陌花拟的博客

自己构建一些数据，来实现一个简单函数的模拟学习import tensorflow as tfimport numpy as np# create datax_data = np.random.rand(100).astype(np.float32)y_data = x_data*0.1 + 0.3# create tensorflow structure startWeig...

Session的两种使用方式import tensorflow as tfmatrix1 = tf.constant([[3,3]])matrix2 = tf.constant([[2,2]])product = tf.matmul(matrix1,matrix2) # matrix multiply np.dot(m1,m2)# session的两种打开模式# me...

Variable变量的简单使用在 Tensorflow 中，定义了某字符串是变量，它才是变量，这一点是与 Python 所不同的import tensorflow as tfstate = tf.Variable(0,name = 'counter')print(state.name)one = tf.constant(1)new_vaule = tf.add(state...

placeholder传值import tensorflow as tfinput1 = tf.placeholder(tf.float32)input2 = tf.placeholder(tf.float32)output = tf.multiply(input1,input2)# with tf.Session as sess:sess = tf.Session()pri...

1. 搭建神经网络基本流程定义添加神经层的函数1.训练的数据 2.定义节点准备接收数据 3.定义神经层：隐藏层和预测层 4.定义 loss 表达式 5.选择 optimizer 使 loss 达到最小然后对所有变量进行初始化，通过 sess.run optimizer，迭代 1000 次进行学习：import tensorflow as tfimport numpy as...

TensorFlow搭建神经网络可视化结果import tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltdef add_layer(inputs, in_size, out_size, activation_function = None): Weights = tf.Variable(tf....