LSTM 和 CNN：ValueError：检查目标时出错：预期 time_distributed_1 有 3 个维度，但得到了形状为 (400, 256) 的数组

Question

我想申请CNN，LSTM在我的数据上，我只选择了一小部分数据；我的训练数据的大小是(400,50)，我的测试数据是(200,50)。只有 CNN 模型，它工作没有任何错误，我在添加 LSTM 模型时有很多错误：

model = Sequential()
model.add(Conv1D(filters=8,
                 kernel_size=16,
                 padding='valid',
                 activation='relu',
                 strides=1, input_shape=(50,1)))
model.add(MaxPooling1D(pool_size=2,strides=None, padding='valid', input_shape=(50,1))) # strides=None means strides=pool_size
model.add(Conv1D(filters=8,
                 kernel_size=8,
                 padding='valid',
                 activation='relu',
                 strides=1))
model.add(MaxPooling1D(pool_size=2,strides=None, padding='valid',input_shape=(50,1)))
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2)) # 100 num of LSTM units
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2))
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2))
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2))
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2))
model.add(TimeDistributed(Dense(256, activation='softmax')))

# # # 4. Compile model
print('########################### Compilation of the model ######################################')
model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
print(model.summary())
print('###########################Fitting the model ######################################')
# # # # # 5. Fit model on training data
x_train = x_train.reshape((400,50,1))
print(x_train.shape) # (400,50,1)
x_test = x_test.reshape((200,50,1))
print(x_test.shape) # (200,50,1)
model.fit(x_train, y_train, batch_size=100, epochs=100,verbose=0)
print(model.summary()) 
# # # # # 6. Evaluate model on test data
score = model.evaluate(x_test, y_test, verbose=0)
print (score)

这是错误：

Traceback (most recent call last):
  File "CNN_LSTM_Based_Attack.py", line 156, in <module>
    model.fit(x_train, y_train, batch_size=100, epochs=100,verbose=0)
  File "/home/doc/.local/lib/python2.7/site-packages/keras/models.py", line 853, in fit
    initial_epoch=initial_epoch)
  File "/home/doc/.local/lib/python2.7/site-packages/keras/engine/training.py", line 1424, in fit
    batch_size=batch_size)
  File "/home/doc/.local/lib/python2.7/site-packages/keras/engine/training.py", line 1304, in _standardize_user_data
    exception_prefix='target')
  File "/home/doc/.local/lib/python2.7/site-packages/keras/engine/training.py", line 127, in _standardize_input_data
    str(array.shape))
ValueError: Error when checking target: expected time_distributed_1 to have 3 dimensions, but got array with shape (400, 256)

您可以在此处找到此模型的完整摘要：（我是 LSTM 新手，这是我第一次使用它）。

_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
conv1d_1 (Conv1D)            (None, 35, 8)             136
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 17, 8)             0
_________________________________________________________________
dropout_1 (Dropout)          (None, 17, 8)             0
_________________________________________________________________
conv1d_2 (Conv1D)            (None, 10, 8)             520
_________________________________________________________________
max_pooling1d_2 (MaxPooling1 (None, 5, 8)              0
_________________________________________________________________
dropout_2 (Dropout)          (None, 5, 8)              0
_________________________________________________________________
lstm_1 (LSTM)                (None, 5, 32)             5248
_________________________________________________________________
lstm_2 (LSTM)                (None, 5, 32)             8320
_________________________________________________________________
lstm_3 (LSTM)                (None, 5, 32)             8320
_________________________________________________________________
lstm_4 (LSTM)                (None, 5, 32)             8320
_________________________________________________________________
lstm_5 (LSTM)                (None, 5, 32)             8320
_________________________________________________________________
time_distributed_1 (TimeDist (None, 5, 256)            8448
=================================================================
Total params: 47,632
Trainable params: 47,632
Non-trainable params: 0
_________________________________________________________________

当我替换这行代码时：

model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2)) # 100 num of LSTM units
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2))
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2))
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2))
model.add(LSTM(32, return_sequences=True,
              activation='tanh', recurrent_activation='hard_sigmoid',
              dropout=0.2,recurrent_dropout=0.2))
model.add(TimeDistributed(Dense(256, activation='softmax')))

只有这一行：

model.add(LSTM(26, activation='tanh'))

比它工作得很好。

如果你能帮助我，我将不胜感激。

Answer 1

所以 LSTM 层期望输入形状（样本、时间步长、特征）。堆叠 LSTM 时，您应该 return_sequences = True。这将给出形状的输出（样本、时间步长、单位），从而允许堆栈组合在一起 - 如果您只想预测一个步骤（即下一个值），您应该在最后一个 LSTM 层上设置 return_sequences = False在序列/时间序列中） - 如果您不这样做，它将预测与输入中相同数量的时间步长。您当然也可以预测不同的数字（例如，给定过去的 50 个观察结果预测接下来的 10 个，但在 Keras 中有点棘手）。

在您的情况下，Conv/MaxPool-layers 输出 5 个“时间步长”，并且您在最后一个 LSTM 层上具有 return_sequences = True - 所以您的“y”必须具有形状 (Samples, 5, 256) - 否则打开 return_sequences = False最后一层，不要使用 TimeDistributed，因为您只预测一个时间步长。