import tensorflow as tf
# 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(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:
hypothesis = w1 * x1 + w2 * x2 + w3 * x3 + b
cost = tf.reduce_mean(tf.square(hypothesis - Y))
# calculates the gradients of the cost
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()))
0 | 138610.9688 50 | 1538.7153 100 | 17.7539 150 | 0.8772 200 | 0.6898 250 | 0.6875 300 | 0.6874 350 | 0.6872 400 | 0.6871 450 | 0.6869 500 | 0.6868 550 | 0.6867 600 | 0.6865 650 | 0.6864 700 | 0.6862 750 | 0.6861 800 | 0.6860 850 | 0.6858 900 | 0.6857 950 | 0.6855 1000 | 0.6854
import numpy as np
data = np.array([
[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] # [ row slicing, col slicing]
y = data[:, [-1]]
W = tf.Variable(tf.random.normal([3, 1])) # row 3개 col 1개
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 = 10000
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 % 1000 == 0:
print("{:5} | {:10.4f}".format(i, cost.numpy()))
0 | 11874.3613 1000 | 3.6428 2000 | 3.6052 3000 | 3.5689 4000 | 3.5338 5000 | 3.5000 6000 | 3.4672 7000 | 3.4354 8000 | 3.4045 9000 | 3.3745 10000 | 3.3454