shigangli Goto Github PK

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

longformer

Longformer: The Long-Document Transformer

lstm-human-activity-recognition

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

magicube

Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.

matterport3dsimulator

AI Research Platform for Reinforcement Learning from Real Panoramic Images.

megatron-lm

Ongoing research training transformer language models at scale, including: BERT & GPT-2

mesh

Mesh TensorFlow: Model Parallelism Made Easier

metal

Love template metaprogramming

mindspore

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

mingpt

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

mixture-of-experts

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models

mobilenet

MobileNet build with Tensorflow

mtensor

A C++ Cuda Tensor Lazy Computing Library

multi-gpu-programming-models

Examples demonstrating available options to program multiple GPUs in a single node or a cluster

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

ngraph.path

Path finding in a graph

nmt

TensorFlow Neural Machine Translation Tutorial

nn-from-scratch

Implementing a Neural Network from Scratch

nnpack

Acceleration package for neural networks on multi-core CPUs

nystromformer

ok-topk

Ok-Topk is a scheme for distributed training with sparse gradients. Ok-Topk integrates a novel sparse allreduce algorithm (less than 6k communication volume which is asymptotically optimal) with the decentralized parallel Stochastic Gradient Descent (SGD) optimizer, and its convergence is proved theoretically and empirically.

onednn

oneAPI Deep Neural Network Library (oneDNN)

onnx-simplifier

Simplify your onnx model

openai-gym-policy-gradient

Reinforcement Learning using Policy Gradient to solve OpenAI Gym games

opencl-caffe

OpenCL version of caffe developed by AMD research lab

openmp-tutorial

Exercises and Solutions for "Programming Your GPU with OpenMP: A Hands-On Introduction"

p4app-switchml

Switch ML Application

paper-template

A template for writing CS papers with latex -- includes CI, todonotes, ...

pipedream

pysc2

StarCraft II Learning Environment