Examples of numpy's flexible definition of neural network structure in Python

This article mainly introduces Python's method of flexibly defining the neural network structure based on numpy. It analyzes the principles of the neural network structure and the specific implementation method of Python in the form of examples. It involves related operating skills of using numpy extension to perform mathematical operations in Python. It needs Friends can refer to

This article describes how Python flexibly defines the neural network structure based on numpy. Share it with everyone for your reference, the details are as follows:

Use numpy to flexibly define the neural network structure, and you can also apply numpy's powerful matrix operation function!

1. Usage

1). Define a three-layer neural network:

'''示例一'''
nn = NeuralNetworks([3,4,2]) # 定义神经网络
nn.fit(X,y) # 拟合
print(nn.predict(X)) #预测

Description:
Number of input layer nodes: 3
Number of hidden layer nodes: 4
Number of output layer nodes: 2

2). Define a five-layer neural network:

'''示例二'''
nn = NeuralNetworks([3,5,7,4,2]) # 定义神经网络
nn.fit(X,y) # 拟合
print(nn.predict(X)) #预测

Description:
Number of nodes in input layer: 3
Number of nodes in hidden layer 1: 5
Number of nodes in hidden layer 2: 7
Hidden layer 3 Number of nodes: 4
Number of output layer nodes: 2

2. Implementation

The following implementation method is mine (@hhh5460) Original. Key points: dtype=object

##

import numpy as np
class NeuralNetworks(object):
  ''''''
  def __init__(self, n_layers=None, active_type=None, n_iter=10000, error=0.05, alpha=0.5, lamda=0.4):
    '''搭建神经网络框架'''
    # 各层节点数目 (向量)
    self.n = np.array(n_layers) # 'n_layers必须为list类型，如：[3,4,2] 或 n_layers=[3,4,2]'
    self.size = self.n.size # 层的总数
    # 层 (向量)
    self.z = np.empty(self.size, dtype=object) # 先占位(置空)，dtype=object ！如下皆然
    self.a = np.empty(self.size, dtype=object)
    self.data_a = np.empty(self.size, dtype=object)
    # 偏置 (向量)
    self.b = np.empty(self.size, dtype=object)
    self.delta_b = np.empty(self.size, dtype=object)
    # 权 (矩阵)
    self.w = np.empty(self.size, dtype=object)
    self.delta_w = np.empty(self.size, dtype=object)
    # 填充
    for i in range(self.size):
      self.a[i] = np.zeros(self.n[i]) # 全零
      self.z[i] = np.zeros(self.n[i]) # 全零
      self.data_a[i] = np.zeros(self.n[i]) # 全零
      if i < self.size - 1:
        self.b[i] = np.ones(self.n[i+1])  # 全一
        self.delta_b[i] = np.zeros(self.n[i+1]) # 全零
        mu, sigma = 0, 0.1 # 均值、方差
        self.w[i] = np.random.normal(mu, sigma, (self.n[i], self.n[i+1])) # # 正态分布随机化
        self.delta_w[i] = np.zeros((self.n[i], self.n[i+1])) # 全零

The complete code below is my study of the Stanford machine learning tutorial, Completely typed out by myself:

