2, name="P1")(x)
x = Conv2D(256, (3, 3),
strides=1,
padding="same",
kernel_initializer='he_normal',
name="C2")(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Conv2D(256, (3, 3),
strides=1,
padding="same",
kernel_initializer='he_normal',
name="C3")(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = MaxPooling2D(pool_size=(2, 1), name="P2")(x)
x = Conv2D(512, (3, 3),
strides=1,
padding="same",
kernel_initializer='he_normal',
name="C4")(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Conv2D(512, (3, 3),
strides=1,
padding="same",
kernel_initializer='he_normal',
name="C5")(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = MaxPooling2D(pool_size=(2, 1), name="P3")(x)
x = Conv2D(512, (2, 2),
strides=1,
padding="same",
kernel_initializer='he_normal',
name="C6")(x) # padding="valid")
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Permute((2, 1, 3))(x)
x = TimeDistributed(Flatten())(x)
# x = Bidirectional(GRU(hidden_unit, return_sequences=True, kernel_initializer='he_normal'), merge_mode='sum')(x)
# x = BatchNormalization()(x)
#
# x = Bidirectional(GRU(hidden_unit, return_sequences=True, kernel_initializer='he_normal'), merge_mode='concat')(x)
# x = BatchNormalization()(x)
# RNN layer
gru_1a = GRU(hidden_unit,
return_sequences=True,
kernel_initializer='he_normal',
name='gru_1a')(x)
gru_1b = GRU(hidden_unit,
return_sequences=True,
kernel_initializer='he_normal',
name='gru_1b',
go_backwards=True)(x)
gru_1merged = add([gru_1a, gru_1b])
x = BatchNormalization()(gru_1merged)
gru_2a = GRU(256,
return_sequences=True,
kernel_initializer='he_normal',
name='gru_2a')(x)
gru_2b = GRU(256,
return_sequences=True,
kernel_initializer='he_normal',
name='gru_2b',
go_backwards=True)(x)
gru_2a = add([gru_2a, x])
gru_2b = add([gru_2b, x])
gru2_merged = concatenate([gru_2a, gru_2b])
x = BatchNormalization()(gru2_merged)
x = Dense(CHAR_SET_LEN + 1, kernel_initializer='he_normal')(x)
y_pred = Activation('softmax', name='softmax')(x)
labels = Input(name='the_labels', shape=[MAX_CAPTCHA], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
loss_out = Lambda(ctc_lambda_func, output_shape=(1, ),
name='ctc')([y_pred, labels, input_length, label_length])
model = Model(inputs=[inputs, labels, input_length, label_length],
outputs=loss_out)
model.summary()
return model
if equalize == 1:
img = cv2.equalizeHist(img)
data = img[np.newaxis, :, :, np.newaxis]
label = list(
map(int,
file.replace(" ", "").split('.')[0].split('_')[0]))
# cv2.imshow("img", img)
# cv2.waitKey()
yield np.array(data), np.array(label), origin, file_path
if __name__ == '__main__':
img_height = int(mod_config.getConfig("train", "img_height"))
equalize = int(mod_config.getConfig("train", "equalize"))
model = ocr.build_network(image_height=img_height, image_width=None)
weight_file = mod_config.getConfig("train", "weight_file")
path = "../text-detection-ctpn/data/data/"
# path = "./data/true_image/"
# path = "./data/test/"
if os.path.exists(weight_file):
model.load_weights(weight_file)
basemodel = Model(inputs=model.get_layer('the_input').output,
outputs=model.get_layer('softmax').output)
count = 0
pos = 0
shape = y_pred[:, :, :].shape
ctc_decode = K.ctc_decode(y_pred[:, :, :],
input_length=np.ones(shape[0]) * shape[1])[0][0]
out = K.get_value(ctc_decode)[:, :MAX_CAPTCHA]
accur = np.sum(abs(out - Y_test), axis=1)
accur_score = len(accur[accur == 0]) * 1.0 / len(accur)
print("accur_score:", accur_score)
# print(decode_model_output(y_pred) - Y_test)
if __name__ == '__main__':
new_data = int(mod_config.getConfig("train", "new_data"))
data_set = int(mod_config.getConfig("train", "data_set"))
testing = int(mod_config.getConfig("train", "testing"))
equalize = int(mod_config.getConfig("train", "equalize"))
if new_data:
gen_data.run(data_set, equalize)
X_train = np.load("ctc/X_train.npy")
Y_train = np.load("ctc/Y_train.npy")
test_size = int(X_train.shape[0] * 0.1)
X_test = X_train[0:test_size, :, :, :]
Y_test = Y_train[0:test_size, :]
import numpy as np
import cv2
import string
sys.path.append(os.getcwd())
from ctc.generator import gen_id_card
from telephone import hand_write
from config import mod_config
# characters = string.digits + string.ascii_uppercase
characters = string.digits
# print(characters)
height = int(mod_config.getConfig("train", "img_height"))
width = int(mod_config.getConfig("train", "img_width"))
n_class = len(characters)
def gen(batch_size=32, n_len=11):
genObj = gen_id_card(height=height, width=width)
x = np.zeros((batch_size, height, width, 1), dtype=np.uint8)
y = np.zeros((batch_size, n_len), dtype=np.uint8)
for i in range(batch_size):
image_data, label, vec = genObj.gen_image(text_size=18)
image_data = cv2.adaptiveThreshold(image_data, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 9, -10)
x[i] = image_data[:, :, np.newaxis]
y[i] = [int(_) for _ in label]
return x, y