API reference
tltorch
: Tensorized Deep Neural Networks
Tensor Regression Layers
TuckerTRL (input_shape, output_shape, rank[, …]) |
Tensor Regression Layer with Tucker weights [Rd83a5f2390c0-1] |
CPTRL (input_shape, output_shape, rank[, …]) |
Tensor Regression Layer with CP weights [Rbacc2ed11ff5-1], [Rbacc2ed11ff5-2] |
TensorTrainTRL (input_shape, output_shape, rank) |
Tensor Regression Layer with Tensor-Train weights [Ra045891b45b0-1], [Ra045891b45b0-2] |
Tensor Contraction Layers
Factorized Linear Layers
TTLinear (in_features, out_features, …[, bias]) |
Tensorized Fully-Connected Layers |
TTMLinear (in_features, out_features, …[, …]) |
Tensorized Fully-Connected Layers in the TT-Matrix format [R34bd7c4440a9-1] |
CPLinear (in_features, out_features, …[, bias]) |
Tensorized Fully-Connected Layers |
TuckerLinear (in_features, out_features, …) |
Tensorized Fully-Connected Layers |
Factorized Convolutions
tltorch.factorized_conv
: General N-Dimensional convolutions in Factorized forms
TuckerConv (*args, **kwargs) |
Create a convolution of arbitrary order with a Tucker kernel |
CPConv (*args, **kwargs) |
Create a Factorized CP convolution of arbitrary order. |
TTConv (*args, **kwargs) |
Create a convolution of arbitrary order with a Tucker kernel. |
Tensor Dropout
Tensor Dropout for TensorModules
Classes
Unless you have a particular use for the classes, you should use the convenient functions provided instead.
TuckerDropout (proba[, min_dim]) |
Decomposition Hook for Tensor Dropout on Tucker tensors |
CPDropout (proba[, min_dim]) |
Decomposition Hook for Tensor Dropout on Tucker tensors |
TTDropout (proba[, min_dim]) |
Decomposition Hook for Tensor Dropout on Tucker tensors |
Functions
Convenience functions to easily add or remove tensor dropout from tensor layers.
L1 Regularization
L1 Regularization on tensor modules.
TuckerL1Regularizer ([penalty, …]) |
Decomposition Hook for Tensor Lasso on Tucker tensors |
CPL1Regularizer ([penalty, clamp_weights, …]) |
Decomposition Hook for Tensor Lasso on TT tensors |
TTL1Regularizer ([penalty, clamp_weights, …]) |
Decomposition Hook for Tensor Lasso on TT tensors |
Initialization
Module for initializing tensor decompositions
cp_init (weights, factors[, std]) |
Initializes directly the weights and factors of a CP decomposition so the reconstruction has the specified std and 0 mean |
tucker_init (core, factors[, std]) |
Initializes directly the weights and factors of a Tucker decomposition so the reconstruction has the specified std and 0 mean |
tt_init (factors[, std]) |
Initializes directly the weights and factors of a TT decomposition so the reconstruction has the specified std and 0 mean |
Internal
TensorModule (*args, **kwargs) |
A PyTorch module augmented for tensor parametrization |