Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

TensorLy: Tensor Learning in Python

About

Tensors are higher-order extensions of matrices. While matrix methods form the cornerstone of machine learning and data analysis, tensor methods have been gaining increasing traction. However, software support for tensor operations is not on the same footing. In order to bridge this gap, we have developed \emph{TensorLy}, a high-level API for tensor methods and deep tensorized neural networks in Python. TensorLy aims to follow the same standards adopted by the main projects of the Python scientific community, and seamlessly integrates with them. Its BSD license makes it suitable for both academic and commercial applications. TensorLy's backend system allows users to perform computations with NumPy, MXNet, PyTorch, TensorFlow and CuPy. They can be scaled on multiple CPU or GPU machines. In addition, using the deep-learning frameworks as backend allows users to easily design and train deep tensorized neural networks. TensorLy is available at https://github.com/tensorly/tensorly

Jean Kossaifi, Yannis Panagakis, Anima Anandkumar, Maja Pantic• 2016

Related benchmarks

TaskDatasetResultRank
Kronecker regressionRandom n^2 x d^2 design matrix
Loss2.00e-4
118
Kronecker regressionSynthetic n^2 x d^2 design matrix (test)
Running Time (s)0.0106
118
Low-rank tensor decompositionCardiac MRI tensor
Avg Iteration Time (s)1.187
64
Tucker decompositionCardiac MRI tensor
Relative Reconstruction Error0.35
63
Tensor DecompositionCOIL-100
Average Iteration Time (s)2.455
48
Tensor DecompositionHyperspectral image tensor
Avg Iteration Time (s)1.873
48
Tensor ReconstructionCOIL-100 1.0 (test)
Relative Reconstruction Error0.349
48
Hyperspectral Tensor ReconstructionHyperspectral radiance image tensor (full)
Relative Reconstruction Error0.133
47
CP DecompositionUBER
Avg Time per ALS Round (s)64.2
4
CP DecompositionNELL-2
Average time per ALS round (seconds)759.6
4
Showing 10 of 10 rows

Other info

Follow for update