[Bug] has_torch_function_variadic error

[lucafrost]

Describe the bug When attempting to initialise a model (I've tried with AutoLayoutModel and Detectron2LayoutModel), torch.jit throws a RuntimeError as below...

RuntimeError: 
undefined value has_torch_function_variadic:
  File "/opt/conda/lib/python3.8/site-packages/torch/utils/smdebug.py", line 2962
         >>> loss.backward()
    """
    if has_torch_function_variadic(input, target, weight, pos_weight):
       ~~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
        return handle_torch_function(
            binary_cross_entropy_with_logits,
'binary_cross_entropy_with_logits' is being compiled since it was called from 'sigmoid_focal_loss'
  File "/opt/conda/lib/python3.8/site-packages/fvcore/nn/focal_loss.py", line 34
    """
    p = torch.sigmoid(inputs)
    ce_loss = F.binary_cross_entropy_with_logits(inputs, targets, reduction="none")
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
    p_t = p * targets + (1 - p) * (1 - targets)
    loss = ce_loss * ((1 - p_t) ** gamma)

To Reproduce Steps to reproduce the behavior:

1. Install layout-parser, OpenCV, Detectron2 as below

%pip install opensearch-py opencv-python --quiet
%pip install -U layoutparser[ocr] --quiet
!python -m pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cpu/torch1.10/index.html

2. Import layoutparser and attempt to init model with lp.models.Detectron2LayoutModel(...)
3. Error appears

Environment Linux with layoutparser latest