Tensorflow 试图理解深层RNN权重

我试图了解RNN训练的重量。对于具有1层的简单RNN，很容易理解。例如，如果时间步长的输入形状为[50,3]，则每个特征需要训练3个权重，加上权重的偏差和输入状态的权重。但我很难理解，随着RNN数量的增加，参数是如何变成12、21、32的。谢谢你的指导

model = Sequential([
    SimpleRNN(1, return_sequences = False, input_shape = [50, 3]),    # 3 features and 1 per Wx and Wy
    Dense(1) 
])


model.summary()

model2 = Sequential([
    SimpleRNN(2, return_sequences = False, input_shape = [50, 3]),    
    Dense(1) # last do not neeed the return sequencies
])

model2.summary()


model3 = Sequential([
    SimpleRNN(3, return_sequences = False, input_shape = [50, 3]),   
    Dense(1) # last do not neeed the return sequencies
])

model3.summary()


model4 = Sequential([
    SimpleRNN(4, return_sequences = False, input_shape = [50, 3]),  
    Dense(1) # last do not neeed the return sequencies
])

对于您的型号2：

model2=顺序([
SimpleRN（2，返回_序列=False，输入_形状=[50,3]），
密集（1）#最后不需要返回顺序
])

下图显示了其中一个神经元的权重（5个权重），您将有1个偏差。因此每个神经元有6个参数，总参数计数为6*2=12

您的示例的公式为：

h*（3+h）+h

---

其中，

（3+h）

是每个神经元的权重数，最后一个

h

将偏差添加到参数中

非常感谢，现在这很有意义。每个“神经元”是一个单独的RNN单元，每个处理一个输入，还是每个输入都连接到单个RNN单元的单个输入？我很困惑，网上的大多数解释都漏掉了很多。@Matt我不太明白你的问题，但我希望这能有所帮助：RNN是层而不是单个神经元。例如，在上面的图像中，当前时间步（红色圆圈）内是一层RNN，它获取一层输入（蓝色圆圈）及其以前的状态（灰色圆圈）。实际上，灰色的圆圈不是单独的东西。它们是最后一个时间步中的红色圆圈

Model: "sequential_20"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
simple_rnn_22 (SimpleRNN)    (None, 1)                 5         
_________________________________________________________________
dense_18 (Dense)             (None, 1)                 2         
=================================================================
Total params: 7
Trainable params: 7
Non-trainable params: 0
_________________________________________________________________
Model: "sequential_21"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
simple_rnn_23 (SimpleRNN)    (None, 2)                 12        
_________________________________________________________________
dense_19 (Dense)             (None, 1)                 3         
=================================================================
Total params: 15
Trainable params: 15
Non-trainable params: 0
_________________________________________________________________
Model: "sequential_22"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
simple_rnn_24 (SimpleRNN)    (None, 3)                 21        
_________________________________________________________________
dense_20 (Dense)             (None, 1)                 4         
=================================================================
Total params: 25
Trainable params: 25
Non-trainable params: 0
_________________________________________________________________
Model: "sequential_23"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
simple_rnn_25 (SimpleRNN)    (None, 4)                 32        
_________________________________________________________________
dense_21 (Dense)             (None, 1)                 5         
=================================================================
Total params: 37
Trainable params: 37
Non-trainable params: 0
_________________________________________________________________