12 - logistic classification 실습

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

# 학습할 데이터들

# 공부시간
x_data = [[1, 2],[2, 3],[3, 1],[4, 3],[5, 3],[6, 2]]
# 결과 0은 불합 1은 합격
y_data = [[0],[0],[0],[1],[1],[1]]

X = tf.placeholder(tf.float32, shape=[None, 2])
Y = tf.placeholder(tf.float32, shape=[None, 1])

W = tf.Variable(tf.random_normal([2, 1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name='bias')

# sigmode 만들고
hypothesis = tf.sigmoid(tf.matmul(X, W) + b)

# cost 정의해주고
cost = -tf.reduce_mean(Y * tf.log(hypothesis) + (1 - Y) * tf.log(1 - hypothesis))

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

# 예상
predicted = tf.cast(hypothesis > 0.5, dtype=tf.float32)
# 정확도
accuracy = tf.reduce_mean(tf.cast(tf.equal(predicted, Y), dtype=tf.float32))

# 학습
with tf.Session() as sess:
    # 초기화
    sess.run(tf.global_variables_initializer())

    for step in range(10001):
        cost_val, _ = sess.run([cost, train], feed_dict={X: x_data, Y: y_data})
        if step % 200 == 0:
            print(step, cost_val)

    # 정확도 예측
    h, c, a = sess.run([hypothesis, predicted, accuracy],feed_dict={X: x_data, Y: y_data})
    print("\nHypothesis: ", h, "\nCorrect (Y): ", c, "\nAccuracy: ", a)

 

참조

[1] - https://www.youtube.com/watch?v=2FeWGgnyLSw&list=PLlMkM4tgfjnLSOjrEJN31gZATbcj_MpUm&index=13