daviduino.co.kr
techtogetworld.com
 david201207.blog.me
cafe.naver.com/3dpservicedavid


인공지능 구현에 대한 글입니다.
글의 순서는 아래와 같습니다.

================================================
1. X의 갯수가3개인 경우
  ==> 코딩이 매우 복잡해짐 , 대안으로 "매트릭스_행렬 "을 사용하면 간단해짐.
2. 매트릭스 적용
  ==> DATA 갯수(X 변수의갯수) 이 많아져도 간단하게 코딩이 가능해짐
3. TENSOR FLOW로 파일에서 DATA 읽어오기
  ==> DATA를  프로그램상에 올리면 메모리한계가 있으므로, DATA를 별도의 화일에 저장하고 불러오는것이 유리함
4. DATA QUE로 읽어들임 시간차로 처리해서 시스템 부하를 줄어줌
 ==> 화일이 많거나, 용량이 커지면  TENSORFLOW에서 자동으로 시간차를 두고 처리해주는 시스템 구현이 가능함
5. Next step
  ==> LOGISTICS 알고리즘 : CLASSSIFICATION 중 주요한 알고리즘.
6.참고자료 

=================================================

[ Cost 최소화 알고리즘 구현 소스코드 분석 ]

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

# Lab 4 Multi-variable linear regression

import tensorflow as tf

tf.set_random_seed(777)  # for reproducibility

==> x값이 3개

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.]

# placeholders for a tensor that will be always fed.

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 = x1 * w1 + x2 * w2 + x3 * w3 + b

print(hypothesis)

==> x,w값이 3개(x1,x2,x3 ,w1,w2,w3) 인 가설임

==> 코딩이 매우 복잡해짐 , 대안으로 "매트릭스_행렬 "을 사용하면 간단해짐.

# cost/loss function

cost = tf.reduce_mean(tf.square(hypothesis - Y))

# Minimize. Need a very small learning rate for this data set

optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)

train = optimizer.minimize(cost)

# Launch the graph in a session.

sess = tf.Session()

# Initializes global variables in the graph.

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)

'''

0 Cost:  19614.8

Prediction:

 [ 21.69748688  39.10213089  31.82624626  35.14236832  32.55316544]

10 Cost:  14.0682

Prediction:

 [ 145.56100464  187.94958496  178.50236511  194.86721802  146.08096313]

 ...

1990 Cost:  4.9197

Prediction:

 [ 148.15084839  186.88632202  179.6293335   195.81796265  144.46044922]

2000 Cost:  4.89449

Prediction:

 [ 148.15931702  186.8805542   179.63194275  195.81971741  144.45298767]

'''

[ 매트릭스 적용 ]

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

# Lab 4 Multi-variable linear regression

import tensorflow as tf

tf.set_random_seed(777)  # for reproducibility

매트릭로 DATA 적용

x_data = [[73., 80., 75.],

          [93., 88., 93.],

          [89., 91., 90.],

          [96., 98., 100.],

          [73., 66., 70.]]

y_data = [[152.],

          [185.],

          [180.],

          [196.],

          [142.]]

# placeholders for a tensor that will be always fed.

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')

매트릭스 곱샘 코딩

# Hypothesis

hypothesis = tf.matmul(X, W) + b

# Simplified cost/loss function

cost = tf.reduce_mean(tf.square(hypothesis - Y))

# Minimize

optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)

train = optimizer.minimize(cost)

# Launch the graph in a session.

sess = tf.Session()

# Initializes global variables in the graph.

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)

'''

0 Cost:  7105.46

Prediction:

 [[ 80.82241058]

 [ 92.26364136]

 [ 93.70250702]

 [ 98.09217834]

 [ 72.51759338]]

10 Cost:  5.89726

Prediction:

 [[ 155.35159302]

 [ 181.85691833]

 [ 181.97254944]

 [ 194.21760559]

 [ 140.85707092]]

...

