TensorBoard

参考：https://blog.csdn.net/u010099080/article/details/77426577

https://blog.csdn.net/qq_31761357/article/details/80225737

将参数信息写到日志当中时，步骤多了，log文件会很大，今天跑了一下，从几十兆到一个多G，一会就到了。

 

 拿tensorflow实战谷歌这本书第七章的例子看了一下

1. tf.summary.histogram(生成Histogram 和distribution), 

2. tf.summary.scalar： 主要用于记录诸如：准确率、损失和学习率等单个值的变化趋势。

3. tf.summary.image:  

4. tf.summary.FileWriter（分别生成日志), 指定一个目录来告诉程序把文件放到哪里。然后运行的时候使用add_summary()来将某一步的summary数据记录到文件中 

5. tf.summary.merge_all(整理日志操作的，sess.run一次就不用对上述分别run)

6.add_summary

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

SUMMARY_DIR = "./log/supervisor.log"
BATCH_SIZE = 100
TRAIN_STEPS = 300000

def variable_summaries(name,var ):
    #with tf.name_scope('summaries'):#summaries删除
    tf.summary.histogram(name, var)
    mean = tf.reduce_mean(var)
    tf.summary.scalar('mean', mean)#name删掉
    #标准差
    stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
    tf.summary.scalar('stddev', stddev)


def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
    with tf.name_scope(layer_name):
        with tf.name_scope('weights'):
            weights = tf.Variable(tf.truncated_normal([input_dim, output_dim], stddev=0.1))
            variable_summaries( 'weights',weights)
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.constant(0.0, shape=[output_dim]))
            variable_summaries('biases',biases )
        with tf.name_scope('Wx_plus_b'):
            preactivate = tf.matmul(input_tensor, weights) + biases
            tf.summary.histogram( 'pre_activations', preactivate)
        activations = act(preactivate, name='activation')

        # 记录神经网络节点输出在经过激活函数之后的分布。
        tf.summary.histogram('activations',activations)
        return activations


def main():
    mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

    with tf.name_scope('input'):
        x = tf.placeholder(tf.float32, [None, 784], name='x-input')
        y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')

    with tf.name_scope('input_reshape'):
        image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
        #10代表展示10张输入图片
        tf.summary.image('input', image_shaped_input, 10)

    hidden1 = nn_layer(x, 784, 500, 'layer1')
    y = nn_layer(hidden1, 500, 10, 'layer2', act=tf.identity)

    with tf.name_scope('cross_entropy'):
        cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y, labels=y_))
        tf.summary.scalar('cross_entropy', cross_entropy)

    with tf.name_scope('train'):
        train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)

    with tf.name_scope('accuracy'):
        with tf.name_scope('correct_prediction'):
            correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        with tf.name_scope('accuracy'):
            accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        tf.summary.scalar('accuracy', accuracy)

    merged = tf.summary.merge_all()

    with tf.Session() as sess:
        summary_writer = tf.summary.FileWriter(SUMMARY_DIR, sess.graph)
        tf.global_variables_initializer().run()

        for i in range(TRAIN_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            # 运行训练步骤以及所有的日志生成操作，得到这次运行的日志。
            summary, _ = sess.run([merged, train_step], feed_dict={x: xs, y_: ys})
            # 将得到的所有日志写入日志文件，这样TensorBoard程序就可以拿到这次运行所对应的
            # 运行信息。
            summary_writer.add_summary(summary, i)

    summary_writer.close()

if __name__ == '__main__':
    main()

一、scalar结果展示

这图片当中红线框出来的地方为什么会有重叠的部分。

二、Image输入图片展示

三、模型图

四、Distributions

五、Histograms