GitHub projects

A state-of-the-art generic dense feature extractor. [Deprecated]

A package for feature extraction in Torch. Provides SIFT and dSIFT modules. [Deprecated]

A bundle adjustment/structure from motion package. [Deprecated]

allows us to use hugin to stitch images and apply same stitching to a video sequence. [Deprecated]

code and tools around integral images. A library for finding interest points based on fast integral histograms. [Deprecated]

A video/graph library for Torch. This package provides routines to construct graphs on videos, segment them, build trees out of them, and convert them back to videos. [Deprecated]

An image/graph library for Torch. This package provides routines to construct graphs on images, segment them, build trees out of them, and convert them back to images. [Deprecated]

Torch CUDA Neural Network Implementation.

Torch CUDA Implementation.

KNN, kernel-weighted average, local linear regression smoothers. [Deprecated]

A Lua wrapper around the Locality sensitive hashing library SHKit [Deprecated]

Spaghetti (sparse linear) module for torch7 by @MichaelMathieu [Deprecated]

OpenGM is a C++ library for graphical modelling, and inference. The Lua bindings provide a simple way of describing graphs, from Lua, and then optimizing them with OpenGM. [Deprecated]

An old vowpalwabbit interface to torch. [Deprecated]

FFI Wrapper for liblbfgs. [Deprecated]

Torch-SVM library. [Deprecated]

A package to manipulate manifolds.

A package for unsupervised learning in Torch. Provides modules that are compatible with nn (LinearPsd, ConvPsd, AutoEncoder, ...), and self-contained algorithms (k-means, PCA). [Deprecated]

An optimization library for Torch. SGD, Adagrad, Conjugate-Gradient, LBFGS, RProp and more.

A deep learning library designed for streamlining research and development using the Torch7 distribution. It emphasizes flexibility through the elegant use of object-oriented design patterns. [Deprecated]

Many useful features that aren't part of the main nn package.

A Recurrent Neural Network library that extends Torch's nn. RNNs, LSTMs, GRUs, BRNNs, BLSTMs, etc.

A completely unstable and experimental package that extends Torch's builtin nn library.

This package provides graphical computation for nn library in Torch7.

framework for torch which provides a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming.

Neural Network package for Torch.

A signal processing toolbox for Torch-7. FFT, DCT, Hilbert, cepstrums, stft.

Numpy's randomkit, wrapped for Torch. [Deprecated]

Graph package for Torch. [Deprecated]

Autograd automatically differentiates native Torch code. Inspired by the original Python version.

Cephes mathematical functions library, wrapped for Torch. Provides and wraps the 180+ special mathematical functions from the Cephes mathematical library, developed by Stephen L. Moshier. It is used, among many other places, at the heart of SciPy. [Deprecated]

On-device streaming speech recognition SDK for Android with Kotlin bindings (JitPack). Based on NVIDIA NeMo FastConformer (80 ms cache-aware lookahead). Companion Silero VAD, wake-word, and 14-command KWS via same runtime.

Deep learning framework written in Kotlin.

Reproducible data setup for reproducible science.

An image library for Julia.

Presentations for JuliaCon.

Digital Signal Processing (filtering, periodograms, spectrograms, window functions).

Basic sampling algorithms for Julia.

Time series toolkit for Julia.

Data structures that allow missing values. [Deprecated]

A Julia package for probability distributions and associated functions.

library for working with tabular data in Julia.

Julia package for loading many of the data sets available in R.

Statistical tests for Julia.

Crafty statistical graphics for Julia.

Hypothesis tests for Julia.

Read files from Stata, SAS, and SPSS.

library for working with tabular data in Julia. [Deprecated]