Joker_xun的博客

import tensorflow as tfmatrix1 = tf.constant([[3,3]])matrix2 = tf.constant([[2], [2]])product =tf.matmul(matrix1,matrix2) #将矩阵1与矩阵2相乘控制方式1：sess = tf.Session()result = se...

在Tensorflow中的，对于变量使用tf.Variable()语句进行定义，然后加入初始化器tf.initialize_all_variables()，最后sess.run(init)对变量进行真正的初始化import tensorflow as tfstate = tf.Variable(0,name='counter') #若有定义Variableprint(state.na...

使用placeholder（）类型时，说明你是想在结果运行时在给里面的变量赋值使用placeholder（）必须与feed_dict（）绑定在一起import tensorflow as tfinput1 = tf.placeholder(tf.float32)input2 = tf.placeholder(tf.float32)output = tf.multiply(input1...

#神经系统的搭建import tensorflow as tfimport numpy as npimport matplotlib,pylab as pltdef add_layer(input,in_size,out_size,activation_function = None): Weights = tf.Variable(tf.random_normal([in_siz...

1、AttributeError: ‘module’ object has noattribute ‘random_crop’tf.scalar_summary(loss.op.name,loss)改为tf.summary.scalar(loss.op.name, loss)即可2、AttributeError: ‘module’ object has no attribute’pe...