Why does groups kwarg in conv2d have different requirements in functional?

1

The convolutional layers (e.g. nn.Conv2d) require groups to divide both in_channels and out_channels. The functional convolutions (e.g. nn.functional.conv2d) only require groups to divide in_channels.

This leads to confusing behavior:

import numpy as np
import torch
from torch import nn
from torch.nn import functional as F

# testing
batch_size = 1

w_img = 1
h_img = 1

c_in = 6
c_out = 9

filter_len = 1

groups = 3

image = np.arange(6, dtype=np.float32).reshape(batch_size, c_in, h_img, w_img)
filters = np.empty((c_out, c_in // groups, filter_len, filter_len), dtype=np.float32)
filters.fill(0.5)

image = torch.tensor(image)
filters = torch.tensor(filters)

features_functional = F.conv2d(image, filters, padding=filter_len // 2, groups=groups)
print(features_functional.shape[1])  # 9

layer = nn.Conv2d(c_in, c_out, filter_len, padding=filter_len // 2, groups=groups)
print(layer.out_channels)  # 9

Here both forms have 9 out_channels. Changing groups to 2, however results in 8 out_channels from the functional form and an exception thrown from the other.

I see two problems with this:

  1. Inconsistency (despite the fact that both are documented correctly).
  2. The functional form opaquely rounds out_channels down to the nearest integer that is divisible by groups. This is a non-obvious process for the user.

Is there a reason for this difference? If not, it seems like the functional form should throw a similar error.

2

It seems to be fixed in the current master, although the error message is a bit unclear:

RuntimeError: std::exception

EDIT: I’ve created an issue here. Thanks for reporting it!