其他分享
首页 > 其他分享> > tensorflow tensorboard可视化并保存训练结果

tensorflow tensorboard可视化并保存训练结果

作者:互联网

一、还是以mnist的例程,来演示tensorboard的可视化

1、先上代码:

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
 
dir = './MNIST_data'  # 最好填绝对路径
# 1.Import data  
mnist = input_data.read_data_sets(dir, one_hot=True)
# print data information  
print(mnist.train.images.shape, mnist.train.labels.shape)
print(mnist.test.images.shape, mnist.train.labels.shape)
print(mnist.validation.images.shape, mnist.validation.labels.shape)
 
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)
 
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)
 
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
 
def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                          strides=[1, 2, 2, 1], padding='SAME')
 
 
#sess = tf.InteractiveSession()
myGraph = tf.Graph()
with myGraph.as_default():
    with tf.name_scope('inputsAndLabels'):
#输入数据
        x = tf.placeholder(tf.float32, [None, 784])
        y_ = tf.placeholder(tf.float32, [None, 10])
 
 
    with tf.name_scope('hidden1'):   #第一层卷积
        W_conv1 = weight_variable([5, 5, 1, 32])
        b_conv1 = bias_variable([32])
        x_image = tf.reshape(x, [-1, 28, 28, 1])
        h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
        h_pool1 = max_pool_2x2(h_conv1)
 
        tf.summary.image('x_input',x_image,max_outputs=10)
        tf.summary.histogram('W_con1',W_conv1)
        tf.summary.histogram('b_con1',b_conv1)
 
    with tf.name_scope('hidden2'):#第二层卷积
        W_conv2 = weight_variable([5, 5, 32, 64])
        b_conv2 = bias_variable([64])
        h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
        h_pool2 = max_pool_2x2(h_conv2)
 
        tf.summary.histogram('W_con2', W_conv2)
        tf.summary.histogram('b_con2', b_conv2)
 
    with tf.name_scope('fc1'):#密集连接层
        W_fc1 = weight_variable([7 * 7 * 64, 1024])
        b_fc1 = bias_variable([1024])
        h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
        h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
        # dropput
        keep_prob = tf.placeholder(tf.float32)
        h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
 
        tf.summary.histogram('W_fc1', W_fc1)
        tf.summary.histogram('b_fc1', b_fc1)
 
    with tf.name_scope('fc2'):#输出层
        W_fc2 = weight_variable([1024, 10])
        b_fc2 = bias_variable([10])
        y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
 
        tf.summary.histogram('W_fc1', W_fc1)
        tf.summary.histogram('b_fc1', b_fc1)
 
    with tf.name_scope('train'):#训练和评估模型
 
        cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
        train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
        correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
 
        tf.summary.scalar('loss', cross_entropy)
        tf.summary.scalar('accuracy', accuracy)
 
with tf.Session(graph=myGraph) as sess:
    sess.run(tf.global_variables_initializer())
    saver = tf.train.Saver()
 
    merged = tf.summary.merge_all()
    summary_writer = tf.summary.FileWriter('./mnistEven/', graph=sess.graph)
 
    for i in range(2000):
        batch = mnist.train.next_batch(50)
        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
        if i % 100 == 0:
            train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
            print("step %d, training accuracy %g" % (i, train_accuracy))
 
            summary = sess.run(merged, feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
            summary_writer.add_summary(summary, i)
 
    saver.save(sess, save_path='./res/mnistmodel', global_step=1)


2、运行完成后,会在mnistEven目录下,生成 events.out.tfevents.1517282424.DESKTOP-527AKJ 这样的文件。

二、启动tensorboard

1、tensorboard不需要额外的安装,在tf安装完成时,tensorboard就会被自动安装。

2、回到刚刚保存的mnistEven文件夹所在目录,在文件资源管理器的路径栏中直接输入cmd启动dos对话框。

3、输入命令:tensorboard --logdir=mnistEven,不出意外的话,会打印出下面所示的信息

TensorBoard 0.4.0rc3 at http://DESKTOP-527AKJ8:6006 (Press CTRL+C to quit)

4、打开谷歌浏览器,输入:http://DESKTOP-527AKJ8:6006,即可看到tensorboard的界面


--------------------------------------------------------------------------------------------------------- 
原文:https://blog.csdn.net/hust_bochu_xuchao/article/details/79203579 

标签:fc1,summary,variable,shape,train,可视化,tensorboard,tf,tensorflow
来源: https://blog.csdn.net/lcczzu/article/details/91491764