class

LazyInstanceNorm1d

extends_LazyInstanceNormMixin

LazyInstanceNorm1d(eps: float = 1e-05, momentum: float = 0.1, affine: bool = False, track_running_stats: bool = False, device: DeviceLike = None, dtype: DTypeLike = None)

source

InstanceNorm1d with lazy num_features inference.

Identical to InstanceNorm1d except that num_features is inferred from x.shape[1] on the first forward pass.

Parameters

epsfloat= 1e-05

Numerical stability constant. Default: 1e-5.

momentumfloat= 0.1

EMA factor for optional running statistics. Default: 0.1.

affinebool= False

If True, lazily allocates per-channel scale and shift. Default: False.

track_running_statsbool= False

If True, lazily allocates running mean/variance buffers. Default: False.

deviceDeviceLike= None

Device for lazily allocated tensors. Default: None.

dtypeDTypeLike= None

Data type for lazily allocated tensors. Default: None.

Notes

Input: $(N, C, L)$ — same as InstanceNorm1d. C is inferred on the first forward pass.
Output: same shape as the input.

Examples

>>> import lucid
>>> import lucid.nn as nn
>>> norm = nn.LazyInstanceNorm1d()
>>> x = lucid.randn(4, 48, 100)
>>> out = norm(x)   # num_features=48 inferred here
>>> out.shape
(4, 48, 100)
With affine parameters inferred lazily:
>>> norm_affine = nn.LazyInstanceNorm1d(affine=True)
>>> out2 = norm_affine(x)
>>> out2.shape
(4, 48, 100)