如何在 PyTorch 中构建具有两个输入的网络 [英] How to construct a network with two inputs in PyTorch

问题描述

假设我想要通用的神经网络架构:

Suppose I want to have the general neural network architecture:

Input1 --> CNNLayer 
                    
                     ---> FCLayer ---> Output
                    /
Input2 --> FCLayer

Input1 是图像数据，input2 是非图像数据.我已经在 Tensorflow 中实现了这个架构.

Input1 is image data, input2 is non-image data. I have implemented this architecture in Tensorflow.

我发现的所有 pytorch 示例都是通过每一层的一个输入.如何定义前向函数来分别处理 2 个输入，然后将它们组合在中间层?

All pytorch examples I have found are one input go through each layer. How can I define forward func to process 2 inputs separately then combine them in a middle layer?

推荐答案

组合它们"我认为您的意思是 连接两个输入.
假设您沿第二维连接:

By "combine them" I assume you mean to concatenate the two inputs.
Assuming you concat along the second dimension:

import torch
from torch import nn

class TwoInputsNet(nn.Module):
  def __init__(self):
    super(TwoInputsNet, self).__init__()
    self.conv = nn.Conv2d( ... )  # set up your layer here
    self.fc1 = nn.Linear( ... )  # set up first FC layer
    self.fc2 = nn.Linear( ... )  # set up the other FC layer

  def forward(self, input1, input2):
    c = self.conv(input1)
    f = self.fc1(input2)
    # now we can reshape `c` and `f` to 2D and concat them
    combined = torch.cat((c.view(c.size(0), -1),
                          f.view(f.size(0), -1)), dim=1)
    out = self.fc2(combined)
    return out

请注意，当您定义 self.fc2 的输入数量时，您需要同时考虑 self.conv 的 out_channels 作为以及c的输出空间维度.

Note that when you define the number of inputs to self.fc2 you need to take into account both out_channels of self.conv as well as the output spatial dimensions of c.

这篇关于如何在 PyTorch 中构建具有两个输入的网络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IT屋！