python - Reduce the dimension of a tensor using max-pooling layer

Question

My question is very simple:

How can I reduce the dimension of a list or a tensor using max-pooling layer to 512 elements in the list:

I'm trying the following code:

    input_ids = tokenizer.encode(question, text)
    print(input_ids) # input_ids is a list of 700 elements
    m = nn.AdaptiveMaxPool1d(512)
    input_ids = m(torch.tensor([[input_ids]])) # convert the list to tensor and apply max-pooling layer

But I get the following error:

RuntimeError: "adaptive_max_pool2d_cpu" not implemented for 'Long'

So, please help to figure out where is the error

Answer 1

问题在于您的 input_ids。您将 long 类型的张量传递给 AdaptiveMaxPool1d，只需将其转换为浮点数。

    input_ids = tokenizer.encode(question, text)
    print(input_ids) # input_ids is a list of 700 elements
    m = nn.AdaptiveMaxPool1d(512)
    input_ids = m(torch.tensor([[input_ids]]).float()) #