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

Google AI 2018 BERT pytorch implementation

Run TensorFlow models in C++ without installation and without Bazel

Go package for computer vision using OpenCV 4 and beyond.

Some basic programming tutorials

Runtime type system for IO decoding/encoding

A C++-based, cross platform ray tracing library

[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.

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

A fast Clojure Tensor & Deep Learning library

High-performance Bayesian Data Analysis on the GPU in Clojure

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

PageTransformer for flutter

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

📘 A comprehensive handbook on how to create transformers for TypeScript with code examples

Integral Human Pose Regression

ArrayFire: a general purpose GPU library.

Minimalist NMT for educational purposes

A python package to run contextualized topic modeling. CTMs combine BERT with topic models to get coherent topics. Also supports multilingual tasks. Cross-lingual Zero-shot model published at EACL 2021.

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

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

A single-header C++ library for simplifying the use of CUDA Runtime Compilation (NVRTC).

Sample codes for my CUDA programming book

(Mirror of GitLab) GPGPU Framework for Rust

Snips NLU rust implementation

Sequence to sequence learning using TensorFlow.

AI 尬舞机

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

A collection of GICP-based fast point cloud registration algorithms

Chinese version of GPT2 training code, using BERT tokenizer.

Laravel 5 JSON API Transformer Package

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

Unsupervised Learning of Video Representations using LSTMs

BERT for Multitask Learning

End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)

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

CUDA Voxelizer to convert polygon meshes into annotated voxel grids

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

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

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.

A scene text recognition toolbox based on PyTorch

CUDA programming in Julia.

The FFmpeg build script provides an easy way to build a static FFmpeg on OSX and Linux with non-free codecs included.

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

Blind WAF identification tool

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

Image Captioning using InceptionV3 and beam search

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

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

Implementation of Transformer Model in Tensorflow

viewpager with parallax pages, together with vertical sliding (or click) and activity transition

A Curious Cumulation of CUDA Cuisine

PyTorch CTC Decoder bindings

PyTorch implementation of Deformable Convolution

Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.

a reimplementation of LiteFlowNet in PyTorch that matches the official Caffe version

Easy Attributed String Creator

Distribution-Aware Coordinate Representation for Human Pose Estimation