文章目录 一、tensorflow 下载安装二、Session三、Variable四、placeholder tensorflow 官网
一、tensorflow 下载安装
tensorflow详细安装过程 大佬介绍
下载完 tensorflow 后 需要下载相应的 keras 版本
tensorflow 与 keras 对应的版本
二、Session执行命令的东西
import tensorflow as tfmatrix1 tf.constant([[3, 3]])matrix2 tf.constant([[2], [2]])# print(matrix1)# print(matrix2)# matrix multiply np.dot(m1, m2) Go ahead and multiply the columnproduct tf.matmul(matrix1, matrix2)# method 1 . tf.Session() have removedsess tf.compat.v1.Session()# Each run executes a resultresult sess.run(product)# method 2with tf.Session() as sess: result2 sess.run(product) print(result2) 三、Variable import tensorflow as tf__all__ [tf]state tf.Variable(0, namecounter)print(state.name)one tf.constant(1)new_value tf.add(state, one)# new_value load in state, so state is new_valueupdata tf.assign(state, new_value)# must have if define variableinit tf.initialize_all_variables()with tf.Session() as sess: # At first must have the run(init) to initial sess.run(init) for _ in range(3): sess.run(updata) # you should print though this if you want to see result print(sess.run(state)) 四、placeholder import tensorflow as tf# placeholder show you can get a parameter when sess is runninginput1 tf.placeholder(tf.float32)input2 tf.placeholder(tf.float32)output tf.multiply(input1, input2)with tf.Session() as sess: # Through type dict to express the value print(sess.run(output, feed_dict{input1:[7.], input2:[2.]}))当使用多层神经网络是慎重考虑激励函数因为可能导致梯度消失和梯度爆炸
五、 tensorflow 搭建神经网络
import tensorflow as tfimport numpy as npdef add_layer(inputs, in_size, out_size, activation_functionNone): Weights tf.Variable(tf.random_normal([in_size, out_size])) biases tf.Variable(tf.zeros([1, out_size]) 0.1) Wx_plus_b tf.matmul(inputs, Weights) biases if activation_function is None: outputs Wx_plus_b else : outputs activation_function(Wx_plus_b) return outputsx_data np.linspace(-1, 1, 300)[:, np.newaxis]noise np.random.normal(0, 0.05, x_data.shape)y_data np.square(x_data) - 0.5 noisexs tf.placeholder(tf.float32, [None, 1])ys tf.placeholder(tf.float32, [None, 1])l1 add_layer(xs, 1, 10, activation_functiontf.nn.relu)predition add_layer(l1, 10, 1, activation_functionNone)# MSE,loss tf.reduce_mean(tf.reduce_sum(tf.square(ys - predition), reduction_indices[1]))# by 0.1 step upgradetrain_step tf.train.GradientDescentOptimizer(0.1).minimize(loss)# must initial the variableinit tf.initialize_all_variables()sess tf.Session()sess.run(init)for i in range(1000): sess.run(train_step, feed_dict{xs:x_data, ys:y_data}) if i % 100 0: print(sess.run(loss, feed_dict{xs:x_data, ys:y_data}))