900 Open source projects that are alternatives of or similar to Mtensor

NumPy & SciPy for GPU

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

Owl's OCaml Interface to Eigen3 C++ Library

Fast zero-overhead bindings between NumPy and Eigen

NumPy aware dynamic Python compiler using LLVM

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

A Python wrapper of NVIDIA Video Loader (NVVL) with CuPy for fast video loading with Python

Deep.Net machine learning framework for F#

Deep Learning framework with NVIDIA & AMD support

Automatic parallelization of Python/NumPy, C, and C++ codes on Linux and MacOSX

Bindings between Numpy and Eigen using Boost.Python

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

N-dimensional arrays in Scala 3. Think NumPy ndarray, but type-safe over shapes, array/axis labels & numeric data types

TensorLy: Tensor Learning in Python.

Image recognition and classification using Convolutional Neural Networks with TensorFlow

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A High Level Python Deep Reinforcement Learning library. Great for beginners, prototyping and quickly comparing algorithms

Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.

A flexible framework of neural networks for deep learning

Examples for the usage of "pybind11"

A c++ header library for matrix operation inspired Numpy Scipy, MATLAB only using Eigen.

Read and write Neuroglancer datasets programmatically.

Detail-Preserving Pooling in Deep Networks (CVPR 2018)

numba_scipy extends Numba to make it aware of SciPy

Extending JAX with custom C++ and CUDA code

Simple Smart Pipe: python productivity-tool for rapid data manipulation

Data science and Big Data with Python

NumPy ndarray ⇋ OpenCV Mat conversion, that just works.

Implementation of cv::Mat conversion to numpy.array for pybind11

Materiály k předmětu NI-PYT na FIT ČVUT

SUPRA: Software Defined Ultrasound Processing for Real-Time Applications - An Open Source 2D and 3D Pipeline from Beamforming to B-Mode

World's fastest and most advanced password recovery utility

Simple neural networks based only on Numpy

A tracker based on joint probabilistic data association filtering.

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade

This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.

Provides a systematic and extensible way to build, train, evaluate, and tune deep learning models using PyTorch.

Study E-Book(ComputerVision DeepLearning MachineLearning Math NLP Python ReinforcementLearning)

DaCe - Data Centric Parallel Programming

Numeric Erlang - vector and matrix operations with CUDA. Heavily inspired by Pteracuda - https://github.com/kevsmith/pteracuda

Ubuntu 18.04 How to install Nvidia driver + CUDA + CUDNN + build tensorflow for gpu step by step command line

Chamfer Distance in Pytorch with f-score

机器学习相关教程

Real-time dense visual SLAM system

Extension package for spatial propagation network in pytorch.

This is the official implementation of the AAAI 2021 accepted paper "Sketch Generation with Drawing Process Guided by Vector Flow and Grayscale"

Stock Market Analysis and Prediction is the project on technical analysis, visualization and prediction using data provided by Google Finance.

NumPy官方中文文档（完整版）

MatConvNet: CNNs for MATLAB

Minimal Deep Learning library is written in Python/Cython/C++ and Numpy/CUDA/cuDNN.

Fast N-dimensional aggregation functions with Numba

Example PyMC3 project for performing Bayesian data analysis using a probabilistic programming approach to machine learning.

Connected components on multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants.

Official source code for our paper "AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation" (CVPR 2020)

Fast CUDA Kernels for ResNet Inference.

Deep Learning library using GPU(CUDA/cuBLAS)

A fast and highly scalable GPU dynamic memory allocator

A Box detection algorithm for any image containing boxes.

Weighted Softmax Loss Layer for Caffe