Pytorch LSTM教程不同的输出

时间:2019-02-06 23:31:50

标签: torch

https://pytorch.org/tutorials/beginner/nlp/sequence_models_tutorial.html

import torch

import torch.nn as nn

import torch.nn.functional as F

import torch.optim as optim

torch.manual_seed(1)


lstm = nn.LSTM(3, 3)

inputs = [torch.randn(1, 3) for _ in range(5)]

hidden = (torch.randn(1, 1, 3),
          torch.randn(1, 1, 3))

for i in inputs:
    out, hidden = lstm(i.view(1, 1, 3), hidden)
    print(out)
    # print(hidden)

print("\n")

inputs = torch.cat(inputs).view(len(inputs), 1, 3)

hidden = (torch.randn(1, 1, 3),
          torch.randn(1, 1, 3))

out, hidden = lstm(inputs, hidden)
print(out)
# print(hidden)

在这两个示例中,“输出”如何打印出不同的内容? for循环的顺序应该与将它们堆叠并运行LSTM一样?

0 个答案:

没有答案