Двунаправленный LSTM со слоем внимания tf.keras

Question

Я пытаюсь добавить механизм внимания к модели ниже. Действительно ли существует потребность в потере CT C для модели внимания.
Как можно реализовать BLSTM с механизмом внимания для проблемы распознавания изображений.

def ctc_lambda_func(args):
    y_pred, labels, input_length, label_length = args
    # the 2 is critical here since the first couple outputs of the RNN
    # tend to be garbage:
    y_pred = y_pred[:, 2:, :]
    return tf.keras.backend.ctc_batch_cost(labels, y_pred, input_length, label_length)




def get_Model(training):

    input_shape = (img_w, img_h, 1)     # (128, 64, 1)
    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)

    # 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
    lstm1 = Bidirectional(LSTM(512, return_sequences=True, kernel_initializer='he_normal'), name='biLSTM1') (inner)
    lstm1_norm = BatchNormalization()(lstm1)

    lstm2 = Bidirectional(LSTM(512, return_sequences=True, kernel_initializer='he_normal'), name='biLSTM2') (lstm1_norm)
    lstm2_norm = BatchNormalization()(lstm2)

    # transforms RNN output to character activations:
    inner = Dense(num_classes, kernel_initializer='he_normal',name='dense2')(lstm2_norm) #(None, 32, 63)
    y_pred = Activation('softmax', name='softmax')(inner)


    # 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)```


Is lstm1 is encoder and lstm2 is decoder?
I didn't find any attention implementation using keras functional api and also it seems there is no keras attention layer.