niftynet.network.dense_vnet module

class DenseVNet(num_classes, hyperparameters={}, architecture_parameters={}, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, acti_func='relu', name='DenseVNet')

Bases: niftynet.network.base_net.BaseNet

implementation of Dense-V-Net:

Gibson et al., “Automatic multi-organ segmentation on abdominal CT with dense V-networks”

layer_op(input_tensor, is_training, layer_id=-1)

image_resize(image, output_size)

class SpatialPriorBlock(prior_shape, output_shape, name='spatial_prior_block')

Bases: niftynet.layer.base_layer.TrainableLayer

layer_op()

class DenseFeatureStackBlock(n_dense_channels, kernel_size, dilation_rates, use_bdo, name='dense_feature_stack_block', **kwargs)

Bases: niftynet.layer.base_layer.TrainableLayer

layer_op(input_tensor, is_training=None, keep_prob=None)

class DenseFeatureStackBlockWithSkipAndDownsample(n_dense_channels, kernel_size, dilation_rates, n_seg_channels, n_downsample_channels, use_bdo, name='dense_feature_stack_block', **kwargs)

Bases: niftynet.layer.base_layer.TrainableLayer

layer_op(input_tensor, is_training=None, keep_prob=None)

class Affine3DAugmentationLayer(scale, interpolation, boundary, transform_func=None, name='AffineAugmentation')

Bases: niftynet.layer.base_layer.TrainableLayer

random_transform(batch_size)

inverse_transform(batch_size)

layer_op(input_tensor)

inverse(interpolation=None, boundary=None)