BatchNorm3d¶
- class
dragon.vm.torch.nn.
BatchNorm3d
(
num_features,
eps=1e-05,
momentum=0.1,
affine=True,
track_running_stats=True
)[source]¶ Apply the batch normalization over 4d input. [Ioffe & Szegedy, 2015].
The normalization is defined as:
\[y = \frac{x - \mathrm{E}[x]} {\sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta \]The running average of statistics are calculated as:
\[x_{\text{running}} = (1 - \text{momentum}) * x_{\text{running}} + \text{momentum} * x_{\text{batch}} \]See also
__init__¶
BatchNorm3d.
__init__
(
num_features,
eps=1e-05,
momentum=0.1,
affine=True,
track_running_stats=True
)[source]¶Create a
BatchNorm3d
module.- Parameters:
- num_features (int) – The number of channels.
- eps (float, optional, default=1e-5) – The value to \(\epsilon\).
- momentum (float, optional, default=0.1) – The value to \(\text{momentum}\).
- affine (bool, optional, default=True) –
True
to apply an affine transformation. - track_running_stats (bool, optional, default=True) –
True
to using stats when switching toeval
.