Keras LSTM输入尺寸设置 [英] Keras LSTM input dimension setting

问题描述

我试图使用keras训练LSTM模型，但我认为这里出了点问题.

I was trying to train a LSTM model using keras but I think I got something wrong here.

我遇到了

ValueError:检查输入时出错:预期lstm_17_input具有 3维，但数组的形状为(10000，0，20)

ValueError: Error when checking input: expected lstm_17_input to have 3 dimensions, but got array with shape (10000, 0, 20)

我的代码看起来像

model = Sequential()
model.add(LSTM(256, activation="relu", dropout=0.25, recurrent_dropout=0.25, input_shape=(None, 20, 64)))
model.add(Dense(1, activation="sigmoid"))
model.compile(loss='binary_crossentropy',
          optimizer='adam',
          metrics=['accuracy'])
model.fit(X_train, y_train,
      batch_size=batch_size,
      epochs=10)

其中X_train的形状为(10000, 20)，而前几个数据点类似于

where X_train has a shape of (10000, 20) and the first few data points are like

array([[ 0,  0,  0, ..., 40, 40,  9],
   [ 0,  0,  0, ..., 33, 20, 51],
   [ 0,  0,  0, ..., 54, 54, 50],
...

和y_train的形状为(10000, )，是二进制(0/1)标签数组.

and y_train has a shape of (10000, ), which is a binary (0/1) label array.

有人可以指出我在哪里错了吗?

Could someone point out where I was wrong here?

推荐答案

为了完整起见，这就是发生的情况.

For the sake of completeness, here's what's happened.

首先，LSTM像Keras中的所有图层一样，接受两个参数:input_shape和batch_input_shape.区别在于习惯上input_shape 不包含批次大小，而batch_input_shape是包括批次大小的完整输入形状.

First up, LSTM, like all layers in Keras, accepts two arguments: input_shape and batch_input_shape. The difference is in convention that input_shape does not contain the batch size, while batch_input_shape is the full input shape including the batch size.

因此，规范input_shape=(None, 20, 64)告诉keras期望4维输入，这不是您想要的.正确的应该是(20,).

Hence, the specification input_shape=(None, 20, 64) tells keras to expect a 4-dimensional input, which is not what you want. The correct would have been just (20,).

但这还不是全部. LSTM层是循环层，因此需要3维输入(batch_size, timesteps, input_dim).这就是为什么正确的规范是input_shape=(20, 1)或batch_input_shape=(10000, 20, 1)的原因.另外，您的训练数组也应重新设计以表示它具有20时间步长和每个步骤1输入功能.

But that's not all. LSTM layer is a recurrent layer, hence it expects a 3-dimensional input (batch_size, timesteps, input_dim). That's why the correct specification is input_shape=(20, 1) or batch_input_shape=(10000, 20, 1). Plus, your training array should also be reshaped to denote that it has 20 time steps and 1 input feature per each step.

因此，解决方案:

X_train = np.expand_dims(X_train, 2)  # makes it (10000,20,1)
...
model = Sequential()
model.add(LSTM(..., input_shape=(20, 1)))

这篇关于Keras LSTM输入尺寸设置的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！