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

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

Runtime type system for IO decoding/encoding

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

Grakn Core: The Knowledge Graph

An easy to use PyTorch to TensorRT converter

TensorFlow template application for deep learning

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Acceleration package for neural networks on multi-core CPUs

DELTA is a deep learning based natural language and speech processing platform.

Pytorch-Named-Entity-Recognition-with-BERT

High-efficiency floating-point neural network inference operators for mobile, server, and Web

TensorFlow models accelerated with NVIDIA TensorRT

Embedded and mobile deep learning research resources

Shape and dimension inference (Keras-like) for PyTorch layers and neural networks

Lua Language Server coded by Lua

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

A REST API for Caffe using Docker and Go

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

LightSeq: A High Performance Inference Library for Sequence Processing and Generation

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

A scalable inference server for models optimized with OpenVINO™

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