python::tensorflow

텐서플로우 객체를 만들고 이름을 출력하는 방법

import tensorflow as tf

hello = tf.constant("Hi, TensorFlow")

sess = tf.Session()

print(sess.run(hello))

텐서플로우 객체 생성후 사용법

import tensorflow as tf

node1 = tf.constant(3.0, tf.float32)
node2 = tf.constant(4.0)
node3 = tf.add(node1,node2)

print("node1:",node1, "node2:", node2)
print("node3: ",node3)

 

 

객체이기 때문에 프린터 할수 없다

 

import tensorflow as tf

node1 = tf.constant(3.0, tf.float32)
node2 = tf.constant(4.0)
node3 = tf.add(node1,node2)

#that is no print
#print("node1:",node1, "node2:", node2)
#print("node3: ",node3)

sess = tf.Session()
print("sess.run(node1,node2): ", sess.run([node1,node2]))
print("sess.run(node3): ", sess.run(node3))

 

그래프를 빌드한후 sess.run을 통해서 그래프를 실행시킨다.

 

 

import tensorflow as tf

a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
adder_node = a + b
sess = tf.Session()
#feed_dict is that vlaue is returned
print(sess.run(adder_node, feed_dict={a: 3, b:4.5}))
print(sess.run(adder_node, feed_dict={a: [1,3],b:[2,4]}))

 

feed_dict는 비어잇는 노드 a b에게 값을 넘겨준다. 배열 형태로 넘겨줄수도 있다.

대표사진 삭제

사진 설명을 입력하세요.

Build graph using TF operations

linear regression 구현

 

import tensorflow as tf

x_train = [1, 2, 3]
y_train = [1, 2, 3]

w = tf.Variable(tf.random_normal([1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name ='bias')
# Our hypothesis XW+b
hypothesis = x_train * w + b

# cost/loss function
cost = tf.reduce_mean(tf.square(hypothesis - y_train))

# Minimize
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
train = optimizer.minimize(cost)

# Launch the groph in a session.
sess= tf.Session()
# Initializes global variables in the graph.
sess.run(tf.global_variables_initializer())

# Fit the Line
for step in range(2001):
    sess.run(train)
    if step & 20 ==0:
        print(step, sess.run(cost), sess.run(w), sess.run(b))

 

tf.random_normal([1]) // 랜덤한 1차원 형식값 리턴

reduce_mean() //평균

train = optimizer.minimize(cost) // cost값을 최소화 한다.

 

 

값을 내가 feed_dict로 정해줄수도 있다.

 

import tensorflow as tf

x = tf.placeholder(tf.float32, shape=[None])
y = tf.placeholder(tf.float32, shape=[None])
w = tf.Variable(tf.random_normal([1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name ='bias')
# Our hypothesis XW+b
hypothesis = x * w + b

# cost/loss function
cost = tf.reduce_mean(tf.square(hypothesis - y))

# Minimize
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
train = optimizer.minimize(cost)

# Launch the groph in a session.
sess= tf.Session()
# Initializes global variables in the graph.
sess.run(tf.global_variables_initializer())

# Fit the Line
for step in range(2001):
    cost_val, w_val, v_val, _ = sess.run([cost, w, b, train],
    feed_dict = {x: [1, 2, 3, 4, 5],
                 y: [2.1, 3.1, 4.1, 5.1, 6.1]})
    if step & 20 ==0:
        print(step, cost_val, w_val, v_val)