TensorFlow introductory tutorial (3)

tags: api tensorflow Artificial Intelligence-Neural Network Algorithm python

Continue from aboveTensorFlow introductory tutorial (2)
Training (tf.train API)
tensorflow provides optimizers (optimizers) to slowly change each variable to minimize the loss function. The simplest optimizer is gradient descent, which modifies the parameter value according to the derivative of the loss function with respect to the variable. Tensorflow can use the method tf.gradients to automatically calculate derivatives for a given model.

optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)
sess.run(init)
for i in range(1000):
    sess.run(train,{x:[1,2,3,4],y:[0,-1,-2,-3]})
print(sess.run([W,b]))

The output is:

[array([-0.9999969], dtype=float32), array([ 0.99999082], dtype=float32)]

Linear regression complete code
So far, we have successfully completed a machine learning, although it is just a simple linear regression. Post the complete linear regression code here:

import tensorflow as tf

sess = tf.Session()

W = tf.Variable([.3],dtype=tf.float32)
b = tf.Variable([-.3],dtype=tf.float32)
x = tf.placeholder(tf.float32)
linear_model = W*x+b

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

y = tf.placeholder(tf.float32) 
squared_deltas = tf.square(linear_model-y) 
loss = tf.reduce_sum(squared_deltas) 
print(sess.run(loss,{x:[1,2,3,4],y:[0,-1,-2,-3]})) 

fixW = tf.assign(W,[-1.])
fixb = tf.assign(b,[1.])
sess.run([fixW,fixb])
print(sess.run(loss,{x:[1,2,3,4],y:[0,-1,-2,-3]}))

optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)
sess.run(init)
for i in range(1000):
    sess.run(train,{x:[1,2,3,4],y:[0,-1,-2,-3]})
print(sess.run([W,b]))

writer = tf.summary.FileWriter('D:/ten', tf.get_default_graph())
writer.close()

The results are as follows:

23.66
0.0
[array([-0.9999969], dtype=float32), array([ 0.99999082], dtype=float32)]

The view in tensorboard is as follows:

So far we have been able to use TensorFlow for the simplest machine learning operation-linear regression.

Learn more here
TensorFlow newbies actually break the verification code

Intelligent Recommendation

pyqt5 introductory tutorial (3)

In fact, it can be seen from the previous code that in the main function part, only three things are actually done 1. Create an application 2. Create a graphical interface 3. The exit signal will be a...

octave introductory tutorial (3)

Matrix Operations Matrix A * B .* Means multiplying matrix by number Matrix + number means adding the number to each element in the matrix A’ represents matrix transpose log is the logarithmic f...