美文网首页
Tensorflow 笔记

Tensorflow 笔记

作者: a十二_4765 | 来源:发表于2017-10-19 13:24 被阅读34次

    1 Hello Word

    import tensorflow as tf

    hello_op =tf.constant("hello,word!")

    with tf.Session() as sess:

            print(sess.run(hello_op))

    2.Tensorflow 简单运算

    import tensorflow as tf

    a  = tf.add(3,5)

    sess = tf.Session()

    print(sess.run(a))

    # 8

    sess.close();

    简单运用

      加载Tensorflow 简历俩个matrix 输出俩个matrix 矩阵相乘的结果 matmul 表示俩个矩阵相乘

     import    tensorflow    as  tf

    matrix1 =tf.constant([3,3])

    matrix2 = tf.constant([[2],[2]])

    product = tf.matmul(matrix1,matrix2)

    product 不是直接计算的步骤,我们会使用session来激活 product 计算结果 

    sess = tf.Session()

    result =sess.run(product)

    print(result)

    Variable 变量

    import tensorflow as tf

    state =tf.Variable(0,name='counter')

    #定义常量 one

    one =tf .constant(1)

    # 定义加法步骤

    new_value = tf.add(state,one)

    # 将state 更新成new_value

    update = tf.assign(state,new_value)

    #使用Session

    with tf.Session() as sess:

    sess.run(init)

    for _ in range(3):

          sess.run(update)

           print(sess.run(state))

    占位符 placeholder

    import tensorflow as tf

    input1 = tf.placeholder(tf.float32)

    input2 =tf.placeholder(tf.float32)

    #mul = multiply 是将input1 和input2 做乘法运算,并输出为output

    output =tf.multiply(input1,input2)

    with tf.Session() as sess:

          print(sess.run(ouput,feed_dict={input1:[7.],input2:[2.]}))

    添加层 def add_layer()

    相关文章

      网友评论

          本文标题:Tensorflow 笔记

          本文链接:https://www.haomeiwen.com/subject/qlfuuxtx.html