How to calculate the output size after Conv2d in pytorch?

1

I am new about pytorch.
the example like this

inputs = torch.rand(1,1,10,10)
mod = nn.Conv2d(1,32,3,2,1)
out = mod(inputs)
print(out.shape)

the output is torch.Size([1, 32, 5, 5])
I think new_width = (old_width+2*padding-kernal_size)/stride +1.
but it cann’t divisible.
So how to calculate it in pytorch?

2

The complete formula for the output size is given in the docs. If it’s not divisible, the output size seems to be rounded down.

EDIT: new link to the Conv2d docs.

3

Is there a built in way to compute the output size of layers, without actually running the layer? I am looking for something like:

output_tensor_size = compute_output_size(layer, input_tensor_size)
4

You could take a look at the different approaches in this thread.

5

Following package calculates the output dimensions of common torch.nn operations:

You can install it by:

pip install torchshape

Disclaimer: I’m the creator of this package.