1990 Cost:  3.18588

Prediction:

 [[ 154.36352539]

 [ 182.94833374]

 [ 181.85189819]

 [ 194.35585022]

 [ 142.03240967]]

2000 Cost:  3.1781

Prediction:

 [[ 154.35881042]

 [ 182.95147705]

 [ 181.85035706]

 [ 194.35533142]

 [ 142.036026  ]]

'''

[ TENSOR FLOW로 파일에서 DATA 읽어오기 ]

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

# Lab 4 Multi-variable linear regression

import tensorflow as tf

import numpy as np

tf.set_random_seed(777)  # for reproducibility

DATA는 CSV 화일에 저장됨, CSV 화일 위치는 PY 화일위치에 있음

xy = np.loadtxt('data-01-test-score.csv', delimiter=',', dtype=np.float32)

슬라이싱방법 숙지필요함

x_data = xy[:, 0:-1]

y_data = xy[:, [-1]]

# Make sure the shape and data are OK

print(x_data.shape, x_data, len(x_data))

print(y_data.shape, y_data)

# placeholders for a tensor that will be always fed.

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

hypothesis = tf.matmul(X, W) + b

# Simplified cost/loss function

cost = tf.reduce_mean(tf.square(hypothesis - Y))

# Minimize

optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)

train = optimizer.minimize(cost)

# Launch the graph in a session.

sess = tf.Session()

# Initializes global variables in the graph.

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)

나의 점수 예측

# Ask my score

print("Your score will be ", sess.run(

    hypothesis, feed_dict={X: [[100, 70, 101]]}))

print("Other scores will be ", sess.run(hypothesis,

                                        feed_dict={X: [[60, 70, 110], [90, 100, 80]]}))

'''

타인의 점수 예측

Your score will be  [[ 181.73277283]]

Other scores will be  [[ 145.86265564]

 [ 187.23129272]]

'''

[ DATA QUE로 읽어들임 시간차로 처리해서 시스템 부하를 줄어줌 ]

import tensorflow as tf

tf.set_random_seed(777)  # for reproducibility

화일 하나를 위한 QUE를 만듦

filename_queue = tf.train.string_input_producer(

    ['data-01-test-score.csv'], shuffle=False, name='filename_queue')

화일 리더 정의

reader = tf.TextLineReader()

key, value = reader.read(filename_queue)

# Default values, in case of empty columns. Also specifies the type of the

# decoded result.

CSV로 디코딩

record_defaults = [[0.], [0.], [0.], [0.]]

xy = tf.decode_csv(value, record_defaults=record_defaults)

불러올때마다 10 개씩 불러옴 (BATCH_SIZE =10 )

# collect batches of csv in

train_x_batch, train_y_batch = \

    tf.train.batch([xy[0:-1], xy[-1:]], batch_size=10)

# placeholders for a tensor that will be always fed.

X 3개 , Y 1개 데이터 숫자를 맞추어줌

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

hypothesis = tf.matmul(X, W) + b

# Simplified cost/loss function

cost = tf.reduce_mean(tf.square(hypothesis - Y))

# Minimize

optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)

train = optimizer.minimize(cost)

# Launch the graph in a session.

sess = tf.Session()

# Initializes global variables in the graph.

sess.run(tf.global_variables_initializer())

# Start populating the filename queue.

coord = tf.train.Coordinator()

threads = tf.train.start_queue_runners(sess=sess, coord=coord)

for step in range(2001):

x_batch , y_batch 값을  train feed_dict로 넘겨줌

    x_batch, y_batch = sess.run([train_x_batch, train_y_batch])

    cost_val, hy_val, _ = sess.run(

        [cost, hypothesis, train], feed_dict={X: x_batch, Y: y_batch})

    if step % 10 == 0:

        print(step, "Cost: ", cost_val, "\nPrediction:\n", hy_val)

coord.request_stop()

coord.join(threads)

# Ask my score

print("Your score will be ",

      sess.run(hypothesis, feed_dict={X: [[100, 70, 101]]}))

print("Other scores will be ",

      sess.run(hypothesis, feed_dict={X: [[60, 70, 110], [90, 100, 80]]}))

'''

Your score will be  [[ 177.78144836]]

Other scores will be  [[ 141.10997009]

 [ 191.17378235]]

'''

[참고자료 ]

https://www.inflearn.com/course/기본적인-머신러닝-딥러닝-강좌/

http://agiantmind.tistory.com/176 

https://www.tensorflow.org/install/

https://github.com/hunkim/deeplearningzerotoall

http://www.derivative-calculator.net/

http://terms.naver.com/entry.nhn?docId=3350391&cid=58247&categoryId=58247    ==> 미분계산/공식

http://matplotlib.org/users/installing.html   ==>matplotlib 설치