pytorch——nn.BatchNorm1d()

版权声明：本文为CSDN博主「七月听雪」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/qq_23262411/article/details/100175943

import torch
import torch.nn as nn
m = nn.BatchNorm1d(2)   # With Learnable Parameters
print('m:', m)
n = nn.BatchNorm1d(2, affine=False)   # Without Learnable Parameters
print('n:', n)
input = torch.randn(3, 2)
print('input:', input)
output = m(input)   # 列归一化
print('output:', input)

结果：
m:  BatchNorm1d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)

n:  BatchNorm1d(2, eps=1e-05, momentum=0.1, affine=False, track_running_stats=True)

input: tensor([[-2.2418, -0.1225],
       [ 0.1637, -0.1043],
       [-0.4440, -0.2567]])

output: tensor([[-2.2418, -0.1225],
         [ 0.1637, -0.1043],
         [-0.4440, -0.2567]])