tensorflow课堂笔记（二）

#coding utf-8
"""
反向传播-》训练模型参数&＃xff0c;在所有参数上用梯度下降&＃xff0c;使NN模型在训练数据上的损失函数最小
损失函数&＃xff08;loss&＃xff09;&＃xff1a;预测值&＃xff08;y&＃xff09;与已知答案&＃xff08;y_&＃xff09;的差距
均方误差MSE : MSE(Y_,Y)&＃61;(Y-Y_)^2求算术平均值
loss &＃61; tf.reduce_mean(tf.square(y_-y))
反向传播训练方法&＃xff1a;以减小loss值为优化目标
train_step &＃61; tf.train.GradientDescentOptimizer(learing_rate).minimize(loss)
train_step &＃61; tf.train.MomentumOptimizer(learnin_rate,momentum).minimize(loss)
train_step &＃61; tf.train.AdamOptimizer(learning_rate).minimize(loss)
learning_rate表示每次更新的幅度"""
import tensorflow as tf
import numpy as np
BATCH_SIZE &＃61; 8
seed &＃61; 23455#基于seed产生随机数
rng &＃61; np.random.RandomState(seed)
#随机数返回32行2列的矩阵 表示32组体积和重量 作为输入数据集
X &＃61; rng.rand(32,2)
#从X这个32行2列的矩阵中 取出一行 判断如果小于1给Y赋值1 如果不小于1 给Y赋值0
#作为输入数据集的标签 &＃xff08;正确答案&＃xff09;
#Y值为1表示合格&＃xff0c;Y值为0表示不合格
Y &＃61; [[int(x0 &＃43; x1 <1)] for [x0, x1] in X]
print("X:\n",X)
print("Y:\n",Y)#1定义神经网络的输入&＃xff0c;参数的输出&＃xff0c;定义前向传播过程
x &＃61; tf.placeholder(tf.float32, shape&＃61;[None,2])
y_ &＃61; tf.placeholder(tf.float32, shape&＃61;[None,1])w1 &＃61; tf.Variable(tf.random_normal([2,3], stddev&＃61;1, seed&＃61;1)) #2行3列的矩阵
w2 &＃61; tf.Variable(tf.random_normal([3,1], stddev&＃61;1, seed&＃61;1)) #3行1列的矩阵a &＃61; tf.matmul(x, w1)
y &＃61; tf.matmul(a, w2)#2定义损失函数及反向传播方法
loss &＃61; tf.reduce_mean(tf.square(y-y_))
train_step &＃61; tf.train.GradientDescentOptimizer(0.001).minimize(loss)
#train_step &＃61; tf.train.MomentumOptimizer(0.001,0.9).minize(loss)
#train_step &＃61; tf.train.AdamOptimizer(0.001).minimize(loss)#3生成会话&＃xff0c;训练STEPS轮
with tf.Session() as sess:init_op &＃61; tf.global_variables_initializer()sess.run(init_op)#输出目前&＃xff08;未经训练&＃xff09; 的参数值print("W1:\n", sess.run(w1))print("W2:\n", sess.run(w2))print("\n")#训练模型STEPS &＃61; 10000for i in range(STEPS):start &＃61; (i % BATCH_SIZE) % 32 #24 25 26 27 28 29 30 31 32end &＃61; start &＃43; BATCH_SIZEsess.run(train_step, feed_dict&＃61;{x:X[start:end], y_:Y[start:end]})if i %500 &＃61;&＃61; 0:total_loss &＃61; sess.run(loss, feed_dict&＃61;{x: X,y_: Y})print("After %d training step(s), loss on all data is %g"%(i, total_loss))#输出训练后的参数值print("\n")print("w1:\n", sess.run(w1))print("w2:\n", sess.run(w2))"""输出结果&＃xff1a;X:[[0.83494319 0.11482951][0.66899751 0.46594987][0.60181666 0.58838408][0.31836656 0.20502072][0.87043944 0.02679395][0.41539811 0.43938369][0.68635684 0.24833404][0.97315228 0.68541849][0.03081617 0.89479913][0.24665715 0.28584862][0.31375667 0.47718349][0.56689254 0.77079148][0.7321604 0.35828963][0.15724842 0.94294584][0.34933722 0.84634483][0.50304053 0.81299619][0.23869886 0.9895604 ][0.4636501 0.32531094][0.36510487 0.97365522][0.73350238 0.83833013][0.61810158 0.12580353][0.59274817 0.18779828][0.87150299 0.34679501][0.25883219 0.50002932][0.75690948 0.83429824][0.29316649 0.05646578][0.10409134 0.88235166][0.06727785 0.57784761][0.38492705 0.48384792][0.69234428 0.19687348][0.42783492 0.73416985][0.09696069 0.04883936]]
Y:[[1], [0], [0], [1], [1], [1], [1], [0], [1], [1], [1], [0], [0], [0], [0], [0], [0], [1], [0], [0], [1], [1], [0], [1], [0], [1], [1], [1], [1], [1], [0], [1]]
2018-10-30 12:48:25.423305: I C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
W1:[[-0.8113182 1.4845988 0.06532937][-2.4427042 0.0992484 0.5912243 ]]
W2:[[-0.8113182 ][ 1.4845988 ][ 0.06532937]]After 0 training step(s), loss on all data is 5.13118
After 500 training step(s), loss on all data is 0.413201
After 1000 training step(s), loss on all data is 0.394286
After 1500 training step(s), loss on all data is 0.390501
After 2000 training step(s), loss on all data is 0.389507
After 2500 training step(s), loss on all data is 0.390754
After 3000 training step(s), loss on all data is 0.391654
After 3500 training step(s), loss on all data is 0.393698
After 4000 training step(s), loss on all data is 0.394749
After 4500 training step(s), loss on all data is 0.396768
After 5000 training step(s), loss on all data is 0.397619
After 5500 training step(s), loss on all data is 0.399442
After 6000 training step(s), loss on all data is 0.400045
After 6500 training step(s), loss on all data is 0.401661
After 7000 training step(s), loss on all data is 0.402039
After 7500 training step(s), loss on all data is 0.403473
After 8000 training step(s), loss on all data is 0.403664
After 8500 training step(s), loss on all data is 0.404948
After 9000 training step(s), loss on all data is 0.404988
After 9500 training step(s), loss on all data is 0.406149w1:[[-0.6102584 0.61458135 0.09446487][-2.371945 -0.00763825 0.5834913 ]]
w2:[[-0.19101174][ 0.6060787 ][-0.00777807]]""""""搭建神经网络的八股&＃xff1a;准备&＃xff0c;前传&＃xff0c;反转&＃xff0c;迭代0 准备 import常量定义生成数据集1.前向传播&＃xff1a; 定义输入&＃xff0c;参数和输出x&＃61;y_&＃61;w1&＃61;w2&＃61;a&＃61;y&＃61;2.反向传播&＃xff1a;定义损失函数&＃xff0c;反向传播方法loss&＃61;train_step&＃61;3.生成会话&＃xff0c;训练STEPS轮with tf.Session() as sessinit_op&＃61;tf.global_variables_initializer()sess_run&＃xff08;init_op&＃xff09;STEPS&＃61;3000for i in range(STEPS): #定义训练次数start&＃61; #每次循环喂入BASH的个数end&＃61;sess.run(train_step,feed_dict&＃61;)"""