nnabla

Deep learning framework

A deep learning framework that provides a flexible and expressive Python API for building and training neural networks on various platforms.

Neural Network Libraries

GitHub

3k stars
154 watching
334 forks
Language: Python
last commit: almost 2 years ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
nvlabs/tiny-cuda-nnA C++/CUDA framework for training and querying neural networks using GPUs3,791
nvlabs/instant-ngpA software toolkit for training and rendering neural graphics primitives16,115
torch/cunnA CUDA implementation of neural network modules and related GPU operations215
annetgpgpu/annetgpgpuA library that provides a GPU-accelerated implementation of artificial neural networks.107
oneapi-src/onednnA performance library of basic building blocks for deep learning applications3,649
nikolaypavlov/mlpneuralnetA fast neural network library for iOS and Mac OS X with vectorized operations and hardware acceleration.900
nvlabs/neuralangeloAn implementation of high-fidelity neural surface reconstruction from video frames using deep learning4,418
irfansharif/cerebrumAn implementation of Artificial Neural Networks in Ruby, allowing developers to experiment and train neural networks using the language.36
libfann/fannA C++ library for building and training artificial neural networks1,601
100/craniumA lightweight, portable C implementation of a feedforward artificial neural network library593
microsoft/cntkA unified deep learning toolkit that describes neural networks as a series of computational steps via a directed graph.17,534
doonny/pipecnnA tool for accelerating convolutional neural networks on Field-Programmable Gate Arrays (FPGAs) using OpenCL-based hardware design1,264
unagiootoro/ruby-dnnA Ruby-based deep learning library for building and training neural networks46
tangledpath/ruby-fannA Ruby library that provides an interface to the FANN neural network library.498
nixtla/neuralforecastAn open-source Python library providing a unified interface to various neural forecasting models, focusing on performance, usability, and robustness.3,181