717 Open source projects that are alternatives of or similar to Returnn

Neural networks library for machine learning on PHP

Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.

Sequence analyzing using Recurrent Neural Networks (RNN) based on Keras

THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is coupled with the Kaldi decoder.

RNN-based generative models for speech.

Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C.

A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text

HDLTex: Hierarchical Deep Learning for Text Classification

💻 Make machines learn so that you don't have to struggle to program them; The ultimate list

AIOpen是一个按人工智能三要素（数据、算法、算力）进行AI开源项目分类的汇集项目，项目致力于跟踪目前人工智能（AI）的深度学习（DL）开源项目，并尽可能地罗列目前的开源项目，同时加入了一些曾经研究过的代码。通过这些开源项目，使初次接触AI的人们对人工智能（深度学习）有更清晰和更全面的了解。

RNN benchmarks of pytorch, tensorflow and theano

This is a STORN (Stochastical Recurrent Neural Network) implementation for keras!

Setting up a Jupyterhub Dockercontainer to spawn Jupyter Notebooks with GPU support (containing Tensorflow, Pytorch and Keras)

Vulkan compute for people

Computer-generated poetry

Tensorflow implementation of Synthetic Gradient for RNN (LSTM)

TensorFlow implementation of "Tracking the World State with Recurrent Entity Networks".

🧠 A tool that makes AI easier.

The On-Ramp to Deep Learning

Dockerfiles for OpenCV compiled with CUDA, opencv_contrib modules and Python 3 bindings

Machine learning models for time series analysis

Lightning fast & tiny C++/CUDA neural network framework

[内测中]前向式Python环境快捷封装工具，快速将Python打包为EXE并添加CUDA、NoAVX等支持。

RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.

An Open Source, Self-Hosted Platform For Applied Deep Learning Development

Open Source Photometric classification https://supernnova.readthedocs.io

Out-of-GPU-Memory Graph Processing with Minimal Data Transfer

Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier

Code base for solving Markov Decision Processes and Reinforcement Learning problems using Recurrent Convolutional Neural Networks.

Simple utilities to enable code reuse and portability between CUDA C/C++ and standard C/C++.

Statistics on GPUs

Climate Machine: an Earth System Model that automatically learns from data

7z辅助破解工具 Fast 7zip crack assistant tool which support GPU/CPU, written in Python.

An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.

FlexGripPlus: an open-source GPU model for reliability evaluation and micro architectural simulation

🥕 Evolutionary Neural Networks in JavaScript

A domain-specific language and compiler for image processing

Simple and comprehensive tutorials in TensorFlow

Sample code for a 'Quaternions revisited' article from GPU Pro 5

PopSift is an implementation of the SIFT algorithm in CUDA.

A curated list of awesome Distributed Deep Learning resources.

Keras package for deep residual networks

an implementation of parallel linear BVH (LBVH) on GPU

Reference github repository for the paper "Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data". We propose a procedure to generate realistic DP data synthetically. Our synthesis approach mimics the optical image formation found on DP sensors and can be applied to virtual scenes rendered with standard computer software. Lev…

Lightweight C++11 library for building deep recurrent neural networks

Deep Neural Network for Sentiment Analysis on Twitter

📃 **Unofficial** PyTorch Implementation of DA-RNN (arXiv:1704.02971)

AI动力(AI Power) GPU云平台使用指南

A framework for quantum computing with hardware acceleration.

Script to remotely check GPU servers for free GPUs

Boost hardware utilization for ML training workloads via Inter-model Horizontal Fusion

An efficient C++17 GPU numerical computing library with Python-like syntax

This is a list of useful libraries and resources for CUDA development.

gprMax is open source software that simulates electromagnetic wave propagation using the Finite-Difference Time-Domain (FDTD) method for numerical modelling of Ground Penetrating Radar (GPR)

High-Performance Multiple-Backend Renderer Based on LuisaCompute

A Silent (Hidden) Monero (XMR) Miner Builder

PyTorch implementation for Seeing without Looking: Contextual Rescoring of Object Detections for AP Mazimization

A high-performance distributed deep learning system targeting large-scale and automated distributed training.

GPU accelerated multigrid library for Python