Search Results for "tensor" - Page 4
Sort By:
Showing 101 open source projects for "tensor"
View related business solutions-
Your monitoring isn't a stack. It's a pile. Fix that.Replace Datadog, New Relic, and Sentry without adding three more dashboards.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
NN-SVG
Publication-ready NN-architecture schematics
Illustrations of Neural Network architectures are often time-consuming to produce, and machine learning researchers all too often find themselves constructing these diagrams from scratch by hand. NN-SVG is a tool for creating Neural Network (NN) architecture drawings parametrically rather than manually. It also provides the ability to export those drawings to Scalable Vector Graphics (SVG) files, suitable for inclusion in academic papers or web pages. The tool provides the ability to... -
2
ForceGen
Derives force constants from Gaussian QM for Gromacs MD
...DOI: 10.1007/s00894-017-3530-6 Instruction video: https://youtu.be/fQVXv8Ge_tg This Java executable jar derives second order bond force constants for bond stretch and bond angle from quantum mechanical Gaussian calculations. The calculations are compatible with the Amber force field family or any force field derived from the second order tensor of the Hessian from molecular fragments. The output has been made compatible with the Gromacs topology format. Examples of use include the derivation of bond force constants and equilibrium values for: -bonded metals in protein active sites -modified amino acids -small molecules/drug molecules A zip of examples files can be found by following the "Browse All Files" link. ... -
3
NimTorch
PyTorch - Python + Nim
NimTorch is a deep learning library for the Nim programming language, providing bindings to PyTorch for efficient tensor computations and neural network functionalities. -
4
Tensor Comprehensions
A domain specific language to express machine learning workloads
Tensor Comprehensions (TC) is a fully functional C++ library that automatically synthesizes high-performance machine learning kernels using Halide, ISL, and NVRTC or LLVM. TC additionally provides basic integration with Caffe2 and PyTorch. We provide more details in our paper on arXiv. This library is designed to be highly portable, machine-learning-framework agnostic and only requires a simple tensor library with memory allocation, offloading, and synchronization capabilities. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
Tiramisu
Polyhedral compiler for expressing fast and portable data algorithms
...It provides a simple C++ API for expressing algorithms (Tiramisu expressions) and how these algorithms should be optimized by the compiler. Tiramisu can be used in areas such as linear and tensor algebra, deep learning, image processing, stencil computations and machine learning. The Tiramisu compiler is based on the polyhedral model thus it can express a large set of loop optimizations and data layout transformations. Currently, it targets (1) multicore X86 CPUs, (2) Nvidia GPUs, (3) Xilinx FPGAs (Vivado HLS) and (4) distributed machines (using MPI). ... -
6
DeepLearn
Implementation of research papers on Deep Learning+ NLP+ CV in Python
Welcome to DeepLearn. This repository contains an implementation of the following research papers on NLP, CV, ML, and deep learning. The required dependencies are mentioned in requirement.txt. I will also use dl-text modules for preparing the datasets. If you haven't use it, please do have a quick look at it. CV, transfer learning, representation learning. -
7
PyTorch Book
PyTorch tutorials and fun projects including neural talk
This is the corresponding code for the book "The Deep Learning Framework PyTorch: Getting Started and Practical", but it can also be used as a standalone PyTorch Getting Started Guide and Tutorial. The current version of the code is based on pytorch 1.0.1, if you want to use an older version please git checkout v0.4or git checkout v0.3. Legacy code has better python2/python3 compatibility, CPU/GPU compatibility test. The new version of the code has not been fully tested, it has been tested... -
8
NNVM
Open deep learning compiler stack for cpu, gpu
...Infrastructure to automatically generates and optimize models on more backend with better performance. Compilation and minimal runtimes commonly unlock ML workloads on existing hardware. Automatically generate and optimize tensor operators on more backends. Need support for block sparsity, quantization (1,2,4,8 bit integers, posit), random forests/classical ML, memory planning, MISRA-C compatibility, Python prototyping or all of the above? NNVM flexible design enables all of these things and more. -
9
Caffe2
Caffe2 is a lightweight, modular, and scalable deep learning framework
Caffe2 is a lightweight, modular, and scalable deep learning framework. Building on the original Caffe, Caffe2 is designed with expression, speed, and modularity in mind. Caffe2 is a deep learning framework that provides an easy and straightforward way for you to experiment with deep learning and leverage community contributions of new models and algorithms. You can bring your creations to scale using the power of GPUs in the cloud or to the masses on mobile with Caffe2’s cross-platform... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
mctc4bmi
Matrix and Tensor Completion for Background Model Initialization
MCTC4BMI (Multimodal Compressed Sensing and Tensor Decomposition for Brain-Machine Interfaces) is a MATLAB toolbox designed to process and analyze EEG data. It applies compressed sensing and tensor decomposition techniques to improve brain-machine interface (BMI) performance. -
11
PrettyTensor
Pretty Tensor: Fluent Networks in TensorFlow
Pretty Tensor is a high-level API built on top of TensorFlow that simplifies the process of creating and managing deep learning models. It wraps TensorFlow tensors in a chainable object syntax, allowing developers to build multi-layer neural networks with concise and readable code. Pretty Tensor preserves full compatibility with TensorFlow’s core functionality while providing syntactic sugar for defining complex architectures such as convolutional and recurrent networks. ... -
12
Laxor is a C++ template library for componentwise tensor algebra, which uses the "Einstein" index notation in expressions and produces efficient binary code.
