Deep learning 如何实施"；多向；LSTM？

我试图实现“辍学改善手写识别的递归神经网络”一文中的LSTM体系结构：

在论文中，研究人员将多向LSTM层定义为“四个平行应用的LSTM层，每个层具有特定的扫描方向”

以下是（我认为）Keras网络的样子：

from keras.layers import LSTM, Dropout, Input, Convolution2D, Merge, Dense, Activation, TimeDistributed
from keras.models import Sequential

def build_lstm_dropout(inputdim, outputdim, return_sequences=True, activation='tanh'):
    net_input = Input(shape=(None, inputdim))
    model = Sequential()
    lstm  = LSTM(output_dim=outputdim, return_sequences=return_sequences, activation=activation)(net_input)
    model.add(lstm)
    model.add(Dropout(0.5))
    return model

def build_conv(nb_filter, nb_row, nb_col, net_input, border_mode='relu'):
    return TimeDistributed(Convolution2D( nb_filter, nb_row, nb_col, border_mode=border_mode, activation='relu')(net_input))

def build_lstm_conv(lstm, conv):
    model = Sequential()
    model.add(lstm)
    model.add(conv)
    return model

def build_merged_lstm_conv_layer(lstm_conv, mode='concat'):
    return Merge([lstm_conv, lstm_conv, lstm_conv, lstm_conv], mode=mode)

def build_model(feature_dim, loss='ctc_cost_for_train', optimizer='Adadelta'):
    net_input = Input(shape=(1, feature_dim, None))

    lstm = build_lstm_dropout(2, 6)
    conv = build_conv(64, 2, 4, net_input)

    lstm_conv = build_lstm_conv(lstm, conv)

    first_layer = build_merged_lstm_conv_layer(lstm_conv)

    lstm = build_lstm_dropout(10, 20)
    conv = build_conv(128, 2, 4, net_input)

    lstm_conv = build_lstm_conv(lstm, conv)

    second_layer = build_merged_lstm_conv_layer(lstm_conv)

    lstm = build_lstm_dropout(50, 1)
    fully_connected = Dense(1, activation='sigmoid')

    lstm_fc = Sequential()
    lstm_fc.add(lstm)
    lstm_fc.add(fully_connected)

    third_layer = Merge([lstm_fc, lstm_fc, lstm_fc, lstm_fc], mode='concat')

    final_model = Sequential()
    final_model.add(first_layer)
    final_model.add(Activation('tanh'))
    final_model.add(second_layer)
    final_model.add(Activation('tanh'))
    final_model.add(third_layer)

    final_model.compile(loss=loss, optimizer=optimizer, sample_weight_mode='temporal')

    return final_model

以下是我的问题：

如果我对体系结构的实现是正确的，您会怎么做 执行四个LSTM层的扫描方向

如果我的执行不正确，是否可以执行 这样的建筑在凯拉斯？如果没有，是否有其他框架可以帮助我实现这样的体系结构

您可以检查双向LSTM的实现。基本上，您只需为向后的LSTM设置

go_backward=True

---

但是，在您的情况下，您必须编写“镜像”+重塑层以反转行。镜像层可以看起来像（为了方便起见，我在这里使用lambda层）：

lambda（lambda x:x[：，：-1，：]）

什么是“特定扫描方向”？你的意思是它看起来像“双向RNN”，但在二维网格上？是的。从这篇论文中得出结论：使用多维递归神经网络的脱机手写识别你确定它是“多向的”吗？因为据我所知，MDLSTM代表“多维LSTM”，好吧，我试试这个。我得到结果后再打给你。你有结果吗？我仍然想知道如何实现文本识别的MDLSTM，你有什么参考资料吗？