-
Notifications
You must be signed in to change notification settings - Fork 0
/
scaling.py
30 lines (25 loc) · 1.16 KB
/
scaling.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
import numpy as np
class RunningMeanStd(object):
# https://en.wikipedia.org/wiki/Algorithms_for_calculating_variance#Parallel_algorithm
def __init__(self, epsilon=1e-4, shape=()):
self.mean = np.zeros(shape, 'float64')
self.var = np.ones(shape, 'float64')
self.count = epsilon
def update(self, x):
batch_mean = np.mean(x, axis=0)
batch_var = np.var(x, axis=0)
batch_count = x.shape[0]
self.update_from_moments(batch_mean, batch_var, batch_count)
def update_from_moments(self, batch_mean, batch_var, batch_count):
self.mean, self.var, self.count = update_mean_var_count_from_moments(
self.mean, self.var, self.count, batch_mean, batch_var, batch_count)
def update_mean_var_count_from_moments(mean, var, count, batch_mean, batch_var, batch_count):
delta = batch_mean - mean
tot_count = count + batch_count
new_mean = mean + delta * batch_count / tot_count
m_a = var * count
m_b = batch_var * batch_count
M2 = m_a + m_b + np.square(delta) * count * batch_count / tot_count
new_var = M2 / tot_count
new_count = tot_count
return new_mean, new_var, new_count