Outputs: output, (h_n, c_n)
- output (seq_len, batch, hidden_size * num_directions): tensor containing the output features (h_t) from the last layer of the RNN, for each t. If a torch.nn.utils.rnn.PackedSequence has been given as the input, the output will also be a packed sequence.
- h_n (num_layers * num_directions, batch, hidden_size): tensor containing the hidden state for t=seq_len
- c_n (num_layers * num_directions, batch, hidden_size): tensor containing the cell state for t=seq_len
renamed num_layers （有几层LSTM/GRU叠加）to w.
output comprises all the hidden states in the last layer ("last" depth-wise, not time-wise).
(h_n, c_n) comprises the hidden states after the last timestep, t = n, so you could potentially feed them into another LSTM.
加入num_layers=1,那么output和hidden相等。
LOSS和logP(y|x)的区别：
decoder每一步输出的是单词词典中每一个单词的概率。就是，下一个是什么单词，候选集里每个单词的都有可能。
目标是模型的输出接近真实值，所以
输出序列是依赖参数的，计算出目标输出的所对应的参数表示函数集合。（回忆考研最大似然的定义）