Keras LSTM多维输出错误-预期time_distributed_17具有3个维度，但数组的形状为(1824，3) [英] Keras LSTM multidimensional output error — expected time_distributed_17 to have 3 dimensions, but got array with shape (1824, 3)

问题描述

我正在尝试按顺序预测多维值，例如 [[0, 0, 2], [1, 0, 3], [2, 3, 4], [3, 2, 5], [4, 0, 6], [5, 0, 7] ... ]，并希望LSTM捕获每个[x, y, z]尺寸.

I am trying to predict multidimensional values in sequence, e.g. [[0, 0, 2], [1, 0, 3], [2, 3, 4], [3, 2, 5], [4, 0, 6], [5, 0, 7] ... ] and want each of the [x, y, z] dimensions to be captured by the LSTM.

当我尝试在以下模型上运行model.fit()时，出现标题错误

When I attempt to run model.fit() on the model below, I get the error in the title,

ValueError: Error when checking target: expected time_distributed_19 to have 3 dimensions, but got array with shape (1824, 3)

我知道输出层应该具有3维，但是在思考如何使用LSTM处理n维值序列时，我感到困惑.

I know the output layer should have three dimensions, but I'm getting confused in my thinking about how I need the LSTM to deal with my sequence of n-dimensional values.

这是我的模特.请注意，如果我取消注释某些解决方案所建议的Flatten()行，则会在model.compile()

Here is my model. Note that if I uncomment the Flatten() line as some solutions suggest, I get a nondescript AssertionError on model.compile()

# X shape: (1824, 256, 3)
# Y shape: (1824, 3)

model = Sequential()

model.add(LSTM(units=128, input_shape=(X.shape[1], X.shape[2]), return_sequences=True))
model.add(Dropout(0.2))

model.add(LSTM(units=128, return_sequences=True))
model.add(Dropout(0.2))

model.add(LSTM(units=128, return_sequences=True))
model.add(Dropout(0.2))

# model.add(Flatten())

model.add(TimeDistributed(Dense(Y.shape[1], activation='softmax')))

model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')

这是模型摘要:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_145 (LSTM)              (None, 256, 128)          67584     
_________________________________________________________________
dropout_140 (Dropout)        (None, 256, 128)          0         
_________________________________________________________________
lstm_146 (LSTM)              (None, 256, 128)          131584    
_________________________________________________________________
dropout_141 (Dropout)        (None, 256, 128)          0         
_________________________________________________________________
time_distributed_19 (TimeDis (None, 256, 3)            387       
=================================================================
Total params: 199,555
Trainable params: 199,555
Non-trainable params: 0
_________________________________________________________________
None

此模型在添加TimeDistributed()包装器之前已运行(尽管我必须从最后一个隐藏层中删除return_sequences=True才能起作用)，但是我添加了TimeDistributed()，因为我不认为单个变量我的3维特征值被捕获了.

This model was running before I added the TimeDistributed() wrapper (though I had to remove return_sequences=True from the last hidden layer for it to work), but I added TimeDistributed() because I don't think the individual variables of my 3-dimensional feature values were being captured.

非常感谢您提供任何见识.

Any insight is greatly appreciated, thank you.

更新

由于nuric对我的最初问题的快速回答，我确认我以前的做法是正确的方法"，而我的困惑源于我得到的预测.给定一个来自X的序列，我得到一个3D向量，像这样:[9.915069e-01 1.084390e-04 8.384804e-03](并且总是关于[1, 0, 0])

Thanks to nuric's quick answer to my initial question, I confirmed that the way I was previously doing it was the "right way" and my confusion stems from the predictions I'm getting. Given a sequence from X, I get a 3D vector like this: [9.915069e-01 1.084390e-04 8.384804e-03] (and it's always about [1, 0, 0])

在我以前的LSTM模型中，此预测向量的最大值对应于我对字母/单词的单次编码中的索引，但是这里我要的是对下一个3D向量的x，y和z值的预测按顺序.

In my previous LSTM models, this prediction vector's max value corresponded to the index in my one-hot encoding of letters/words, but here what I want is predictions for the x, y, and z values of the next 3D vector in the sequence.

推荐答案

您对模型的预测(当前为3D)和目标(二维)不匹配.您有2个选择:

You have a mismatch in what the model predicts, currently 3D, and what the target is, 2D. You have 2 options:

1. 应用Flatten并删除TimeDistributed，这意味着模型将基于整个序列进行预测.
2. 从最后一个LSTM中删除return_sequences=True，以使LSTM压缩序列，然后再次删除TimeDistributed.这样，模型将基于最后的LSTM输出而不是序列进行预测.

1. Apply Flatten and remove TimeDistributed which means the model will predict based on the entire sequence.
2. Remove return_sequences=True from last LSTM to let the LSTM compress the sequence and again remove TimeDistributed. This way the model will predict based on the last LSTM output not the sequences.

鉴于序列的大小和隐藏单元的数量，我宁愿选择第二个选项.如果您只是展平序列，即参数太多，则选项1将为Dense层创建一个非常大的内核.

I would prefer the second option given the size of the sequence and the number of hidden units you have. Option one will create a very large kernel for the Dense layer if you just flatten the sequence, i.e. too many parameters.

这篇关于Keras LSTM多维输出错误-预期time_distributed_17具有3个维度，但数组的形状为(1824，3)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！