-
13
FaRe
Mathematica package for tensor reduction of Feynman integrals.
Version 1.2 is now available! This version is compatible with FeynCalc 9.0 FaRe is a Mathematica package for tensor reduction of Feynman integrals. The integral can be any-rank and any-order. Dimensional reduction is used and the final output is regrouped according to tensor structures. FaRe requires FeynCalc to work. Please refer to http://arxiv.org/abs/1507.03527 for a detailed manual. If you use FaRe in a scientific publication or talk, please give proper academic credit by citing http://inspirehep.net/record/1382623 For any information please write to: m.re-fiorentin AT soton.ac.uk -
14
WavePacket
Dynamics of quantum systems, controlled by external fields
...The Matlab/Octave version is mature and has been used in production for decades. The C++/Python version has been superseded by https://github.com/ulflor/wavepacket. Using tensor train techniques, the additional WaveTrain package aims at beating the curse of dimensionalit -
15
TTV
Tensor total variation for low-dose CT perfusion
We have developed a robust and efficient framework to accurately estimate the perfusion parameters at low radiation dosage. Specifically, we present a tensor total-variation (TTV) technique which fuses the spatial correlation of the vascular structure and the temporal continuation of the blood signal flow. An efficient algorithm is proposed to find the solution with fast convergence and reduced computational complexity. -
16
Uni10
C++ library for tensor network algorithms
Uni10 is an open-source C++ library designed for the development of tensor network algorithms. Programming tensor network algorithms is tedious and prone to errors. The task of keeping track of tensor indices while performing contraction of a complicated tensor network can be daunting. It is desirable to have a platform that provides bookkeeping capability and optimization. -
17
MasQu
Finite-differencing on the sphere
MasQU is a code for calculating derivatives on grids with regular or irregular pixel distributions, using finite differences. Particularly, it is constructed to perform tensor-mode separation on the HEALPix spherical grid, but can be generalized. -
18
Multilinear Subspace Learning
MSL: Dimensionality Reduction of Tensor Data via Subspace Learning
...With more connections revealed and analogies drawn between multilinear algorithms and their linear counterparts, MSL has become an exciting area to explore for applications involving large-scale multidimensional (tensorial) data as well as a challenging problem for machine learning researchers to tackle. MSL-based dimensionality reduction employs either tensor-to-tensor projection (TTP) or tensor-to-vector projection (TVP). TTP finds a direct mapping from high-dimensional tensors to low-dimensional tensors of the same (or lower) order. TVP finds a direct mapping from high-dimensional tensors to low-dimensional vectors. -
19
TCE
The Tensor Contraction Engine
A domain-specific compiler that facilitates the generation of high-performance parallel programs for a class of scientific computations encountered in chemistry and physics. -
20
MEPCM Package
This is a package for multi-element probabilistic collocation method.
The Multi-Element Probabilistic Collocation Method Package (MEPCMP) is a C++ package which can generate high dimensional, multi-element collocation points based on arbitrary probability density function for the application of Multi-Element Probabilistic Collocation Method (MEPCM). This package can generate high-dimensional stochastic collocation points based on tensor product rule, non-nested sparse grids method or anchored-ANOVA method. It can also be used for the multi-element probabilistic polynomial chaos method. -
21
zmcomplex library is a C++ library for multi-precision complex-number matrix calculations. It provides several functionalities including singular value decomposition, tensor product calculation, and tracing-out operation.
-
22
C/CUDA C library for working with tensors in Tensor Train format.
-
23
The Tensor Voting Framework is a powerful technique for perceptual grouping, manifold learning, etc. It has proved to be a useful tool in the Computer Vision community. OpenTVF is an open source implementation of TVF.
-
24
Linear algebra C++ library built upon a tensor class template that can be used to represent tensors of ranks 0 - scalaras, 1 - vectors, 2 - matrices, 3 - tensors of rank 3, etc. It also includes an interface to BLAS and LAPACK subroutines.
-
25
Grok-2.5
Large-scale xAI model for local inference with SGLang, Grok-2.5
Grok-2.5 is a large-scale AI model developed and released by xAI in 2024, made available through Hugging Face for research and experimentation. The model is distributed as raw weights that require specialized infrastructure to run, rather than being hosted by inference providers. To use it, users must download over 500 GB of files and set them up locally with the SGLang inference engine. Grok-2.5 supports advanced inference with multi-GPU configurations, requiring at least 8 GPUs with more...
