|View source on GitHub|
Applies a feature mask on features if the mask is not None.
nsl.lib.apply_feature_mask( features, feature_mask=None )
features: A dense tensor representing features.
feature_mask: A dense tensor with values in [0, 1] and a broadcastable shape to 'features'. If not set, or set to None, the 'features' will be returned untouched.
A dense tensor has the same shape as 'features'.