tensorflow采用传统全连接神经网络（mnist识别）

大概网上都有很多了，我直接上代码，可以直接运行的，但是文件路径什么的需要大家自己改

1、神经网络结构

import tensorflow as tf

#
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500

def get_weight_variable(shape, regularizer):
    weights = tf.get_variable("weights", shape, initializer = tf.truncated_normal_initializer(stddev=0.1))
    if regularizer!=None:
        tf.add_to_collection('losses', regularizer(weights))
        
    return weights

def inference(input_tensor, regularizer):
    with tf.variable_scope('layer1'):
        weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
        biases = tf.get_variable("biases",[LAYER1_NODE],initializer=tf.constant_initializer(0.0))
        layer1 = tf.nn.relu(tf.matmul(input_tensor,weights) + biases)
    with tf.variable_scope('layer2'):
        weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
        biases = tf.get_variable("biases", [OUTPUT_NODE], initializer = tf.constant_initializer(0.0))
        layer2 = tf.matmul(layer1, weights)+biases
    return layer2

2、训练模型并保存

import os

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

import mnist_inference_529

# 配置参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 50000
MOVING_AVERAGE_DECAY = 0.99

# 保存模型路径
MODEL_SAVE_PATH = "model/"
MODEL_NAME = "model.ckpt"

def train(mnist):
    # 1
    x = tf.placeholder(tf.float32,[None, mnist_inference_529.INPUT_NODE], name='x_INPUT')
    y_ = tf.placeholder(tf.float32,[None, mnist_inference_529.OUTPUT_NODE])
    
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    
    y = mnist_inference_529.inference(x, regularizer)
    
    # 2
    global_step = tf.Variable(0, trainable=False)    
    variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variable_average_op = variable_average.apply(tf.trainable_variables())
    # 3
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_,1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    
    #  4
    loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
    
    # 5
    learning_rate = tf.train.exponential_decay(
            LEARNING_RATE_BASE,
            global_step,
            mnist.train.num_examples / BATCH_SIZE,
            LEARNING_RATE_DECAY)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    
    # 6
    with tf.control_dependencies([train_step, variable_average_op]):
        train_op = tf.no_op(name='train')
    
    saver = tf.train.Saver()
    # 7
    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        
        for i in range(TRAINING_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x:xs,y_:ys})
            
            if i % 1000==0:
                print("After %d training step(s), loss on training batch is %g."%(step, loss_value))
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
                
def main(argv=None):
    mnist = input_data.read_data_sets("/path/to/mnist_data", one_hot = True)
    train(mnist)
    
    
if __name__=='__main__':
    tf.app.run()

3、测试模型，正确率为0.9842

import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

import mnist_inference_529
import mnist_train_529

EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
    x = tf.placeholder(tf.float32, [None, mnist_inference_529.INPUT_NODE])
    y_= tf.placeholder(tf.float32, [None, mnist_inference_529.OUTPUT_NODE])
    
    validate_feed = {x:mnist.validation.images, y_:mnist.validation.labels}
    
    y = mnist_inference_529.inference(x,None)
    
    correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    
    variable_averages = tf.train.ExponentialMovingAverage(mnist_train_529.MOVING_AVERAGE_DECAY)
    variable_to_restore = variable_averages.variables_to_restore()
    saver = tf.train.Saver(variable_to_restore)
    
    while True:
        with tf.Session() as sess:
            ckpt = tf.train.get_checkpoint_state(mnist_train_529.MODEL_SAVE_PATH)
            if ckpt and ckpt.model_checkpoint_path:
                saver.restore(sess,ckpt.model_checkpoint_path)
                global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
                print("After %s training step(s), validation accuracy = %g"%(global_step, accuracy_score))
            else:
                print('No checkpoint file found')
            return
        time.sleep(EVAL_INTERVAL_SECS)
    
def main(argv=None):
    mnist = input_data.read_data_sets("data/",one_hot=True)
    evaluate(mnist)
if __name__=='__main__':
    main()

tensorflow采用传统全连接神经网络（mnist识别）

猜你喜欢