我的输入状态为shape =（84,84,4）
state = Input(shape=(84,84,4), dtype="float")
所以我想把它传递给一些TimeDistributed层，时间步长为1 = 5（范围为1到5），我不确切知道它等于哪一个。
我的下一层是这样的：
conv1 = TimeDistributed(Convolution2D(16, 8, 8, subsample=(4, 4), border_mode='valid',
activation='relu', dim_ordering='tf'))(state)
我在这一层遇到错误：
IndexError: tuple index out of range
我只想传递未知的时间序列大小到TimeDistributed，然后再传递给LSTM。
答案 0 :(得分：1)
So basically in Keras - you need to provide the sequence length because during computations Keras layers accepts as an input numpy array with a specified shape - what makes compulsory for all inputs (at least in one batch) to have a length fixed. But - you still can deal with varying input size by 0-padding (making all sequence equal size by adding all zero dummy timesteps at the beginning) and then masking what makes your network equivalent to a varying length input network.
答案 1 :(得分：0)
您可以给定可变的序列长度，如下所示：
classifier.add(TimeDistributed(Convolution2D(64,(3,3)),input_shape=(None,None,None,3)))
但是现在，当向量在时间预测中变平或展开时，您将不得不调整向量的长度。