吴裕雄 python 神经网络——TensorFlow训练神经网络:MNIST最佳实践

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

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

BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "E:\\MNIST_model\\"
MODEL_NAME = "mnist_model"

def train(mnist):
    # 定义输入输出placeholder。
    x = tf.placeholder(tf.float32, [None, INPUT_NODE], name=‘x-input‘)
    y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name=‘y-input‘)

    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    y = inference(x, regularizer)
    global_step = tf.Variable(0, trainable=False)

    # 定义损失函数、学习率、滑动平均操作以及训练过程。
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variable_averages.apply(tf.trainable_variables())
    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)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection(‘losses‘))
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,
        staircase=True)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name=‘train‘)

    # 初始化TensorFlow持久化类。
    saver = tf.train.Saver()
    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("E:\\MNIST_data\\", one_hot=True)
    train(mnist)

if __name__ == ‘__main__‘:
    main()

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

INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500

BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "E:\\MNIST_model\\"
MODEL_NAME = "mnist_model"

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

# 加载的时间间隔。
EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
    with tf.Graph().as_default() as g:
        x = tf.placeholder(tf.float32, [None, INPUT_NODE], name=‘x-input‘)
        y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name=‘y-input‘)
        validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}

        y = 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(MOVING_AVERAGE_DECAY)
        variables_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variables_to_restore)

        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(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("E:\\MNIST_data\\", one_hot=True)
    evaluate(mnist)

if __name__ == ‘__main__‘:
    main()

原文地址:https://www.cnblogs.com/tszr/p/10876274.html

时间: 2024-09-30 06:16:52

吴裕雄 python 神经网络——TensorFlow训练神经网络:MNIST最佳实践的相关文章

吴裕雄 python 神经网络——TensorFlow训练神经网络:不使用激活函数

import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 # 输入节点 OUTPUT_NODE = 10 # 输出节点 LAYER1_NODE = 500 # 隐藏层数 BATCH_SIZE = 100 # 每次batch打包的样本个数 # 模型相关的参数 LEARNING_RATE_BASE = 0.01 LEARNING_RATE_DECAY = 0.

吴裕雄 python 神经网络——TensorFlow 使用卷积神经网络训练和预测MNIST手写数据集

import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data #设置输入参数 batch_size = 128 test_size = 256 # 初始化权值与定义网络结构,建构一个3个卷积层和3个池化层,一个全连接层和一个输出层的卷积神经网络 # 首先定义初始化权重函数 def init_weights(shape): return tf.Variabl

吴裕雄 python 神经网络——TensorFlow实现回归模型训练预测MNIST手写数据集

import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("E:\\MNIST_data\\", one_hot=True) #构建回归模型,输入原始真实值(group truth),采用sotfmax函数拟合,并定义损失函数和优化器 #定义回归模型 x = tf.placeholder(tf.float32,

吴裕雄 python 神经网络——TensorFlow 输入数据处理框架

import tensorflow as tf files = tf.train.match_filenames_once("E:\\MNIST_data\\output.tfrecords") filename_queue = tf.train.string_input_producer(files, shuffle=False) # 读取文件. reader = tf.TFRecordReader() _,serialized_example = reader.read(filen

吴裕雄 python 神经网络——TensorFlow TFRecord样例程序

import numpy as np import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data # 定义函数转化变量类型. def _int64_feature(value): return tf.train.Feature(int64_list=tf.train.Int64List(value=[value])) def _bytes_feature(value): return tf.

吴裕雄--天生自然TensorFlow高层封装:使用TensorFlow-Slim处理MNIST数据集实现LeNet-5模型

# 1. 通过TensorFlow-Slim定义卷机神经网络 import numpy as np import tensorflow as tf import tensorflow.contrib.slim as slim from tensorflow.examples.tutorials.mnist import input_data # 通过TensorFlow-Slim来定义LeNet-5的网络结构. def lenet5(inputs): inputs = tf.reshape(in

吴裕雄 python深度学习与实践(17)

import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import time # 声明输入图片数据,类别 x = tf.placeholder('float', [None, 784]) y_ = tf.placeholder('float', [None, 10]) # 输入图片数据转化 x_image = tf.reshape(x, [-1, 28, 28, 1]) #第一层卷积层

吴裕雄 python深度学习与实践(15)

import tensorflow as tf import tensorflow.examples.tutorials.mnist.input_data as input_data mnist = input_data.read_data_sets("D:\\F\\TensorFlow_deep_learn\\MNIST\\", one_hot=True) x_data = tf.placeholder("float32", [None, 784]) weight

吴裕雄 python 神经网络——TensorFlow 数据集高层操作

import tempfile import tensorflow as tf train_files = tf.train.match_filenames_once("E:\\output.tfrecords") test_files = tf.train.match_filenames_once("E:\\output_test.tfrecords") # 解析一个TFRecord的方法. def parser(record): features = tf.pa