KellenSunderland

KenLMJava

KenLM is a popular Language Modeling Toolkit that is written in performant C++. KenLM for Java aims to make KenLM easily accessible to the Java ecosystem.

dockcross

Cross compiling toolchains in Docker images

fastserv

A lightweight implementation of TensorRT and ONNX model serving.

MXNetArmCI

MXNet Arm CI

sockeye

Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet

incubator-mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

mxnet-notebooks

Notebooks for MXNet

apbsint

Approximate Bayesian Inference Toolkit (Python, C++)

AsyncMNIST

CoreNLP

Stanford CoreNLP: A Java suite of core NLP tools.

displacy

:boom: displaCy.js: An open-source NLP visualiser for the modern web

hunter

:package: CMake driven cross-platform package manager for C/C++. Linux, Mac, Windows, iOS, Android, Raspberry Pi.

incubator-joshua

Mirror of Apache Joshua (Incubating)

kenlm

KenLM: Faster and Smaller Language Model Queries

mshadow

Matrix Shadow:Lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for (Deep) Machine Learning

mxnet-the-straight-dope

An interactive book on deep learning, in concept and in MXNet

mxnet_to_onnx

MxNet to ONNX Exporter

nd-direct-s3

NDArrays directly read from S3.

netscope

Neural network visualizer

onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

serving

A flexible, high-performance serving system for machine learning models