How to construct a network with two inputs in PyTorch

by

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

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.

More Related Contents:

  1. How to initialize weights in PyTorch?
  2. How do I initialize weights in PyTorch?
  3. How does Pytorch’s “Fold” and “Unfold” work?
  4. How can I use a weight matrix created by a trained neural network to make predictions in another file?
  5. What is a `”Python”` layer in caffe?
  6. How does Keras calculate the accuracy?
  7. Keras Sequential model input layer
  8. How to concatenate two layers in keras?
  9. Why do we need to call zero_grad() in PyTorch?
  10. What does model.eval() do in pytorch?
  11. PyTorch NotImplementedError in forward
  12. error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support
  13. What is the role of TimeDistributed layer in Keras?
  14. What’s the difference between torch.stack() and torch.cat() functions?
  15. How to use fit_generator with multiple inputs
  16. Pytorch RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0
  17. Tensor is not an element of this graph
  18. Neural network XOR gate not learning
  19. keras: how to save the training history attribute of the history object
  20. How to implement the ReLU function in Numpy
  21. Tensorflow One Hot Encoder?
  22. How to log Keras loss output to a file
  23. Can I send callbacks to a KerasClassifier?
  24. Keras give input to intermediate layer and get final output
  25. RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
  26. Pytorch ValueError: optimizer got an empty parameter list
  27. PyTorch Binary Classification – same network structure, ‘simpler’ data, but worse performance?
  28. Python – Detect a QR code from an image and crop using OpenCV
  29. Calculating percentage of Bounding box overlap, for image detector evaluation
  30. How is the Keras Conv1D input specified? I seem to be lacking a dimension

Leave a Comment