如何理解Keras中一个简单中立网络Python代码的密集层参数

Question

import numpy as np
    from keras.models import Sequential
    from keras.layers.core import Dense, Activation

    # X has shape (num_rows, num_cols), where the training data are stored
    # as row vectors
    X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]], dtype=np.float32)

    # y must have an output vector for each input vector
    y = np.array([[0], [0], [0], [1]], dtype=np.float32)

    # Create the Sequential model
    model = Sequential()

    # 1st Layer - Add an input layer of 32 nodes with the same input shape as
    # the training samples in X
    model.add(Dense(32, input_dim=X.shape[1]))

    # Add a softmax activation layer
    model.add(Activation('softmax'))

    # 2nd Layer - Add a fully connected output layer
    model.add(Dense(1))

    # Add a sigmoid activation layer
    model.add(Activation('sigmoid'))

我是Keras的新手，正在努力理解它。

<代码>模型。add（稠密（32，input\u dim=X.shape[1]）对于每个训练实例，有32个输入变量，其维数由input\u dim给出。但在输入X向量中，

array([[0., 0.],
       [0., 1.],
       [1., 0.],
       [1., 1.]], dtype=float32)

共有4个培训实例。看起来每个示例只有两个输入变量。那么，这与致密层定义中的“32”是如何对应的呢？这个网络是什么样子的？

Answer 1

按照本杰明的回答。下面是一个例子：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
Input (Dense)                (None, 16)                32        
_________________________________________________________________
Hidden_1 (Dense)             (None, 16)                272       
_________________________________________________________________
Output (Dense)               (None, 1)                 17        
=================================================================
Total params: 321
Trainable params: 321
Non-trainable params: 0
_________________________________________________________________

计算每一层的参数数：

输入大小=（1，）一个输入

Input layer number of parameters  = 16 weights * 1(input) + 16 biases = 32
Hidden layer number of parameters = 16 weights * 16(hidden neurons) + 16 biases = 272
Output layer number of parameters = 16 weights * 1(output neuron) + 1 bias = 17

Answer 2

如果你尝试

model.summary()

你会得到最后一个问题的答案。

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              (None, 32)                96        
_________________________________________________________________
activation_1 (Activation)    (None, 32)                0         
_________________________________________________________________
dense_2 (Dense)              (None, 1)                 33        
_________________________________________________________________
activation_2 (Activation)    (None, 1)                 0         
=================================================================
Total params: 129
Trainable params: 129
Non-trainable params: 0
_________________________________________________________________

网络输入为2个节点（变量），与dense\u 1层（32个节点）相连。总共32*2个权重，32个偏差为您提供96个参数。希望这有帮助。