# data and label
x1 = [73., 93., 89., 96., 73.]
x2 = [80., 88., 91., 98., 66.]
x3 = [75., 93., 90., 100., 70.]
Y = [152., 185., 180., 196., 142.]
# weights
w1 = tf.Variable(10.)
w2 = tf.Variable(10.)
w3 = tf.Variable(10.)
b = tf.Variable(10.)
hypothesis = w1 * x1 + w2 * x2 + w3 * x3 + b
w1 = tf.Variable(tf.random_normal([1]))
w2 = tf.Variable(tf.random_normal([1]))
w3 = tf.Variable(tf.random_normal([1]))
b = tf.Variable(tf.random_normal([1]))
learning_rate = 0.000001
for i in range(1000 + 1):
# tf.GradientTape() to record the gradient of the cost function
with tf.GradientTape() as tape:
# 내부에 있는 변수들의 변화량을 tape에 기록한다.
hypothesis = w1 * x1 + w2 * x2 + w3 * x3 + b
cost = tf.reduce_mean(tf.square(hypothesis - Y))
# calculates the gradients of the cost
# cost와 4개의 변수의 기울기값을 구함
w1_grad, w2_grad, w3_grad, b_grad = tape.gradient(cost, [w1, w2, w3, b])
# update w1, w2, w3 and b
w1.assign_sub(learning_rate * w1_grad)
w2.assign_sub(learning_rate * w2_grad)
w3.assign_sub(learning_rate * w3_grad)
b.assign_sub(learning_rate * b_grad)
if i % 50 == 0:
print("{:5} | {:12.4f}".format(i, cost.numpy()))
import numpy as np
data = np.array([
# X1, X2, X3, y
[73., 80., 75., 152.],
[93., 88., 93., 185.],
[89., 91., 90., 180.],
[96., 98., 100.,196.],
[73., 66., 70., 142.],
], dtype=np.float32)
# slice data
# 앞은 행, 뒤는 열
# :는 "처음부터 끝까지"
# :-1은 "마지막 열 제외"
# [:, [-1]]은 "마지막 열만 2차원 컬럼 벡터로"
X = data[:, :-1] # 모든 행, 마지막 열을 뺀 특징 3개 → shape [5,3]
y = data[:, [-1]] # 모든 행, 마지막 열만 → shape [5,1]
W = tf.Variable(tf.random_normal([3, 1])) # 변수가 3개, 출력이 1개
b = tf.Variable(tf.random_normal([1]))
# hypothesis, prediction function
def predict(X):
return tf.matmul(X, W) + b # 이후에 b를 생략할 수도 있음
W = tf.Variable(tf.random_normal([3, 1])) # 변수 3개 → [3,1]
b = tf.Variable(tf.random_normal([1]))
# hypothesis, prediction function
def predict(X):
return tf.matmul(X, W) + b # 필요 시 b 생략 가능
import tensorflow as tf
import numpy as np
tf.random.set_seed(0)
data = np.array([
# X1, X2, X3, y
[73., 80., 75., 152.],
[93., 88., 93., 185.],
[89., 91., 90., 180.],
[96., 98., 100., 196.],
[73., 66., 70., 142.],
], dtype=np.float32)
# slice data
X = data[:, :-1]
y = data[:, [-1]]
W = tf.Variable(tf.random.normal([3, 1]))
b = tf.Variable(tf.random.normal([1]))
learning_rate = 0.000001
# hypothesis, prediction function
def predict(X):
return tf.matmul(X, W) + b
n_epochs = 20000
for i in range(n_epochs + 1):
# record the gradient of the cost function
with tf.GradientTape() as tape:
cost = tf.reduce_mean(tf.square(predict(X) - y))
# calculates the gradients of the loss
W_grad, b_grad = tape.gradient(cost, [W, b])
# updates parameters (W and b)
W.assign_sub(learning_rate * W_grad)
b.assign_sub(learning_rate * b_grad)
if i % 100 == 0:
print("{:5} | {:10.4f}".format(i, cost.numpy()))
# initialize W
w1 = tf.Variable(tf.random.normal([1]))
w2 = tf.Variable(tf.random.normal([1]))
w3 = tf.Variable(tf.random.normal([1]))
# hypothesis
hypothesis = w1 * x1 + w2 * x2 + w3 * x3 + b
# updates
w1.assign_sub(learning_rate * w1_grad)
w2.assign_sub(learning_rate * w2_grad)
w3.assign_sub(learning_rate * w3_grad)
# initialize W
W = tf.Variable(tf.random.normal([3, 1]))
# hypothesis
hypothesis = tf.matmul(X, W) + b
# updates
W.assign_sub(learning_rate * W_grad)
출처: 모두를 위한 딥러닝 강좌 2
https://www.youtube.com/watch?v=7eldOrjQVi0&list=PLQ28Nx3M4Jrguyuwg4xe9d9t2XE639e5C