def get_Model(training):
input_shape = (img_w, img_h, 1) # (128, 64, 1)
# Make Networkw
inputs = Input(name='the_input', shape=input_shape, dtype='float32') # (None, 128, 64, 1)
# Convolution layer (VGG)
inner = Conv2D(64, (3, 3), padding='same', name='conv1', kernel_initializer='he_normal')(inputs) # (None, 128, 64, 64)
inner = BatchNormalization()(inner)
inner = Activation('relu')(inner)
inner = MaxPooling2D(pool_size=(2, 2), name='max1')(inner) # (None,64, 32, 64)
inner = Conv2D(128, (3, 3), padding='same', name='conv2', kernel_initializer='he_normal')(inner) # (None, 64, 32, 128)
inner = BatchNormalization()(inner)
inner = Activation('relu')(inner)
inner = MaxPooling2D(pool_size=(2, 2), name='max2')(inner) # (None, 32, 16, 128)
inner = Conv2D(256, (3, 3), padding='same', name='conv3', kernel_initializer='he_normal')(inner) # (None, 32, 16, 256)
inner = BatchNormalization()(inner)
inner = Activation('relu')(inner)
inner = Conv2D(256, (3, 3), padding='same', name='conv4', kernel_initializer='he_normal')(inner) # (None, 32, 16, 256)
inner = BatchNormalization()(inner)
inner = Activation('relu')(inner)
inner = MaxPooling2D(pool_size=(1, 2), name='max3')(inner) # (None, 32, 8, 256)
inner = Conv2D(512, (3, 3), padding='same', name='conv5', kernel_initializer='he_normal')(inner) # (None, 32, 8, 512)
inner = BatchNormalization()(inner)
inner = Activation('relu')(inner)
inner = Conv2D(512, (3, 3), padding='same', name='conv6')(inner) # (None, 32, 8, 512)
inner = BatchNormalization()(inner)
inner = Activation('relu')(inner)
inner = MaxPooling2D(pool_size=(1, 2), name='max4')(inner) # (None, 32, 4, 512)
inner = Conv2D(512, (2, 2), padding='same', kernel_initializer='he_normal', name='con7')(inner) # (None, 32, 4, 512)
inner = BatchNormalization()(inner)
inner = Activation('relu')(inner)
# CNN to RNN
inner = Reshape(target_shape=((32, 2048)), name='reshape')(inner) # (None, 32, 2048)
inner = Dense(64, activation='relu', kernel_initializer='he_normal', name='dense1')(inner) # (None, 32, 64)
# RNN layer
lstm_1 = CuDNNLSTM(256, return_sequences=True, kernel_initializer='he_normal', name='lstm1')(inner) # (None, 32, 512)
lstm_1b = CuDNNLSTM(256, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='lstm1_b')(inner)
lstm1_merged = add([lstm_1, lstm_1b]) # (None, 32, 512)
lstm1_merged = BatchNormalization()(lstm1_merged)
lstm_2 = CuDNNLSTM(256, return_sequences=True, kernel_initializer='he_normal', name='lstm2')(lstm1_merged)
lstm_2b = CuDNNLSTM(256, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='lstm2_b')(lstm1_merged)
lstm2_merged = concatenate([lstm_2, lstm_2b]) # (None, 32, 1024)
lstm_merged = BatchNormalization()(lstm2_merged)
# transforms RNN output to character activations:
inner = Dense(num_classes, kernel_initializer='he_normal',name='dense2')(lstm2_merged) #(None, 32, 63)
y_pred = Activation('softmax', name='softmax')(inner)
labels = Input(name='the_labels', shape=[max_text_len], dtype='float32') # (None ,8)
input_length = Input(name='input_length', shape=[1], dtype='int64') # (None, 1)
label_length = Input(name='label_length', shape=[1], dtype='int64') # (None, 1)
# Keras doesn't currently support loss funcs with extra parameters
# so CTC loss is implemented in a lambda layer
loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name='ctc')([y_pred, labels, input_length, label_length]) #(None, 1)
if training:
return Model(inputs=[inputs, labels, input_length, label_length], outputs=loss_out)
else:
return Model(inputs=[inputs], outputs=y_pred)
