PyTorch之nn.ReLU与F.ReLU的区别介绍

import torch.nn as nn
import torch.nn.functional as F
import torch.nn as nn
 
class AlexNet_1(nn.Module):
 
  def __init__(self, num_classes=n):
    super(AlexNet, self).__init__()
    self.features = nn.Sequential(
      nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1),
      nn.BatchNorm2d(64),
      nn.ReLU(inplace=True),
     )
 
  def forward(self, x):
    x = self.features(x)
 
class AlexNet_2(nn.Module):
 
  def __init__(self, num_classes=n):
    super(AlexNet, self).__init__()
    self.features = nn.Sequential(
      nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1),
      nn.BatchNorm2d(64),
     )
 
  def forward(self, x):
    x = self.features(x)
    x = F.ReLU(x)

import torch
x = torch.rand(2)
x
Out[3]: tensor([0.3486, 0.2924])  #<-----这是x初始值
 
y = torch.rand(2)
y
Out[5]: tensor([0.6301, 0.0101])  #<-----这是y初始值
x.add(y)
Out[6]: tensor([0.9788, 0.3026])   #<-----这是x+y的结果
x
Out[7]: tensor([0.3486, 0.2924])  #<-----这是执行操作之后x的值
y
Out[8]: tensor([0.6301, 0.0101])   #<-----这是执行操作之后y的值

import torch
x = torch.rand(2)
x
Out[3]: tensor([0.3486, 0.2924])  #<-----这是x初始值
y = torch.rand(2)
y
Out[5]: tensor([0.6301, 0.0101])  #<-----这是y初始值
x.add_(y)
Out[9]: tensor([0.9788, 0.3026])  #<-----这是x+y结果
x
Out[10]: tensor([0.9788, 0.3026]) #<-----这是操作后x的值
y
Out[11]: tensor([0.6301, 0.0101])  #<-----这是操作后y的值