945 Open source projects that are alternatives of or similar to Lightseq

Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL

Using LSTM or Transformer to solve Image Captioning in Pytorch

Explore the Capabilities of the TensorRT Platform

A library for high performance deep learning inference on NVIDIA GPUs.

TensorFlow examples in C, C++, Go and Python without bazel but with cmake and FindTensorFlow.cmake

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Running BERT without Padding

Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

Neutron: A pytorch based implementation of Transformer and its variants.

a reimplementation of PWC-Net in PyTorch that matches the official Caffe version

Fast parallel CTC.

A scalable inference server for models optimized with OpenVINO™

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.

Fuse multiple depth frames into a TSDF voxel volume.

Simple implementations of NLP models. Tutorials are written in Chinese on my website https://mofanpy.com

Julia support for native CUDA programming

GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN

C++ library for solving large sparse linear systems with algebraic multigrid method

A wrapper around tensor2tensor to flexibly train, interact, and generate data for neural chatbots.

Open3D: A Modern Library for 3D Data Processing

A Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"

cuDF - GPU DataFrame Library

A UNIVERSAL MUSIC TRANSLATION NETWORK - a method for translating music across musical instruments and styles.

All-in-one AI container for rapid prototyping

Google AI 2018 BERT pytorch implementation

Go package for computer vision using OpenCV 4 and beyond.

Runtime type system for IO decoding/encoding

H2Oai GPU Edition

Implementation of SYCL for CPUs, AMD GPUs, NVIDIA GPUs

Train a state-of-the-art yolov3 object detector from scratch!

🌀 Oxygen Engine 2.0. [Preview] Discord: https://discord.gg/P3aMf66

Integral Human Pose Regression

Minimalist NMT for educational purposes

High-performance Vision library in Python. Scale your research, not boilerplate.

(Mirror of GitLab) GPGPU Framework for Rust

Sequence to sequence learning using TensorFlow.

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

Chinese version of GPT2 training code, using BERT tokenizer.

Super fast implementation of ICP in CUDA for compute capable devices 3.5 or higher

BERT for Multitask Learning

Official Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

Implementation of State-of-the-art Text Classification Models in Pytorch

ILGPU JIT Compiler for high-performance .Net GPU programs

CUDA programming in Julia.

Python code to fuse multiple RGB-D images into a TSDF voxel volume.

Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.

A REST API for Caffe using Docker and Go

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020

Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).

Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai

NVIDIA-accelerated zero latency video compression library for interactive remoting applications

VUDA is a header-only library based on Vulkan that provides a CUDA Runtime API interface for writing GPU-accelerated applications.

PyTorch CTC Decoder bindings

PyTorch implementation of Deformable Convolution