TensorFlow——可视化（3）动态

TensorFlow可视化3

（1）使用代码

**#**************代表实现可视化需要改动的地方
mnist数据集实现可视化，使用projector实动态过程

'''
mnist数据集实现可视化，使用projector实现动态过程
coding: utf-8
# *************为实现的动态projector过程所需步骤
'''
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.contrib.tensorboard.plugins import projector   # ********************
import os
os.environ['CUDA_VISIBLE_DEVICES'] = "0,2"  # 使用GPU/CPU
# os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'    # CPU忽略警告

# 载入数据集
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# 运行次数
max_steps = 1001
# 图片数量
image_num = 3000
# 文件路径
DIR = "F:/BaiduNetdiskDownload/资料/第六周/程序/"

# 定义会话
sess = tf.Session()

# 载入图片
embedding = tf.Variable(tf.stack(mnist.test.images[:image_num]), trainable=False, name='embedding')  # stack相当于矩阵链连接

# 参数概要 ***********************
def variable_summaries(var):
    with tf.name_scope('summaries'):
        mean = tf.reduce_mean(var)
        tf.summary.scalar('mean', mean)#平均值
        with tf.name_scope('stddev'):
            stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
        tf.summary.scalar('stddev', stddev)#标准差
        tf.summary.scalar('max', tf.reduce_max(var))#最大值
        tf.summary.scalar('min', tf.reduce_min(var))#最小值
        tf.summary.histogram('histogram', var)#直方图

# 命名空间
with tf.name_scope('input'):
    x = tf.placeholder(tf.float32, [None, 784], name='x-input')
    # 正确的标签
    y = tf.placeholder(tf.float32, [None, 10], name='y-input')

# 显示图片
with tf.name_scope('input_reshape'):
    image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])  # [-1,28,28,1]  784->28*28,图片为黑白图片，所以维度为1
    tf.summary.image('input', image_shaped_input, 10)   # 存10张图片

with tf.name_scope('layer'):
    # 创建一个简单神经网络
    with tf.name_scope('weights'):
        W = tf.Variable(tf.zeros([784, 10]), name='W')
        variable_summaries(W)
    with tf.name_scope('biases'):
        b = tf.Variable(tf.zeros([10]), name='b')
        variable_summaries(b)
    with tf.name_scope('wx_plus_b'):
        wx_plus_b = tf.matmul(x, W) + b
    with tf.name_scope('softmax'):    
        prediction = tf.nn.softmax(wx_plus_b)

with tf.name_scope('loss'):
    # 交叉熵代价函数
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
    tf.summary.scalar('loss', loss)
with tf.name_scope('train'):
    # 使用梯度下降法
    train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)

# 初始化变量
sess.run(tf.global_variables_initializer())
with tf.name_scope('accuracy'):
    with tf.name_scope('correct_prediction'):
        # 结果存放在一个布尔型列表中
        correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1))#argmax返回一维张量中最大的值所在的位置
    with tf.name_scope('accuracy'):
        # 求准确率
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))#把correct_prediction变为float32类型
        tf.summary.scalar('accuracy', accuracy)

# 产生metadata文件*******************************
if tf.gfile.Exists(DIR + 'projector/projector/metadata.tsv'):
    tf.gfile.DeleteRecursively(DIR + 'projector/projector/metadata.tsv')   # 如有则删除掉
with open(DIR + 'projector/projector/metadata.tsv', 'w') as f:  # 生成新的文件
    labels = sess.run(tf.argmax(mnist.test.labels[:], 1))   # 得到测试集的标签（最大位置的）one—hot形式
    for i in range(image_num):   
        f.write(str(labels[i]) + '\n')
# **********************************************

#合并所有的summary
merged = tf.summary.merge_all()   

# *******************************固定操作，官网上有***********************************
projector_writer = tf.summary.FileWriter(DIR + 'projector/projector', sess.graph)   # 用于保存网络结构
saver = tf.train.Saver()
config = projector.ProjectorConfig()
embed = config.embeddings.add()
embed.tensor_name = embedding.name
embed.metadata_path = DIR + 'projector/projector/metadata.tsv'
embed.sprite.image_path = DIR + 'projector/data/mnist_10k_sprite.png'
embed.sprite.single_image_dim.extend([28, 28])   # 图片切分
projector.visualize_embeddings(projector_writer, config)   # 记录可视化工具，包括配置
# ***********************************************************************

for i in range(max_steps):
    #每个批次100个样本
    batch_xs, batch_ys = mnist.train.next_batch(100)  #
    run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)  # *******固定写法********
    run_metadata = tf.RunMetadata()  # *******固定写法*********
    summary, _ = sess.run([merged, train_step], feed_dict={x: batch_xs, y: batch_ys}, options=run_options, run_metadata= run_metadata)   # ************
    projector_writer.add_run_metadata(run_metadata, 'step%03d' % i)    # *************
    projector_writer.add_summary(summary, i)  # *************
    
    if i % 100 == 0:
        acc = sess.run(accuracy,feed_dict={x: mnist.test.images, y: mnist.test.labels})
        print ("Iter " + str(i) + ", Testing Accuracy= " + str(acc))

saver.save(sess, DIR + 'projector/projector/a_model.ckpt', global_step=max_steps)
projector_writer.close()
sess.close()

（2）打开tensorbored

运行后，会生成：

在cmd中，定位到F盘，

复制 http://DESKTOP-ER877HB:6006或输入http://localhost:6006在浏览器中打开

（3）projector 效果显示

有点慢，没画出来