全连接层:BatchNorm1d
卷积层:BatchNorm2d(batch,C,H,W)->(1,C,1,1)(每个卷积层1个均值,一个方差)
import torch
from torch import nn
from d2l import torch as d2l
def batch_norm(X, gamma, beta, moving_mean, moving_var, eps, momentum):
# 通过is_grad_enabled来判断当前模式是训练模式还是预测模式
if not torch.is_grad_enabled():
# 如果是在预测模式下,直接使用传入的移动平均所得的均值和方差
X_hat = (X - moving_mean) / torch.sqrt(moving_var + eps)
else:
assert len(X.shape) in (2, 4)
if len(X.shape) == 2:
# 使用全连接层的情况,计算特征维上的均值和方差
mean = X.mean(dim=0)
var = ((X - mean) ** 2).mean(dim=0)
else:
# 使用二维卷积层的情况,计算通道维上(axis=1)的均值和方差。
# 这里我们需要保持X的形状以便后面可以做广播运算
mean = X.mean(dim=(0, 2, 3), keepdim=True)
var = ((X - mean) ** 2).mean(dim=(0, 2, 3), keepdim=True)
# 训练模式下,用当前的均值和方差做标准化
X_hat = (X - mean) / torch.sqrt(var + eps)
# 更新移动平均的均值和方差
moving_mean = momentum * moving_mean + (1.0 - momentum) * mean
moving_var = momentum * moving_var + (1.0 - momentum) * var
Y = gamma * X_hat + beta # 缩放和移位
return Y, moving_mean.data, moving_var.data```