Skip to main content

Deep Learning with Tensors in Python, using PyTorch and TensorLy.

Project description

https://badge.fury.io/py/tensorly-torch.svg

TensorLy-Torch

TensorLy-Torch is a Python library for deep tensor networks that builds on top of TensorLy and PyTorch. It allows to easily leverage tensor methods in a deep learning setting and comes with all batteries included.

With TensorLy-Torch, you can easily:

  • Tensor Factorizations: decomposing, manipulating and initializing tensor decompositions can be tricky. We take care of it all, in a convenient, unified API.

  • Leverage structure in your data: with tensor layers, you can easily leverage the structure in your data, through Tensor Regression Layers, Factorized Convolutions, etc

  • Built-in tensor layers: all you have to do is import tensorly torch and include the layers we provide directly within your PyTorch models!

  • Tensor hooks: you can easily augment your architectures with our built-in Tensor Hooks. Robustify your network with Tensor Dropout and automatically select the rank end-to-end with L1 Regularization!

  • All the methods available: we are always adding more methods to make it easy to compare between the performance of various deep tensor based methods!

Deep Tensorized Learning

Tensor methods generalize matrix algebraic operations to higher-orders. Deep neural networks typically map between higher-order tensors. In fact, it is the ability of deep convolutional neural networks to preserve and leverage local structure that, along with large datasets and efficient hardware, made the current levels of performance possible. Tensor methods allow to further leverage and preserve that structure, for individual layers or whole networks.

./doc/_static/tensorly-torch-pyramid.png

TensorLy is a Python library that aims at making tensor learning simple and accessible. It provides a high-level API for tensor methods, including core tensor operations, tensor decomposition and regression. It has a flexible backend that allows running operations seamlessly using NumPy, PyTorch, TensorFlow, JAX, MXNet and CuPy.

TensorLy-Torch is a PyTorch only library that builds on top of TensorLy and provides out-of-the-box tensor layers.

Improve your neural networks with tensor methods

Tensor methods generalize matrix algebraic operations to higher-orders. Deep neural networks typically map between higher-order tensors. In fact, it is the ability of deep convolutional neural networks to preserve and leverage local structure that, along with large datasets and efficient hardware, made the current levels of performance possible. Tensor methods allow to further leverage and preserve that structure, for individual layers or whole networks.

In TensorLy-Torch, we provide convenient layers that do all the heavy lifting for you and provide the benefits tensor based layers wrapped in a nice, well documented and tested API.

For instance, convolution layers of any order (2D, 3D or more), can be efficiently parametrized using tensor decomposition. Using a CP decomposition results in a separable convolution and you can replace your original convolution with a series of small efficient ones:

./doc/_static/cp-conv.png

These can be easily perform with FactorizedConv in TensorLy-Torch. We also have Tucker convolutions and new tensor-train convolutions! We also implement various other methods such as tensor regression and contraction layers, tensorized linear layers, tensor dropout and more!

Installing TensorLy-Torch

Through pip

pip install tensorly-torch

From source

git clone https://github.com/tensorly/torch
cd torch
pip install -e .

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tensorly-torch-0.5.0.tar.gz (43.3 kB view hashes)

Uploaded Source

Built Distribution

tensorly_torch-0.5.0-py3-none-any.whl (59.3 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page