PyTorch 中的 nn.functional() 与 nn.sequential() 之间是否存在计算效率差异

问题描述

以下是使用 PyTorch 中的 nn.functional() 模块的前馈网络

The following is a Feed-forward network using the nn.functional() module in PyTorch

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

class newNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(784, 128)
        self.fc2 = nn.Linear(128, 64)
        self.fc3 = nn.Linear(64,10)

    def forward(self,x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = F.softmax(self.fc3(x))
        return x

model = newNetwork()
model

以下是相同的前馈，使用 nn.sequential() 模块基本上构建相同的东西.两者有什么区别，我什么时候会用一个而不是另一个?

The following is the same Feed-forward using nn.sequential() module to essentially build the same thing. What is the difference between the two and when would i use one instead of the other?

input_size = 784
hidden_sizes = [128, 64]
output_size = 10

构建前馈网络

 model = nn.Sequential(nn.Linear(input_size, hidden_sizes[0]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[0], hidden_sizes[1]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[1], output_size),
                      nn.Softmax(dim=1))
    print(model)

推荐答案

两者没有区别.后者可以说更简洁，更容易编写，并且像 ReLU 和 Sigmoid 这样的纯(即无状态)函数的客观"版本的原因是允许它们使用在像 nn.Sequential.

There is no difference between the two. The latter is arguably more concise and easier to write and the reason for "objective" versions of pure (ie non-stateful) functions like ReLU and Sigmoid is to allow their use in constructs like nn.Sequential.

这篇关于PyTorch 中的 nn.functional() 与 nn.sequential() 之间是否存在计算效率差异的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！