nip.utils.torch.BatchNorm1dSimulateBatchDims#
- class nip.utils.torch.BatchNorm1dSimulateBatchDims(num_features: int, eps: float = 1e-05, momentum: float = 0.1, affine: bool = True, track_running_stats: bool = True, device=None, dtype=None)[source]#
Batch normalization layer with arbitrary batch dimensions.
See
torch.nn.BatchNorm1d
for documentation.Assumes an input of shape (… features).
Methods Summary
forward
(x)Apply the module to the input tensor, simulating multiple batch dimensions.
Attributes
T_destination
call_super_init
dump_patches
feature_dims
num_features
eps
momentum
affine
track_running_stats
training
Methods