niftynet.layer.base_layer module¶
-
class
niftynet.layer.base_layer.
DataDependentLayer
(name='data_dependent_op')¶ Bases:
niftynet.layer.base_layer.Layer
Some layers require a one-pass training through the training set to determine their internal models, this abstract provides interfaces for training these internal models and querying the status.
-
is_ready
()¶
-
train
(*args, **kwargs)¶
-
-
class
niftynet.layer.base_layer.
Invertible
¶ Bases:
object
interface of Invertible data
-
inverse_op
(*args, **kwargs)¶
-
-
class
niftynet.layer.base_layer.
Layer
(name='untitled_op')¶ Bases:
object
-
layer_op
(*args, **kwargs)¶
-
layer_scope
()¶
-
to_string
()¶
-
-
class
niftynet.layer.base_layer.
LayerFromCallable
(layer_op, name='untitled_op')¶ Bases:
niftynet.layer.base_layer.Layer
Module wrapping a function provided by the user. Analogous to snt.Module
-
layer_op
(*args, **kwargs)¶
-
-
class
niftynet.layer.base_layer.
RandomisedLayer
(name='randomised_op')¶ Bases:
niftynet.layer.base_layer.Layer
The layers require a randomisation process, to randomly change some of the layer’s states on the fly.
-
randomise
(*args, **kwargs)¶
-
-
class
niftynet.layer.base_layer.
TrainableLayer
(name='trainable_op')¶ Bases:
niftynet.layer.base_layer.Layer
Extends the Layer object to have trainable parameters, adding intiailizers and regularizers.
-
initializers
¶
-
num_trainable_params
()¶
-
regularizer_loss
()¶
-
regularizers
¶
-
restore_from_checkpoint
(checkpoint_name, scope=None)¶
-
to_string
()¶
-
trainable_variables
()¶
-