Tensorflow tf.keras.layers.LSTM

参数

参数	描述
units	输出空间的维度
input_shape	(timestep, input_dim),timestep可以设置为None,由输入决定,input_dime根据具体情况
activation	激活函数,默认tanh
recurrent_activation
use_bias
kernel_initializer
recurrent_initializer
bias_initializer
unit_forget_bias
kernel_regularizer
recurrent_regularizer
bias_regularizer
activity_regularizer
kernel_constraint
recurrent_constraint
bias_constraint
dropout
recurrent_dropout
implementation
return_sequences
return_state
go_backwards
stateful
unroll

例子

keras.layers.LSTM(units=200,input_shape=(None,1),return_sequences=True)

init

__init__(
    units,
    activation='tanh',
    recurrent_activation='sigmoid',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    recurrent_initializer='orthogonal',
    bias_initializer='zeros',
    unit_forget_bias=True,
    kernel_regularizer=None,
    recurrent_regularizer=None,
    bias_regularizer=None,
    activity_regularizer=None,
    kernel_constraint=None,
    recurrent_constraint=None,
    bias_constraint=None,
    dropout=0.0,
    recurrent_dropout=0.0,
    implementation=2,
    return_sequences=False,
    return_state=False,
    go_backwards=False,
    stateful=False,
    time_major=False,
    unroll=False,
    **kwargs
)

原理

${\hat{c}}^{<t>}$是记忆状态,对应矩阵形状($units\ast features+units\ast units+bias$)

${\Gamma }_u$为更新门(update),形状是$(units\ast features+units\ast units+bias)$

${\Gamma }_f$为更新门(forget),形状是$(units\ast features+units\ast units+bias)$

${\Gamma }_o$为输出门(out),形状是$(units\ast features+units\ast units+bias)$

所以LSTM的参数个数是:$(units\ast features+units\ast units+units)\ast 4$

参考：
官网
https://blog.csdn.net/jiangpeng59/article/details/77646186
https://www.zhihu.com/question/41949741?sort=created
https://stackoverflow.com/questions/38080035/how-to-calculate-the-number-of-parameters-of-an-lstm-network/56614978#56614978
https://stackoverflow.com/questions/46584171/why-does-the-first-lstm-in-a-keras-model-have-more-params-than-the-subsequent-on