confused about the BN layer

Hi,thanks for your works.
The BN layer in pytorch is
class torch.nn.BatchNorm2d(num_features, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
in your code you choose the default parameters. Is that right for object detection with a small batchsize?

Locate the BatchNorm2d uses in the repository and review how PyTorch's default parameters are applied in the object-detection code. Compare that configuration with the small-batch setting described in the issue; done means providing a clear, repository-specific explanation or documenting any required change.

Written by the indexing model from the issue text.