[学习笔记] 【学习笔记】from functions import * from gradient import numerical_gradi ... [推广有奖]

0关注
0粉丝

本科生

83%

还不是VIP/贵宾

威望: 0 级
论坛币: 40 个
通用积分: 14.1000
学术水平: 0 点
热心指数: 0 点
信用等级: 0 点
经验: 510 点
帖子: 91
精华: 0
在线时间: 0 小时
注册时间: 2019-10-29
最后登录: 2020-1-12

楼主

9248_1572342225 发表于 2020-1-8 09:25:40 来自手机 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

from functions import *
from gradient import numerical_gradient

# 构造的是两层神经网络
class TwoLayerNet:
# 初始化方法
def __init__(self, input_size, hidden_size, output_size,
weight_init_std=0.01):
# 初始化权重
      self.params = {}
      # 权重的初始值,使用标准正态分布生成, 再缩小100倍
      self.params[\'W1\'] = weight_init_std * np.random.randn(input_size, hidden_size)
      # 偏置的初始值设置为0
      self.params[\'b1\'] = np.zeros(hidden_size)
      self.params[\'W2\'] = weight_init_std * np.random.randn(hidden_size, output_size)
      self.params[\'b2\'] = np.zeros(output_size)

def predict(self, x):
      # 信号向前传播过程
      W1, W2 = self.params[\'W1\'], self.params[\'W2\']
      b1, b2 = self.params[\'b1\'], self.params[\'b2\']
      a1 = np.dot(x, W1) + b1
      z1 = sigmoid(a1)
      a2 = np.dot(z1, W2) + b2
      y = softmax(a2)
      return y

# x:输入数据, t:监督数据
def loss(self, x, t):
      # 计算损失函数
      y = self.predict(x)
      # 交叉熵误差计算损失函数的值
      return cross_entropy_error(y, t)
def accuracy(self, x, t):
      y = self.predict(x)
      y = np.argmax(y, axis=1)
      t = np.argmax(t, axis=1)
      accuracy = np.sum(y == t) / float(x.shape[0])
      return accuracy
# x:输入数据, t:监督数据
def numerical_gradient(self, x, t):
      # 梯度计算
      loss_W = lambda W: self.loss(x, t)

      grads = {}
      grads[\'W1\'] = numerical_gradient(loss_W, self.params[\'W1\'])
      grads[\'b1\'] = numerical_gradient(loss_W, self.params[\'b1\'])
      grads[\'W2\'] = numerical_gradient(loss_W, self.params[\'W2\'])
      grads[\'b2\'] = numerical_gradient(loss_W, self.params[\'b2\'])
      return grads

def gradient(self, x, t):
      # 反向传播法 ,backward
      W1, W2 = self.params[\'W1\'], self.params[\'W2\']
      b1, b2 = self.params[\'b1\'], self.params[\'b2\']
      grads = {}

      batch_num = x.shape[0]

      # forward
      a1 = np.dot(x, W1) + b1
      z1 = sigmoid(a1)
      a2 = np.dot(z1, W2) + b2
      y = softmax(a2)

      # backward
      dy = (y - t) / batch_num
      grads[\'W2\'] = np.dot(z1.T, dy)
      grads[\'b2\'] = np.sum(dy, axis=0)

      da1 = np.dot(dy, W2.T)
      dz1 = sigmoid_grad(a1) * da1
      grads[\'W1\'] = np.dot(x.T, dz1)
      grads[\'b1\'] = np.sum(dz1, axis=0)

      return grads