Question

我正在尝试使用Keras建立LTSM模型。训练数据的尺寸为[7165，27]，在我当前的设置下，它会引发以下错误：

  File "C:\Users\Eier\Anaconda3\lib\site-packages\keras\models.py", line 441, in __init__
    self.add(layer)

  File "C:\Users\Eier\Anaconda3\lib\site-packages\keras\models.py", line 497, in add
    layer(x)

  File "C:\Users\Eier\Anaconda3\lib\site-packages\keras\layers\recurrent.py", line 500, in __call__
    return super(RNN, self).__call__(inputs, **kwargs)

  File "C:\Users\Eier\Anaconda3\lib\site-packages\keras\engine\topology.py", line 575, in __call__
    self.assert_input_compatibility(inputs)

  File "C:\Users\Eier\Anaconda3\lib\site-packages\keras\engine\topology.py", line 474, in assert_input_compatibility
    str(K.ndim(x)))

ValueError: Input 0 is incompatible with layer lstm_64: expected ndim=3, found ndim=4

我知道这个错误相当普遍，但是网上找到的许多不同解决方案中没有一个对我有用。我已经尝试过将训练数据重塑为3D矩阵，用不同的图层组合鬼混，明确说明批处理大小，使用Flatten（）等等都无济于事。如果有人能朝正确的方向推动我解决这个问题，将不胜感激。

代码段：

input_dim = 27
units = 5
timesteps = 1 
samples =  X_train.shape[0]

X_train = np.reshape(X_train, (X_train.shape[0], 1, X_train.shape[1]))
X_test = np.reshape(X_test, (X_test.shape[0], 1, X_test.shape[1]))

model = Sequential([
    LSTM(units, return_sequences=True, stateful = True, input_shape=(samples,timesteps,input_dim)),
    Dropout(0.2),
    LSTM(units,return_sequences=False),
    Dropout(0.2),
    Dense(1),
    Activation('softmax'),
])

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['acc'])
model.fit(X_train, y_train, batch_size = 32, epochs = 60)

Answer 1

正如@ShubhamPanchal在评论中指出的那样，您无需指定样本尺寸。 LSTM层期望输入具有[batch_size，time_steps，通道）的形状，因此，当您传递input_shape参数时，您必须传递指定time_steps和通道尺寸的元组。

LSTM(32, return_sequences=True, stateful = True, input_shape=(time_steps, input_dim))

由于使用的是有状态的lstm，因此还需要指定batch_size参数。因此，该模型的完整代码应为

model = Sequential([
    LSTM(units, return_sequences=True, stateful = True, input_shape=(timesteps,input_dim), batch_size=batch_size),
    Dropout(0.2),
    LSTM(units,return_sequences=False),
    Dropout(0.2),
    Dense(1),
    Activation('softmax'),
])

LTSM-图层不兼容，尺寸不匹配？

1 个答案: