Pytorch's LSTM parameters explained

LSTM has a total of 7 parameters:

1: input_size - the size of the input data

2: hidden_size – the size of the hidden layer (ie the number of hidden layer nodes), the dimension of the output vector is equal to the number of hidden nodes

3: num_layers – the number of layers of LSTM stack, the default value is 1 layer, if set to 2, the second LSTM receives the calculation result of the first LSTM.That is, the first layer inputs [ X0 X1 X2 ... Xt ], calculates [ h0 h1 h2 ... ht ], and the second layer takes [ h0 h1 h2 ... ht ] as [ X0 X1 X2 ... Xt ]] The input is calculated again, outputting the final [ h0 h1 h2 ... ht ].

4: bias – whether the hidden layer state has bias, the default is true.bias is the bias value, or offset value

5: batch_first – whether the first dimension of input and output is batch_size, the default value is False

6: dropout – default value 0.Whether to add dropout layers after other RNN layers except the last RNN layer.The input value is a decimal between 0-1 and represents a probability.0 means 0 probability dropout, i.e. no dropout

7: bidirectional – whether it is a bidirectional RNN, the default is: false, if it is true, then: num_directions=2, otherwise it is 1.