win incorrect in sim.gaussian filter?

[peterlionelnewman]

For 3d images was getting the error:

out = conv(out, weight=win.transpose(2 + i, -1), stride=1, padding=0, groups=C)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: expected stride to be a single integer value or a list of 2 values to match the convolution dimensions, but got stride=[1, 1, 1]

though weight was 4D? is this incorrect and requires and undate?

def gaussian_filter(input: Tensor, win: Tensor) -> Tensor:
    r""" Blur input with 1-D kernel
    Args:
        input (torch.Tensor): a batch of tensors to be blurred
        window (torch.Tensor): 1-D gauss kernel
    Returns:
        torch.Tensor: blurred tensors
    """
    ndim = input.dim()

    assert all([ws == 1 for ws in win.shape[1:-1]]), win.shape
    if ndim == 4:
        conv = F.conv2d
    elif ndim == 5:
        conv = F.conv3d
    else:
        raise NotImplementedError(input.shape)

    C = input.shape[1]
    out = input
    for i, s in enumerate(input.shape[2:]):
        if ndim == 5:
            weight = win.view(1, 1, 1, 1, win.shape[-1])
        elif ndim == 4:
            weight = win.view(1, 1, 1, win.shape[-1])

        if s >= win.shape[-1]:
            out = conv(out, weight=weight, stride=1, padding=0, groups=C)
        else:
            warnings.warn(
                f"Skipping Gaussian Smoothing at dimension 2+{i} for input: {input.shape} and win size: {win.shape[-1]}"
            )

    return out

Let me know,

[lxy51]

Same question