Pass variable sized input to Linear layer in Pytorch

Question

I have a Linear() layer in Pytorch after a few Conv() layers. All the images in my dataset are black and white. However most of the images in my test set are of a different dimension than the images in my training set. Apart from resizing the images themselves, is there any way to define the Linear() layer in such a way that it takes a variable input dimension? For example something similar to view(-1)

You have to pre-process your image array before passing in torch.nn.Linear() layer. I think there is no way to pass any external parameter as you want. — Dishin Goyani
– Dishin Goyani, Commented Dec 25, 2019 at 12:09

Taras Sereda · Accepted Answer · 2019-12-25 14:23:10Z

2

Well, it doesn't make sense to have a Linear() layer with a variable input size. Because in fact it's a learnable matrix of shape [n_in, n_out]. And matrix multiplication is not defined for inputs if theirs feature dimension != n_in

What you can do is to apply pooling from functional API. You'll need to specify kernel_size and stride such that resulting output will have feature dimension size = n_in.

answered Dec 25, 2019 at 14:23

Taras Sereda

4304 silver badges9 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Pass variable sized input to Linear layer in Pytorch

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related