import numpy as np
'''
参考：http://ufldl.stanford.edu/wiki/index.php/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C
'''
class NeuralNetworks(object):
  ''''''
  def __init__(self, n_layers=None, active_type=None, n_iter=10000, error=0.05, alpha=0.5, lamda=0.4):
    '''搭建神经网络框架'''
    self.n_iter = n_iter # 迭代次数
    self.error = error # 允许最大误差
    self.alpha = alpha # 学习速率
    self.lamda = lamda # 衰减因子 # 此处故意拼写错误！
    if n_layers is None:
      raise '各层的节点数目必须设置！'
    elif not isinstance(n_layers, list):
      raise 'n_layers必须为list类型，如：[3,4,2] 或 n_layers=[3,4,2]'
    # 节点数目 (向量)
    self.n = np.array(n_layers)
    self.size = self.n.size # 层的总数
    # 层 (向量)
    self.a = np.empty(self.size, dtype=object) # 先占位(置空)，dtype=object ！如下皆然
    self.z = np.empty(self.size, dtype=object)
    # 偏置 (向量)
    self.b = np.empty(self.size, dtype=object)
    self.delta_b = np.empty(self.size, dtype=object)
    # 权 (矩阵)
    self.w = np.empty(self.size, dtype=object)
    self.delta_w = np.empty(self.size, dtype=object)
    # 残差 (向量)
    self.data_a = np.empty(self.size, dtype=object)
    # 填充
    for i in range(self.size):
      self.a[i] = np.zeros(self.n[i]) # 全零
      self.z[i] = np.zeros(self.n[i]) # 全零
      self.data_a[i] = np.zeros(self.n[i]) # 全零
      if i < self.size - 1:
        self.b[i] = np.ones(self.n[i+1])  # 全一
        self.delta_b[i] = np.zeros(self.n[i+1]) # 全零
        mu, sigma = 0, 0.1 # 均值、方差
        self.w[i] = np.random.normal(mu, sigma, (self.n[i], self.n[i+1])) # # 正态分布随机化
        self.delta_w[i] = np.zeros((self.n[i], self.n[i+1])) # 全零
    # 激活函数
    self.active_functions = {
      &#39;sigmoid&#39;: self.sigmoid,
      &#39;tanh&#39;: self.tanh,
      &#39;radb&#39;: self.radb,
      &#39;line&#39;: self.line,
    }
    # 激活函数的导函数
    self.derivative_functions = {
      &#39;sigmoid&#39;: self.sigmoid_d,
      &#39;tanh&#39;: self.tanh_d,
      &#39;radb&#39;: self.radb_d,
      &#39;line&#39;: self.line_d,
    }
    if active_type is None:
      self.active_type = [&#39;sigmoid&#39;] * (self.size - 1) # 默认激活函数类型
    else:
      self.active_type = active_type
  def sigmoid(self, z):
    if np.max(z) > 600:
      z[z.argmax()] = 600
    return 1.0 / (1.0 + np.exp(-z))
  def tanh(self, z):
    return (np.exp(z) - np.exp(-z)) / (np.exp(z) + np.exp(-z))
  def radb(self, z):
    return np.exp(-z * z)
  def line(self, z):
    return z
  def sigmoid_d(self, z):
    return z * (1.0 - z)
  def tanh_d(self, z):
    return 1.0 - z * z
  def radb_d(self, z):
    return -2.0 * z * np.exp(-z * z)
  def line_d(self, z):
    return np.ones(z.size) # 全一
  def forward(self, x):
    &#39;&#39;&#39;正向传播（在线）&#39;&#39;&#39; 
    # 用样本 x 走一遍，刷新所有 z, a
    self.a[0] = x
    for i in range(self.size - 1):
      self.z[i+1] = np.dot(self.a[i], self.w[i]) + self.b[i] 
      self.a[i+1] = self.active_functions[self.active_type[i]](self.z[i+1]) # 加了激活函数
  def err(self, X, Y):
    &#39;&#39;&#39;误差&#39;&#39;&#39;
    last = self.size-1
    err = 0.0
    for x, y in zip(X, Y):
      self.forward(x)
      err += 0.5 * np.sum((self.a[last] - y)**2)
    err /= X.shape[0]
    err += sum([np.sum(w) for w in self.w[:last]**2])
    return err
  def backward(self, y):
    &#39;&#39;&#39;反向传播（在线）&#39;&#39;&#39;
    last = self.size - 1
    # 用样本 y 走一遍，刷新所有delta_w, delta_b
    self.data_a[last] = -(y - self.a[last]) * self.derivative_functions[self.active_type[last-1]](self.z[last]) # 加了激活函数的导函数
    for i in range(last-1, 1, -1):
      self.data_a[i] = np.dot(self.w[i], self.data_a[i+1]) * self.derivative_functions[self.active_type[i-1]](self.z[i]) # 加了激活函数的导函数
      # 计算偏导
      p_w = np.outer(self.a[i], self.data_a[i+1]) # 外积！感谢 numpy 的强大！
      p_b = self.data_a[i+1]
      # 更新 delta_w, delta_w
      self.delta_w[i] = self.delta_w[i] + p_w
      self.delta_b[i] = self.delta_b[i] + p_b
  def update(self, n_samples):
    &#39;&#39;&#39;更新权重参数&#39;&#39;&#39;
    last = self.size - 1
    for i in range(last):
      self.w[i] -= self.alpha * ((1/n_samples) * self.delta_w[i] + self.lamda * self.w[i])
      self.b[i] -= self.alpha * ((1/n_samples) * self.delta_b[i])
  def fit(self, X, Y):
    &#39;&#39;&#39;拟合&#39;&#39;&#39;
    for i in range(self.n_iter):
      # 用所有样本，依次
      for x, y in zip(X, Y):
        self.forward(x) # 前向，更新 a, z;
        self.backward(y) # 后向，更新 delta_w, delta_b
      # 然后，更新 w, b
      self.update(len(X))
      # 计算误差
      err = self.err(X, Y)
      if err < self.error:
        break
      # 整千次显示误差（否则太无聊！）
      if i % 1000 == 0:
        print(&#39;iter: {}, error: {}&#39;.format(i, err))
  def predict(self, X):
    &#39;&#39;&#39;预测&#39;&#39;&#39;
    last = self.size - 1
    res = []
    for x in X:
      self.forward(x)
      res.append(self.a[last])
    return np.array(res)
if __name__ == &#39;__main__&#39;:
  nn = NeuralNetworks([2,3,4,3,1], n_iter=5000, alpha=0.4, lamda=0.3, error=0.06) # 定义神经网络
  X = np.array([[0.,0.], # 准备数据
         [0.,1.],
         [1.,0.],
         [1.,1.]])
  y = np.array([0,1,1,0])
  nn.fit(X,y)     # 拟合
  print(nn.predict(X)) # 预测

The above is the detailed content of Examples of numpy's flexible definition of neural network structure in Python. For more information, please follow other related articles on the PHP Chinese website!