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

Posted 2021-11-30 tszr

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()