如何在不嵌入的情况下使用带有 keras 的不同长度的序列数据的 LSTM？

Question

I have an input data where each example is some varying number of vectors of length k. In total I have n examples. So the dimensions of the input is n * ? * k. The question mark symbolizes varying length.

I want to input it to an LSTM layer in Keras, if possible, without using embedding (it isn't your ordinary words dataset).

Could someone write a short example of how to do this?

The data is currently a double nested python array, eg

example1 = [[1,0,1], [1,1,1]]
example2 = [[1,1,1]]
my_data = []
my_data.append(example1)
my_data.append(example2)

Answer 1

I think you could use pad_sequences . This should get all of your inputs to the same length.

Answer 2

You can use padding ( pad_sequences ) and a Masking layer.

You can also train batches of different lenghts in a manual training loop:

for e in range(epochs):
    for batch_x, batch_y in list_of_batches: #providade you separated the batches by length
        model.train_on_batch(batch_x, batch_y)

The keypoint in all of this is that your input_shape=(None, k)