niftynet.network.vae module¶
-
class
niftynet.network.vae.
ConvDecoder
(layer_sizes_decoder, acti_func_decoder, trans_conv_output_channels, trans_conv_kernel_sizes, trans_conv_unpooling_factors, acti_func_trans_conv, upsampling_mode, downsampled_shape, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, name='ConvDecoder')¶ Bases:
niftynet.layer.base_layer.TrainableLayer
This is a generic decoder composed of fully-connected layers followed by {upsampling then transpose convolution} blocks. There is no batch normalisation on the final transpose convolutional layer.
-
layer_op
(codes, is_training)¶
-
-
class
niftynet.network.vae.
ConvEncoder
(denoising_variance, conv_output_channels, conv_kernel_sizes, conv_pooling_factors, acti_func_conv, layer_sizes_encoder, acti_func_encoder, serialised_shape, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, name='ConvEncoder')¶ Bases:
niftynet.layer.base_layer.TrainableLayer
This is a generic encoder composed of {convolutions then downsampling} blocks followed by fully-connected layers.
-
layer_op
(images, is_training)¶
-
-
class
niftynet.network.vae.
FCDecoder
(layer_sizes_decoder, acti_func_decoder, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, name='FCDecoder')¶ Bases:
niftynet.layer.base_layer.TrainableLayer
This is a generic fully-connected decoder.
-
layer_op
(codes, is_training)¶
-
-
class
niftynet.network.vae.
GaussianSampler
(number_of_latent_variables, number_of_samples_from_posterior, logvars_upper_bound, logvars_lower_bound, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, name='gaussian_sampler')¶ Bases:
niftynet.layer.base_layer.TrainableLayer
This predicts the mean and logvariance parameters, then generates an approximate sample from the posterior.
-
layer_op
(codes, is_training)¶
-
-
class
niftynet.network.vae.
VAE
(w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, name='VAE')¶ Bases:
niftynet.layer.base_layer.TrainableLayer
This is a denoising, convolutional, variational autoencoder (VAE), composed of a sequence of {convolutions then downsampling} blocks, followed by a sequence of fully-connected layers, followed by a sequence of {transpose convolutions then upsampling} blocks. See Auto-Encoding Variational Bayes, Kingma & Welling, 2014. 2DO: share the fully-connected parameters between the mean and logvar decoders.
-
layer_op
(images, is_training)¶
-