RNN和LSTM的PCB板：

先看LSTM：

必須清楚的知道每一個變量的形狀：
1、h,c,以及y經(jīng)過線性變換前都是hidden_size的；
2、矩陣形式的形狀如下：

# x shape (batch, time_step, input_size)# r_out shape (batch, time_step, output_size)# h_n shape (n_layers, batch, hidden_size)# h_c shape (n_layers, batch, hidden_size) class RNN(nn.Module):def __init__(self):super(RNN, self).__init__()self.rnn = nn.LSTM( # if use nn.RNN(), it hardly learnsinput_size=INPUT_SIZE,hidden_size=64, # rnn hidden unitnum_layers=1, # number of rnn layerbatch_first=True, # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size))self.out = nn.Linear(64, 10)def forward(self, x):# x shape (batch, time_step, input_size)# r_out shape (batch, time_step, output_size)# h_n shape (n_layers, batch, hidden_size)# h_c shape (n_layers, batch, hidden_size)r_out, (h_n, h_c) = self.rnn(x, None) # None represents zero initial hidden state# choose r_out at the last time stepout = self.out(r_out[:, -1, :])return out

先看RNN，也就是Naive RNN：

1、由圖可知：h和y經(jīng)過線性變換前都是hidden_size的；
2、矩陣形式的形狀如下：

# x (batch, time_step, input_size)# h_state (n_layers, batch, hidden_size)# r_out (batch, time_step, hidden_size) class RNN(nn.Module):def __init__(self):super(RNN, self).__init__()self.rnn = nn.RNN(input_size=INPUT_SIZE,hidden_size=32, # rnn hidden unitnum_layers=1, # number of rnn layerbatch_first=True, # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size))self.out = nn.Linear(32, 1)def forward(self, x, h_state):# x (batch, time_step, input_size)# h_state (n_layers, batch, hidden_size)# r_out (batch, time_step, hidden_size)r_out, h_state = self.rnn(x, h_state)outs = [] # save all predictions

總結(jié)

以上是生活随笔為你收集整理的深度学习总结：pytorch构建RNN和LSTM，对比原理图加深理解的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。