27、深度学习模型训练与逻辑回归从基础实现

深度学习模型训练与逻辑回归从基础实现

模型训练

在构建网络时，由于空间限制，我们构建一个简单的三层网络，每层有五个神经元。以下是具体的代码实现：

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