NN of TF: Using neural network algorithm to train and predict slope and intercept of data set (randomly generating 100 numbers with primary function) based on Tensorflow

 

directory

The output

Code design

 

 

The output

 

 

Code design

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' 
import tensorflow as tf
import numpy as np

x_data = np.random.rand(100).astype(np.float32)  
y_data = x_data*0.1 + 0.3                      

Weights = tf.Variable(tf.random_uniform([1] -1.0.1.0))  
biases = tf.Variable(tf.zeros([1]))                      

y = Weights*x_data + biases                  

loss = tf.reduce_mean(tf.square(y-y_data))        
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)

#init = tf.initialize_all_variables()  
init = tf.global_variables_initializer()     

### create tensorflow structure end ###

sess = tf.Session()   
sess.run(init)       

for step in range(201): 
    sess.run(train)     
    if step % 10= =0:    
        print(step, sess.run(Weights), sess.run(biases))
Copy the code

TF: One of Tensorflow function applications, randomly generated 100 numbers, using Tensorflow training to make it close to the slope and intercept of a known function