How to set the Conv2d to have a common filter over all input channels

vision
1

How to set the Conv2d layer to convolve one common filter (one filter per kernel) over all input channels rather than creating one per each input channel?

2

By default each filter in a conv layer will use all input channels and create a single output channel.
Could you describe your use case a bit more in case nn.Conv2d(in_channels, 1, ...) won’t work?

4

Thanks. There is no special use case as it is a part of another bigger project. I need a conv layer with different kernels and one filter per kernel to be shared between all input channels. The “nn.Conv2d(in_channels, 1, …)” will do the job however, I need to define multiples of this in case of having output_channels > 1.

Do I need to modify the C codes to implement this?

5

I’m not sure how to understand:

Filters and kernels are used as a synonym while it seems you put a different meaning to these terms. Could you explain what means what exactly?

6

Hi Moslem!

If I understand your use case correctly, you can reshape your input tensor
to “move” the channels dimension into the batch dimension, pass it into a
convolution with a single input channel, in_channels = 1, and then reshape
the output to restore the initial batch dimension. Something like this:

>>> import torch
>>> torch.__version__
'2.0.0'
>>> _ = torch.manual_seed (2023)
>>> conv = torch.nn.Conv2d (1, 1, 3)
>>> t = torch.randn (2, 3, 5, 5)
>>> conv (t.reshape (6, 1, 5, 5)).reshape (2, 3, 3, 3).shape
torch.Size([2, 3, 3, 3])

Best.

K. Frank

7

Sorry for the ambiguity in my description. @KFrank 's solution is roughly what I am looking for.

8

Thank you Frank. You saved me a lot of time.