pytorch lstm gru rnn 得到每個state輸出的操作

# coding=UTF-8
import torch
import torch.autograd as autograd  # torch中自動計算梯度模塊
import torch.nn as nn  # 神經網絡模塊
torch.manual_seed(1)
# lstm單元輸入和輸出維度都是3
lstm = nn.LSTM(input_size=3, hidden_size=3)
# 生成一個長度為5，每一個元素為1*3的序列作為輸入，這裡的數字3對應於上句中第一個3
inputs = [autograd.Variable(torch.randn((1, 3)))
          for _ in range(5)]
# 設置隱藏層維度，初始化隱藏層的數據
hidden = (autograd.Variable(torch.randn(1, 1, 3)),
          autograd.Variable(torch.randn((1, 1, 3))))
for i in inputs:
  out, hidden = lstm(i.view(1, 1, -1), hidden)
  print(out.size())
  print(hidden[0].size())
  print("--------")
print("-----------------------------------------------")
# 下面是一次輸入多個step的樣子
inputs_stack = torch.stack(inputs)
out,hidden = lstm(inputs_stack,hidden)
print(out.size())
print(hidden[0].size())

import torch
import torch.nn as nn
 
lstm = nn.LSTM(10, 20, 2)
 
# 序列長度seq_len=5, batch_size=3, 數據向量維數=10
input = torch.randn(5, 3, 10)
 
# 初始化的隱藏元和記憶元,通常它們的維度是一樣的
# 2個LSTM層，batch_size=3,隱藏元維度20
h0 = torch.randn(2, 3, 20)
c0 = torch.randn(2, 3, 20)
 
# 這裡有2層lstm，output是最後一層lstm的每個詞向量對應隱藏層的輸出,其與層數無關，隻與序列長度相關
# hn,cn是所有層最後一個隱藏元和記憶元的輸出
output, (hn, cn) = lstm(input, (h0, c0))
 
print(output.size(),hn.size(),cn.size())
 
# 分別是：
# torch.Size([5, 3, 20])
# torch.Size([2, 3, 20])
# torch.Size([2, 3, 20]))

class LSTM(RNNBase):
   
    '''參數Args:
        input_size: 輸入數據的特征維度，比如我對時間序列建模，特征為1，我對一個句子建模，每一個單詞的嵌入向量為10，則它為10
        
        hidden_size: 即循環神經網絡中隱藏節點的個數，這個是自己定義的，多少都可以，後面會詳說
        
        num_layers: 堆疊的LSTM的層數，默認是一層，也可以自己定義 Default: 1
        bias: LSTM層是否使用偏置矩陣 偏置權值為 `b_ih` and `b_hh`.
            Default: ``True``（默認是使用的）
        
        batch_first: 如果設置 ``True``, then the input and output tensors are provided
            as (batch, seq, feature). Default: ``False``，(seq,batch,features)
        dropout: 是否使用dropout機制，默認是0，表示不使用dropout，如果提供一個非0的數字，則表示在每一個LSTM層之後默認使用dropout，但是最後一個層的LSTM層不使用dropout。
        
        bidirectional: 是否是雙向RNN，默認是否，If ``True``, becomes a bidirectional LSTM. Default: ``False``
#---------------------------------------------------------------------------------------
    類的構造函數的輸入為Inputs: input, (h_0, c_0)
        - **input** of shape `(seq_len, batch, input_size)`: tensor containing the features of the input sequence.
          
        - **h_0** of shape `(num_layers * num_directions, batch, hidden_size)`: tensor
          containing the initial hidden state for each element in the batch.
          If the LSTM is bidirectional, num_directions should be 2, else it should be 1.
        - **c_0** of shape `(num_layers * num_directions, batch, hidden_size)`: tensor
          containing the initial cell state for each element in the batch.
          If `(h_0, c_0)` is not provided, both **h_0** and **c_0** default to zero.
#----------------------------------------------------------------------------------
    輸出是什麼：Outputs: output, (h_n, c_n)
        - **output** of shape `(seq_len, batch, num_directions * hidden_size)`: tensor
          containing the output features `(h_t)` from the last layer of the LSTM,
          for each `t`. If a :class:`torch.nn.utils.rnn.PackedSequence` has been
          given as the input, the output will also be a packed sequence.
          For the unpacked case, the directions can be separated
          using ``output.view(seq_len, batch, num_directions, hidden_size)``,
          with forward and backward being direction `0` and `1` respectively.
          Similarly, the directions can be separated in the packed case.
        
