keras cnn_lstm输入层不接受一维输入

时间:2018-08-23 18:41:39

标签: python machine-learning keras conv-neural-network lstm

我有一些长的1_D向量序列(3000位数),我要对其进行分类。之前,我已经实现了一个简单的CNN,可以相对成功地对它们进行分类:

def create_shallow_model(shape,repeat_length,stride):
    model = Sequential()
    model.add(Conv1D(75,repeat_length,strides=stride,padding='same', input_shape=shape, activation='relu'))
    model.add(MaxPooling1D(repeat_length))
    model.add(Flatten())
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
    return model

但是我希望通过在网络末端堆叠LSTM / RNN来提高性能。

我对此感到困难,因为我似乎找不到网络接受数据的方法。

def cnn_lstm(shape,repeat_length,stride):
    model = Sequential()
    model.add(TimeDistributed(Conv1D(75,repeat_length,strides=stride,padding='same', activation='relu'),input_shape=(None,)+shape))
    model.add(TimeDistributed(MaxPooling1D(repeat_length)))
    model.add(TimeDistributed(Flatten()))
    model.add(LSTM(6,return_sequences=True))
    model.add(Dense(1,activation='sigmoid'))
    model.compile(loss='sparse_categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
    return model

model=cnn_lstm(X.shape[1:],1000,1)
tprs,aucs=calculate_roc(model,3,100,train_X,train_y,test_X,test_y,tprs,aucs)

但是出现以下错误:

ValueError: Error when checking input: expected time_distributed_4_input to have 4 dimensions, but got array with shape (50598, 3000, 1)

我的问题是:

  1. 这是分析数据的正确方法吗?

  2. 如果是这样,我如何使网络接受并分类输入序列?

1 个答案:

答案 0 :(得分:4)

无需添加这些TimeDistributed包装器。当前,在添加LSTM层之前,您的模型如下所示(我假设使用repeat_length=5stride=1):

Layer (type)                 Output Shape              Param #   
=================================================================
conv1d_2 (Conv1D)            (None, 3000, 75)          450       
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 600, 75)           0         
_________________________________________________________________
flatten_2 (Flatten)          (None, 45000)             0         
_________________________________________________________________
dense_4 (Dense)              (None, 1)                 45001     
=================================================================
Total params: 45,451
Trainable params: 45,451
Non-trainable params: 0
_________________________________________________________________

因此,如果要添加LSTM层,可以将其放在MaxPooling1D层之后,例如model.add(LSTM(16, activation='relu')),而只需删除Flatten层。现在模型看起来像这样:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1d_4 (Conv1D)            (None, 3000, 75)          450       
_________________________________________________________________
max_pooling1d_3 (MaxPooling1 (None, 600, 75)           0         
_________________________________________________________________
lstm_1 (LSTM)                (None, 16)                5888      
_________________________________________________________________
dense_5 (Dense)              (None, 1)                 17        
=================================================================
Total params: 6,355
Trainable params: 6,355
Non-trainable params: 0
_________________________________________________________________

如果需要,可以将return_sequences=True参数传递到LSTM层,并保留Flatten层。但是只有在尝试了第一种方法并且结果很差之后才做这样的事情,因为添加return_sequences=True可能根本没有必要,并且只会增加模型大小并降低模型性能。


请注意:为什么在第二个模型中将损失函数更改为sparse_categorical_crossentropy?无需这样做,因为binary_crossentropy可以正常工作。