Question

我正在用LSTM构建我的第一个神经网络，输入大小有误。

我猜错误在于输入参数，大小，尺寸，但我无法理解错误。

print df.shape

data_dim = 13
timesteps = 13
num_classes = 1
batch_size = 32

model = Sequential()
model.add(LSTM(32, return_sequences = True, stateful = True,
               batch_input_shape = (batch_size, timesteps, data_dim)))

model.add(LSTM(32, return_sequences = True, stateful = True))

model.add(LSTM(32, stateful = True))

model.add(Dense(1, activation = 'relu'))

#Compile.
model.compile(loss = 'binary_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
model.summary()

#Fit.
history = model.fit(data[train], label[train], epochs = iteraciones, verbose = 0)

#Eval.
scores = model.evaluate(data[test], label[test], verbose = 0)

#Save.
cvshistory.append(history)
cvscores.append(scores[1] * 100)

形状：

(303, 14)

summary:
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_19 (LSTM)               (32, 13, 32)              5888      
_________________________________________________________________
lstm_20 (LSTM)               (32, 13, 32)              8320      
_________________________________________________________________
lstm_21 (LSTM)               (32, 32)                  8320      
_________________________________________________________________
dense_171 (Dense)            (32, 1)                   33        
=================================================================
Total params: 22,561
Trainable params: 22,561
Non-trainable params: 0
_________________________________________________________________

错误输出告诉我以下内容：

---> 45   history = model.fit(data[train], label[train], epochs = iteraciones, verbose = 0)

ValueError: Error when checking input: expected lstm_19_input to have 3 dimensions, but got array with shape (226, 13)

Answer 1

LSTM需要输入形状(batch_size, timestep, feature_size)。您仅传递二维特征。由于timesteps=13，您需要在输入中再添加一个维度。

如果数据是一个numpy数组，则： data = data[..., np.newaxis]应该这样做。

现在数据的形状将为(batch_size, timesteps, feature)。 (226, 13, 1)。

使用LSTM进行序列分类，检查输入时出错

1 个答案: