Mo TensorFlow Series Tutorial Learning

1. General machine learning predictive function coefficient (y=0.1x+0.3)

#-*-CODING:GBK-*-
import tensorflow as tf
import numpy as NP

#生成数据, y=0.1x+0.3
X_data=np.random.rand ( Astype (np.float32)
y_data=x_data*0.1+0.3


# # #开始创建tensorflow结构 ###
WEIGHT=TF. Variable (Tf.random_uniform ([1],-1.0,1.0))
BIASES=TF. Variable (Tf.zeros ([1]))

y=weight*x_data+biases

#误差
Loss=tf.reduce_mean (Tf.square (y-y_data)
) #优化器
Optimizer=tf.train.gradientdescentoptimizer (0.5)
#用优化器减少误差
train=optimizer.minimize (loss)

#定义初始化变量
init=tf.initialize_all_variables ()

# # #完成创建tensorflow结构 ###

SESS=TF. Session ()
Sess.run (init) #激活init to step in

range (201):
    Sess.run (train)
    if step%20==0:
        Print (Step,sess.run (weight), sess.run (biases))

2. Construct simple neural Network predictive y=x^2, visual interface display

#-*-CODING:GBK-*-import tensorflow as TF import numpy as NP import Matplotlib.pyplot as Plt def add_layer (inputs,in_s Ize,out_size,activation_function=none): WEIGHT=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,weight) +biases if Activation_function==none: Outputs=wx_plus_b else:outputs=activation_function (wx_plus_b) return outputs #numpy. Linspace (Start, Stop, num=50, Endpoint=true, Retstep=false, Dtype=none) #在指定的间隔内返回均匀间隔的数字 #[:,np.newaxis] Adding a new dimension to each element is equivalent to a matrix transpose, One row, multiple columns, multiple rows x_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+noise Xs=tf.placeholder (tf.float32,[none,1]) Ys=tf.placeholder (tf.float32,[none,1)) L1=add_layer (XS, 1,10,activation_function=tf.nn.relu) Prediction=add_layer (l1,10,1,activation_function=none) Loss=tf.reduce_mean ( Tf.reduce_sum (Tf.square (ys-prediction), reduction_indices=[1]) train_step=tf.train.gradientdescentoptimizer (0.1). Minimize (loss) init=tf.initialize_all_variables () sess=tf.
Session () Sess.run (init) #呼出画图窗口 fig=plt.figure () ax=fig.add_subplot (1,1,1) ax.scatter (x_data,y_data) #不暂停, continuous update status
        Plt.ion () plt.show () for I in range (1000): Sess.run (Train_step,feed_dict={xs:x_data,ys:y_data}) if i%50==0: #print (Sess.run (Loss,feed_dict={xs:x_data,ys:y_data})) Try:ax.lines.remove (Lines[0]) excep T exception:pass prediction_value=sess.run (Prediction,feed_dict={xs:x_data}) Lines=ax.plot (x_ Data,prediction_value, ' R ', lw=5) Plt.pause (0.1)

3.tensorflow Board Learning ... It's like adding a few names ...

#-*-CODING:GBK-*-import tensorflow as TF import numpy as NP import Matplotlib.pyplot as Plt def add_layer (inputs,in_s
            Ize,out_size,activation_function=none): With Tf.name_scope (' layer '): with Tf.name_scope (' weight '): WEIGHT=TF. Variable (Tf.random_normal ([in_size,out_size]), Name= ' W ') with Tf.name_scope (' biases '): BIASES=TF. Variable (Tf.zeros ([1,out_size]) +0.1,name= ' B ') with Tf.name_scope (' Wx_plus_b '): Wx_plus_b=tf.matmul (INP Uts,weight) +biases if Activation_function==none:outputs=wx_plus_b else:outputs=a Ctivation_function (Wx_plus_b) return outputs #numpy. Linspace (Start, Stop, num=50, Endpoint=true, Retstep=false, Dtype=none) #在指定的间隔内返回均匀间隔的数字 #[:,np.newaxis] Adds a new dimension to each element, which is equivalent to a matrix transpose, a row of multiple columns to a row of multiple rows X_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+noise with Tf.name_scope (' Inputs '): Xs=tf.placeholder (tf.float32,[nOne,1],name= ' X_input ') ys=tf.placeholder (tf.float32,[none,1],name= ' y_input ') L1=add_layer (xs,1,10,activation_ Function=tf.nn.relu) Prediction=add_layer (L1,10,1,activation_function=none) with tf.name_scope (' loss '): loss= Tf.reduce_mean (Tf.reduce_sum (Tf.square (ys-prediction), reduction_indices=[1]) with Tf.name_scope (' Train '): Train_ Step=tf.train.gradientdescentoptimizer (0.1). Minimize (loss) init=tf.initialize_all_variables () sess=tf. Session () Writer=tf.summary.filewriter ("logs/", Sess.graph) Sess.run (init) to I in range (1000): Sess.run (Train_step, Feed_dict={xs:x_data,ys:y_data}) if I%50==0:print (Sess.run (Loss,feed_dict={xs:x_data,ys:y_data}))