nn.ReLU和nn.functional.relu有什么区别

其中nn.ReLU作为一个层结构，必须添加到nn.Module容器中才能使用

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1   = nn.Linear(16*5*5, 120)
        self.fc2   = nn.Linear(120, 84)
        self.fc3   = nn.Linear(84, 40)
        self.fc4   = nn.Linear(40, 10)
        ***self.relu = nn.ReLU()***
    def forward(self, x):
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(x.size()[0], -1)
        ***x = self.relu(self.fc1(x))***
        ***x = self.relu(self.fc2(x))***
        ***x = self.relu(self.fc3(x))***
        x = self.fc4(x)
        return x

而F.ReLU则作为一个函数调用，看上去作为一个函数调用更方便更简洁。

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1   = nn.Linear(16*5*5, 120)
        self.fc2   = nn.Linear(120, 84)
        self.fc3   = nn.Linear(84, 40)
        self.fc4   = nn.Linear(40, 10)
  
    def forward(self, x):
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(x.size()[0], -1)
        ***x = torch.nn.functional.relu(self.fc1(x))***
        ***x = torch.nn.functional.relu(self.fc2(x))***
        ***x = torch.nn.functional.relu(self.fc3(x))***
        x = self.fc4(x)
        return x

具体使用哪种方式，取决于编程风格。