为什么在不提及方法的情况下调用类的方法?

时间:2018-12-06 14:25:04

标签: python-3.x class

我目前正在阅读pytorch教程,但是我认为这个问题通常是关于python类的问题:https://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#sphx-glr-beginner-blitz-neural-networks-tutorial-py

具体来说,创建了一个名为Net的类,我们创建了一个名为net = Net()的对象。在Net类中,有一个方法forward(self,X)。但是,后来的转发只是通过编写net(X)来使用。它不是net.forward(X)吗?

import torch
import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


net = Net()
print(net)

input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)

1 个答案:

答案 0 :(得分:1)

如果您检查nn.Module中的source code,您会发现它实现了__call__,这使它的实例(及其子类的实例)可以调用。

def __call__(self, *input, **kwargs):
    for hook in self._forward_pre_hooks.values():
        hook(self, input)
    if torch.jit._tracing:
        result = self._slow_forward(*input, **kwargs)
    else:
        result = self.forward(*input, **kwargs)
    for hook in self._forward_hooks.values():
        hook_result = hook(self, input, result)
        if hook_result is not None:
            raise RuntimeError(
                "forward hooks should never return any values, but '{}'"
                "didn't return None".format(hook))
    if len(self._backward_hooks) > 0:
        var = result
        while not isinstance(var, torch.Tensor):
            if isinstance(var, dict):
                var = next((v for v in var.values() if isinstance(v, torch.Tensor)))
            else:
                var = var[0]
        grad_fn = var.grad_fn
        if grad_fn is not None:
            for hook in self._backward_hooks.values():
                wrapper = functools.partial(hook, self)
                functools.update_wrapper(wrapper, hook)
                grad_fn.register_hook(wrapper)
    return result


那就是为什么

net = Net()
input = torch.randn(1, 1, 32, 32)
out = net(input)

是完全有效的代码。 net(input)执行net.__call__(input)