        - **h_n** of shape `(num_layers * num_directions, batch, hidden_size)`: tensor
          containing the hidden state for `t = seq_len`.
          Like *output*, the layers can be separated using
          ``h_n.view(num_layers, num_directions, batch, hidden_size)`` and similarly for *c_n*.
        
        - **c_n** of shape `(num_layers * num_directions, batch, hidden_size)`: tensor
          containing the cell state for `t = seq_len`.
#------------------------------------------------------------------------------------------
    類的屬性有Attributes:
        weight_ih_l[k] : the learnable input-hidden weights of the :math:`\text{k}^{th}` layer
            `(W_ii|W_if|W_ig|W_io)`, of shape `(4*hidden_size, input_size)` for `k = 0`.
            Otherwise, the shape is `(4*hidden_size, num_directions * hidden_size)`
        weight_hh_l[k] : the learnable hidden-hidden weights of the :math:`\text{k}^{th}` layer
            `(W_hi|W_hf|W_hg|W_ho)`, of shape `(4*hidden_size, hidden_size)`
        bias_ih_l[k] : the learnable input-hidden bias of the :math:`\text{k}^{th}` layer
            `(b_ii|b_if|b_ig|b_io)`, of shape `(4*hidden_size)`
        bias_hh_l[k] : the learnable hidden-hidden bias of the :math:`\text{k}^{th}` layer
            `(b_hi|b_hf|b_hg|b_ho)`, of shape `(4*hidden_size)`
    '''

lstm = nn.LSTM(10, 20, 2)

class LSTM(RNNBase):
   
    '''參數Args:
        input_size:
        hidden_size:         
        num_layers: 
        bias:       
        batch_first: 
        dropout: 
        bidirectional:
    '''

output, (hn, cn) = lstm(input, (h0, c0))

output, hn = rnn(input, h0)  # 普通rnn
output, hn = gru(input, h0)  # gru

output, hn = rnn(input, h0)  # 普通rnn
output, hn = gru(input, h0)  # gru
output, (hn, cn) = lstm(input, (h0, c0)) # lstm

# 首先導入RNN需要的相關模塊
import torch
import torch.nn as nn
 
# 數據向量維數10, 隱藏元維度20, 2個RNN層串聯(如果是1，可以省略，默認為1)
rnn = nn.RNN(10, 20, 2)
 
# 序列長度seq_len=5, batch_size=3, 數據向量維數=10
input = torch.randn(5, 3, 10)
 
# 初始化的隱藏元和記憶元,通常它們的維度是一樣的
# 2個RNN層，batch_size=3,隱藏元維度20
h0 = torch.randn(2, 3, 20)
 
# 這裡有2層RNN，output是最後一層RNN的每個詞向量對應隱藏層的輸出,其與層數無關，隻與序列長度相關
# hn,cn是所有層最後一個隱藏元和記憶元的輸出
output, hn = rnn(input, h0)
 
print(output.size(),hn.size()) # 分別是：torch.Size([5, 3, 20])   torch.Size([2, 3, 20])
 
# 查看一下那幾個重要的屬性：
print("------------輸入--》隱藏------------------------------")
print(rnn.weight_ih_l0.size())  
print(rnn.weight_ih_l1.size())
print(rnn.bias_ih_l0.size())
print(rnn.bias_ih_l1.size())
print("------------隱藏--》隱藏------------------------------")
print(rnn.weight_hh_l0.size())  
print(rnn.weight_hh_l1.size())
print(rnn.bias_hh_l0.size())
print(rnn.bias_hh_l1.size())
 
'''輸出結果為：
------------輸入--》隱藏------------------------------
torch.Size([20, 10])
torch.Size([20, 20])
torch.Size([20])
torch.Size([20])
------------隱藏--》隱藏------------------------------
torch.Size([20, 20])
torch.Size([20, 20])
torch.Size([20])
torch.Size([20])
'''