|View source on GitHub|
Feature gating as used in S3D-G.
tfm.vision.layers.SelfGating( filters, **kwargs )
This implements the S3D-G network from: Saining Xie, Chen Sun, Jonathan Huang, Zhuowen Tu, Kevin Murphy. Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification. (https://arxiv.org/pdf/1712.04851.pdf)
||Additional keyword arguments to be passed.|
call( inputs )
This is where the layer's logic lives.
call() method may not create state (except in its first
invocation, wrapping the creation of variables or other resources in
tf.init_scope()). It is recommended to create state, including
tf.Variable instances and nested
__init__(), or in the
build() method that is
called automatically before
call() executes for the first time.
Input tensor, or dict/list/tuple of input tensors.
The first positional
||Additional positional arguments. May contain tensors, although this is not recommended, for the reasons above.|
Additional keyword arguments. May contain tensors, although
this is not recommended, for the reasons above.
The following optional keyword arguments are reserved:
|A tensor or list/tuple of tensors.|