1

我计划实现一个类似于此博客(或仅使用tf.nn.batch_normalization)的批量归一化函数tf.nn.moments来计算均值和方差,但我希望对矢量和图像类型的时间数据执行此操作。我通常在理解如何axestf.nn.moments.

我的矢量序列输入数据有 shape (batch, timesteps, channels),我的图像序列输入数据有 shape (batch, timesteps, height, width, 3)(注意它们是 RGB 图像)。在这两种情况下,我都希望在整个批次跨时间步长上进行标准化,这意味着我不想为不同的时间步长保持单独的均值/方差。

如何正确设置axes不同的数据类型(例如图像、矢量)和时间/非时间?

4

1 回答 1

1

考虑它的最简单方法是 - 传入的轴axes将被折叠,并且统计数据将通过切片来计算axes。例子:

import tensorflow as tf

x = tf.random.uniform((8, 10, 4))

print(x, '\n')
print(tf.nn.moments(x, axes=[0]), '\n')
print(tf.nn.moments(x, axes=[0, 1]))
Tensor("random_uniform:0", shape=(8, 10, 4), dtype=float32)

(<tf.Tensor 'moments/Squeeze:0'   shape=(10, 4) dtype=float32>,
 <tf.Tensor 'moments/Squeeze_1:0' shape=(10, 4) dtype=float32>)

(<tf.Tensor 'moments_1/Squeeze:0'   shape=(4,) dtype=float32>,
 <tf.Tensor 'moments_1/Squeeze_1:0' shape=(4,) dtype=float32>)

从源代码中,math_ops.reduce_mean用于计算meanvariance,其运行方式如下:

# axes = [0]
mean = (x[0, :, :] + x[1, :, :] + ... + x[7, :, :]) / 8
mean.shape == (10, 4)  # each slice's shape is (10, 4), so sum's shape is also (10, 4)

# axes = [0, 1]
mean = (x[0, 0,  :] + x[1, 0,  :] + ... + x[7, 0,  :] +
        x[0, 1,  :] + x[1, 1,  :] + ... + x[7, 1,  :] +
        ... +
        x[0, 10, :] + x[1, 10, :] + ... + x[7, 10, :]) / (8 * 10)
mean.shape == (4, ) # each slice's shape is (4, ), so sum's shape is also (4, )

换句话说,axes=[0]将计算(timesteps, channels)关于samples- 即迭代samples,计算(timesteps, channels)切片的均值和方差的统计信息。因此,对于

标准化将在整个批次和时间步中发生,这意味着我不想为不同的时间步保持单独的均值/方差

您只需要折叠timesteps维度(沿samples),并通过迭代和计算统计samples信息timesteps

axes = [0, 1]

图像的相同故事,除了你有两个非通道/样本尺寸,你会做axes = [0, 1, 2](折叠samples, height, width)。


伪代码演示:查看平均计算

import tensorflow as tf
import tensorflow.keras.backend as K
import numpy as np

x = tf.constant(np.random.randn(8, 10, 4))
result1 = tf.add(x[0], tf.add(x[1], tf.add(x[2], tf.add(x[3], tf.add(x[4], 
                       tf.add(x[5], tf.add(x[6], x[7]))))))) / 8
result2 = tf.reduce_mean(x, axis=0)
print(K.eval(result1 - result2))
# small differences per numeric imprecision
[[ 2.77555756e-17  0.00000000e+00 -5.55111512e-17 -1.38777878e-17]
 [-2.77555756e-17  2.77555756e-17  0.00000000e+00 -1.38777878e-17]
 [ 0.00000000e+00 -5.55111512e-17  0.00000000e+00 -2.77555756e-17]
 [-1.11022302e-16  2.08166817e-17  2.22044605e-16  0.00000000e+00]
 [ 0.00000000e+00  0.00000000e+00  0.00000000e+00  0.00000000e+00]
 [-5.55111512e-17  2.77555756e-17 -1.11022302e-16  5.55111512e-17]
 [ 0.00000000e+00  0.00000000e+00  0.00000000e+00 -2.77555756e-17]
 [ 0.00000000e+00  0.00000000e+00  0.00000000e+00 -5.55111512e-17]
 [ 0.00000000e+00 -3.46944695e-17 -2.77555756e-17  1.11022302e-16]
 [-5.55111512e-17  5.55111512e-17  0.00000000e+00  1.11022302e-16]]
于 2019-11-07T18:15:10.823 回答