[딥러닝 기본 09] Lab 04_1 - multi-variable linear regression을 tensorflow에서 구현하기

모두를 위한 머신러닝 / 딥러닝 김성훈 교수님 강의를 듣고 정리한 내용입니다.

Lab 04_1 - multi-variable linear regression을 tensorflow에서 구현하기  

@ x1, x2, x3 (출석, 퀴즈, 중간)를 통해 Y(기말)를 예측

- data set

@ TensorFlow

- Matrix를 사용하지 않은 예제 (이런식으로 하면 안됨)

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

import tensorflow as tf

# 학습 데이터
x1_data = [73., 93., 89., 96., 73.]
x2_data = [80., 88., 91., 98., 66.]
x3_data = [75., 93., 90., 100., 70.]
y_data = [152., 185., 180., 196., 142.]

# placeholder
x1 = tf.placeholder(tf.float32)
x2 = tf.placeholder(tf.float32)
x3 = tf.placeholder(tf.float32)
Y = tf.placeholder(tf.float32)

w1 = tf.Variable(tf.random_normal([1]), name='weight1')
w2 = tf.Variable(tf.random_normal([1]), name='weight2')
w3 = tf.Variable(tf.random_normal([1]), name='weight3')
b = tf.Variable(tf.random_normal([1]), name='bias')

# Hypothesis
hypothesis = x1 * w1 + x2 * w2 + x3 * w3 + b

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

# Minimize : gradient descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)
train = optimizer.minimize(cost)

# 세션 준비 및 초기화
sess = tf.Session()
sess.run(tf.global_variables_initializer())

for step in range(2001):
    cost_val, hy_val, _ = sess.run([cost, hypothesis, train],
                                   feed_dict={x1: x1_data, x2: x2_data, x3: x3_data, Y: y_data})
    if step % 10 == 0:
        print(step, "cost: ", cost_val, "\nPrediction:\n", hy_val)
        # 2000 cost:  1.29522
        # Prediction:
        #  [ 150.25749207  185.29418945  180.15109253  197.58331299  141.0925293 ]

- Matrix 사용 예제

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

import tensorflow as tf

# 학습 데이터
# x_data shape = [5, 3]
# y_data shape = [5, 1]
x_data = [[73., 80., 75.],
          [93., 88., 93.],
          [89., 91., 90.],
          [96., 98., 100.],
          [73., 66., 70.]]
y_data = [[152.],
          [185.],
          [180.],
          [196.],
          [142.]]

# placeholder : shape 주의!!
X = tf.placeholder(tf.float32, shape=[None, 3])
Y = tf.placeholder(tf.float32, shape=[None, 1])

W = tf.Variable(tf.random_normal([3, 1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name='bias')

# Hypothesis : Matrix 이용
hypothesis = tf.matmul(X, W) + b

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

# Minimize : gradient descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)
train = optimizer.minimize(cost)

# 세션 준비 및 초기화
sess = tf.Session()
sess.run(tf.global_variables_initializer())

for step in range(2001):
    cost_val, hy_val, _ = sess.run([cost, hypothesis, train], feed_dict={X: x_data, Y: y_data})
    if step % 10 == 0:
        print(step, "cost: ", cost_val, "\nPrediction:\n", hy_val)
        # 2000 cost:  0.784948 
        # Prediction:
        #  [[ 150.69198608]
        #  [ 185.04780579]
        #  [ 180.29139709]
        #  [ 197.24359131]
        #  [ 141.23834229]]