def __init__(
self,
eps=1e-5,
momentum=0.1,
affine=True,
track_running_stats=True,
device=None,
dtype=None,
) -> None:
factory_kwargs = {"device": device, "dtype": dtype}
super(_LazyInstanceNorm, self).__init__(
# affine and track_running_stats are hardcoded to False to
# avoid creating tensors that will soon be overwritten.
0,
eps,
momentum,
False,
False,
**factory_kwargs,
)
self.affine = affine
self.track_running_stats = track_running_stats
if self.affine:
self.weight = UninitializedParameter(**factory_kwargs)
self.bias = UninitializedParameter(**factory_kwargs)
if self.track_running_stats:
self.running_mean = UninitializedBuffer(**factory_kwargs)
self.running_var = UninitializedBuffer(**factory_kwargs)
self.num_batches_tracked = torch.tensor(
0,
dtype=torch.long,
**{k: v for k, v in factory_kwargs.items() if k != "dtype"},
)
def __init__(self,
eps=1e-5,
momentum=0.1,
affine=True,
track_running_stats=True):
super(_LazyBatchNorm, self).__init__(0, eps, momentum, affine,
track_running_stats)
if self.affine:
self.weight = UninitializedParameter()
self.bias = UninitializedParameter()
if self.track_running_stats:
self.running_mean = UninitializedBuffer()
self.running_var = UninitializedBuffer()
def __init__(self, eps=1e-5, momentum=0.1, affine=True, track_running_stats=True):
super(_LazyBatchNorm, self).__init__(
# affine and track_running_stats are hardcoded to False to
# avoid creating tensors that will soon be overwritten.
0, eps, momentum, False, False)
self.affine = affine
self.track_running_stats = track_running_stats
if self.affine:
self.weight = UninitializedParameter()
self.bias = UninitializedParameter()
if self.track_running_stats:
self.running_mean = UninitializedBuffer()
self.running_var = UninitializedBuffer()
self.num_batches_tracked = torch.tensor(0, dtype=torch.long)