lua torch实现ST-LSTM

小鱼儿 2022-06-02 01:37 69阅读 0赞

参考文章\[[https://www.csdn.net/article/2015-09-14/2825693\]][https_www.csdn.net_article_2015-09-14_2825693]  
原文链接\[[https://apaszke.github.io/lstm-explained.html\]][https_apaszke.github.io_lstm-explained.html]

### 1.定义输入 ###

-- there will be 4*n+1 inputs
        local inputs = {}  #创建一个空的table
        table.insert(inputs, nn.Identity()()) -- x
        for L = 1, n do  
         # nn.Identity() - 传递输入（用来存放输入数据）
            table.insert(inputs, nn.Identity()()) -- prev_cj[L]
            table.insert(inputs, nn.Identity()()) -- prev_hj[L]
        end    
        for L = 1, n do
            table.insert(inputs, nn.Identity()()) -- prev_ct[L]
            table.insert(inputs, nn.Identity()()) -- prev_ht[L]
        end
    
        local x, input_size_L

普通LSTM上一状态的输入只有c和h，而ST-LSTM分成两部分，t和j

将输入表中的元素分别送给prev\_cj，prev\_hj，prev\_ct，prev\_ht

local outputs = {}
    
        for L = 1, n do
            -- c,h from previos steps
            local prev_cj = inputs[L*2]
            local prev_hj = inputs[L*2+1]
    
            local prev_ct = inputs[n*2+L*2]
            local prev_ht = inputs[n*2+L*2+1]
    
            -- the input to this layer
            if (L == 1) then
                x = inputs[1]
                input_size_L = input_size
            else
                x = outputs[(L-1)*2] 
                if dropout > 0 then x = nn.Dropout(dropout)(x) end -- apply dropout, if any
                input_size_L = rnn_size
            end

### 2.输入线性变换 ###

rnn\_size是hideen units个数，线性变换后，拆成5部分（普通LSTM是四部分）

-- evaluate the input sums at once for efficiency
            local i2h  = nn.Linear(input_size_L, 5 * rnn_size)(x):annotate{      name = 'i2h_'  .. L}
            local h2hj = nn.Linear(rnn_size,     5 * rnn_size)(prev_hj):annotate{name = 'h2hj_' .. L}
            local h2ht = nn.Linear(rnn_size,     5 * rnn_size)(prev_ht):annotate{name = 'h2ht_' .. L}
            local all_input_sums = nn.CAddTable()({i2h, h2hj, h2ht})
    
            local reshaped = nn.Reshape(5, rnn_size)(all_input_sums)
            local n1, n2, n3, n4, n5 = nn.SplitTable(2)(reshaped):split(5)

### 3. 输入非线性变换 ###

-- decode the gates
            local in_gate       = nn.Sigmoid()(n1)
            local forget_gate_j = nn.Sigmoid()(n2)
            local forget_gate_t = nn.Sigmoid()(n3)
            local out_gate      = nn.Sigmoid()(n4)
            -- decode the write inputs
            local in_transform  = nn.Tanh()(n5)

### 4.状态更新 ###

local next_c = nn.CAddTable()({
                nn.CMulTable()({forget_gate_j, prev_cj}),
                nn.CMulTable()({forget_gate_t, prev_ct}),
                nn.CMulTable()({in_gate,  in_transform})  })
    
            -- gated cells form the output
            local next_h = nn.CMulTable()({out_gate, nn.Tanh()(next_c)})
    
            table.insert(outputs, next_c)
            table.insert(outputs, next_h)

[https_www.csdn.net_article_2015-09-14_2825693]: https://www.csdn.net/article/2015-09-14/2825693]
[https_apaszke.github.io_lstm-explained.html]: https://apaszke.github.io/lstm-explained.html]