zoukankan      html  css  js  c++  java
  • 129、TensorFlow计算图的可视化

    import tensorflow as tf
    # Build your graph
    x = tf.constant([[37.0, -23.0], [1.0, 4.0]], name="inputs")
    w = tf.Variable(tf.random_uniform([2, 2]), name="weights")
    _y = tf.matmul(x, w, name="predict_y")
    y = tf.constant([[74.0, -46.0], [2.0, 8.0]], name="target_y")
    loss = tf.losses.mean_squared_error(y, _y, w)
    train_op = tf.train.AdagradOptimizer(0.01).minimize(loss)
    init = tf.global_variables_initializer()
    with tf.Session() as sess:
        sess.run(init)
        # 'sess.graph' provides access to the graph used in a 'tf.Session'
        writer = tf.summary.FileWriter("tmp/log/", sess.graph)
        
        # Perform your computation...
        for i in range(10000):
            _, loss_op = sess.run([train_op, loss])
            print("The loss on step " + str(i) + "  is " + str(loss_op))
            if(loss_op<=0.1):
                break;
        writer.close()

  • 相关阅读:
    【lc-database】595. 大的国家
    Visual Studio 2010软件安装教程
    Win10系统下安装VC6.0教程
    HTTP协议
    正则表达式
    类装饰器
    装饰器工厂函数
    装饰器函数
    闭包
    web服务器
  • 原文地址:https://www.cnblogs.com/weizhen/p/8451504.html
Copyright © 2011-2022 走看看