基于深度学习实现梯度下降算法

# -*- coding: utf-8 -*-
"""
Created on Mon Oct 22 17:23:49 2018

@author: zhen
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
from tensorflow.contrib.layers import fully_connected

# 构建图阶段
n_inputs = 28 * 28
n_hidden1 = 300
n_hidden2 = 100
n_outputs = 10

x = tf.placeholder(tf.float32, shape=(None, n_inputs), name='x')
y = tf.placeholder(tf.int64, shape=(None), name='y')

# 构建神经网络，基于两个隐藏层，激活函数：relu，Softmax
def neuron_layer(x, n_neurons, name, activation=None):
    with tf.name_scope(name):
        # 取输入矩阵的维度作为层的输入连接个数
        n_inputs = int(x.get_shape()[1])
        stddev = 2 / np.sqrt(n_inputs)
        init = tf.truncated_normal((n_inputs, n_neurons), stddev=stddev)
        w = tf.Variable(init, name='weights')
        b = tf.Variable(tf.zeros([n_neurons]), name='biases')
        z = tf.matmul(x, w) + b
        if activation == 'relu':
            return tf.nn.relu(z)
        else:
            return z

with tf.name_scope("dnn"):
    # 创建输入层到第一层隐藏层的映射
    hidden1 = neuron_layer(x, n_hidden1, "hidden1", activation="relu")
    # 创建第一层隐藏层到第二层隐藏层的映射
    hidden2 = neuron_layer(hidden1, n_hidden2, "hidden2", activation="relu")
    # 创建第二层隐藏层到输出层的映射
    logits = neuron_layer(hidden2, n_outputs, "outputs")
     
with tf.name_scope("loss"):
    entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)        
    loss = tf.reduce_mean(entropy, name="loss")
    
learning_rate = 0.01

with tf.name_scope("train"):
    optimizer = tf.train.GradientDescentOptimizer(learning_rate)
    training_op = optimizer.minimize(loss)
    
with tf.name_scope("eval"):
    correct = tf.nn.in_top_k(logits, y, 1)
    accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))
    
init = tf.global_variables_initializer()
saver = tf.train.Saver()

# 计算图阶段
mnist = input_data.read_data_sets("C:/Users/zhen/MNIST_data_bak/")
n_epochs = 20
batch_size = 50

with tf.Session() as sess:
    init.run()
    for epoch in range(n_epochs):
        for iteration in range(mnist.train.num_examples // batch_size):
            x_batch, y_batch = mnist.train.next_batch(batch_size)
            sess.run(training_op, feed_dict={x:x_batch, y:y_batch})
        acc_train = accuracy.eval(feed_dict={x:x_batch, y:y_batch})
        acc_test = accuracy.eval(feed_dict={x:mnist.test.images, y:mnist.test.labels})
        print(epoch, "train accuracy:", acc_train, "test accuracy", acc_test)
    save_path = saver.save(sess, "./my_dnn_model_final.ckpt")
    

结果：

　　

分析：

　　从结果可知：整体训练和测试准确率较高，前期波动较大，后期逐渐趋于稳定，收敛！