22、神经网络模型训练与逻辑回归从零实现

神经网络模型训练与逻辑回归从零实现

1. 模型训练

首先，我们要构建一个简单的三层神经网络，每层包含 5 个神经元。以下是构建网络的代码：

import tensorflow as tf
import numpy as np

tf.reset_default_graph()
n1 = 5  # Number of neurons in layer 1
n2 = 5  # Number of neurons in layer 2
n3 = 5  # Number of neurons in layer 3
nx = number_of_x_points
n_dim = nx
n4 = 1
stddev_f = 2.0
tf.set_random_seed(5)
X = tf.placeholder(tf.float32, [n_dim, None])
Y = tf.placeholder(tf.float32, [10, None])
W1 = tf.Variable(tf.random_normal([n1, n_dim], stddev=stddev_f))
b1 = tf.Variable(tf.constant(0.0, shape = [n1,1]) )
W2 = tf.Variable(tf.random_normal([n2, n1], stddev=stddev_f))
b2 = tf.Variable(tf.constant(0.0, shape = [n2,1]))
W3 = tf.Variable(tf.random_normal([n3,n2], stddev = stddev_f))
b3 = tf.Variab