KSAI Lite is a deep learning inference framework of kingsoft, based on tensorflow lite

Overview

KSAI Lite

English | 简体中文

Documentation Status Release License

KSAI Lite是一个轻量级、灵活性强、高性能且易于扩展的深度学习推理框架,底层基于tensorflow lite,定位支持包括移动端、嵌入式以及服务器端在内的多硬件平台。

当前KSAI Lite已经应用在金山office内部业务中,并逐步支持金山企业的生产任务和众多外部用户。

快速入门

使用KSAI Lite,只需几个简单的步骤,就可以把模型部署到多种终端设备中,运行高性能的推理任务,使用流程如下所示:

一. 准备模型

KSAI Lite框架直接支持模型结构为tflite模型。 如果您手中的模型是由诸如Caffe、MXNet、PyTorch等框架产出的,那么您可以使用工具将模型转换为tflite格式。

二. 模型优化

KSAI Lite框架基于底层tensorflow lite的优化方法,拥有优秀的加速、优化策略及实现,包含量化、子图融合、Kernel优选等优化手段。优化后的模型更轻量级,耗费资源更少,并且执行速度也更快。

三. 下载或编译

KSAI Lite提供了多平台的官方Release预测库下载,我们优先推荐您直接下载 KSAI Lite预编译库,包括了Linux-X64, Linux-ARM, Linux-MIPS64以及Windows-X64索引库Windows-X64动态链接库。 您也可以根据目标平台选择对应的源码编译方法。KSAI Lite 提供了源码编译脚本,位于 tools/目录下,只需要按照docs/目录下的准备环境说明文档environment setup.md搭建好环境然后切到tools/目录调用编译脚本两个步骤即可一键编译得到目标平台的KSAI Lite预测库。

四. 预测示例

KSAI Lite提供了C++ API,并且提供了相应API的完整使用示例: 目录为tensorflow/lite/examples/reg_test/reg_test.cc 您可以参考示例快速了解使用方法,并集成到您自己的项目中去,也可以参考KSAI-Toolkits该项目。

主要特性

  • 多硬件支持
    • KSAI Lite架构已经验证和完整支持从 Mobile 到 Server 多种硬件平台,包括 intel X86、ARM、华为 Kunpeng 920、龙芯Loongson-3A R3、兆芯C4600、Phytium FT1500a等,且正在不断增加更多新硬件支持。
  • 轻量级部署
    • KSAI Lite在设计上对图优化模块和执行引擎实现了良好的解耦拆分,移动端可以直接部署执行阶段,无任何第三方依赖。
  • 高性能
    • 极致的 ARM及X86 CPU 性能优化:针对不同微架构特点实现kernel的定制,最大发挥计算性能,在主流模型上展现出领先的速度优势。
  • 多模型多算子
    • KSAI Lite和tensorflow训练框架的OP对齐,提供广泛的模型支持能力。
    • 目前已对视觉类模型做到了较为充分的支持,覆盖分类、检测和识别,包含了特色的OCR模型的支持,并在不断丰富中。
  • 强大的图分析和优化能力
    • 不同于常规的移动端预测引擎基于 Python 脚本工具转化模型, Lite 架构上有完整基于 C++ 开发的 IR 及相应 Pass 集合,以支持操作融合,计算剪枝,存储优化,量化计算等多类计算图优化。

持续集成

System X86 Linux ARM Linux MIPS64 Linux windows
CPU(32bit) Build Status - - Build Status
CPU(64bit) Build Status - - Build Status
高通骁龙845 - Build Status - -
华为kunpeng920 - Build Status - -
龙芯Loongson-3A - - Build Status -
兆芯C4600 - Build Status - -
Phytium FT1500a - Build Status - -

交流与反馈

版权和许可证

KSAI-Lite由Apache-2.0 license提供

Blender add-on: Add to Cameras menu: View → Camera, View → Add Camera, Camera → View, Previous Camera, Next Camera

Blender add-on: Camera additions In 3D view, it adds these actions to the View|Cameras menu: View → Camera : set the current camera to the 3D view Vie

German Bauer 11 Feb 08, 2022
Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".

VL-BERT By Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai. This repository is an official implementation of the paper VL-BERT:

Weijie Su 698 Dec 18, 2022
Prototype python implementation of the ome-ngff table spec

Prototype python implementation of the ome-ngff table spec

Kevin Yamauchi 8 Nov 20, 2022
This code implements constituency parse tree aggregation

README This code implements constituency parse tree aggregation. Folder details code: This folder contains the code that implements constituency parse

Adithya Kulkarni 0 Oct 11, 2021
Python periodic table module

elemenpy Hello! elements.py is a small Python periodic table module that is used for calling certain information about an element. Installation Instal

Eric Cheng 2 Dec 27, 2021
A curated list of awesome resources related to Semantic Search🔎 and Semantic Similarity tasks.

A curated list of awesome resources related to Semantic Search🔎 and Semantic Similarity tasks.

224 Jan 04, 2023
GAN JAX - A toy project to generate images from GANs with JAX

GAN JAX - A toy project to generate images from GANs with JAX This project aims to bring the power of JAX, a Python framework developped by Google and

Valentin Goldité 14 Nov 29, 2022
Deeper DCGAN with AE stabilization

AEGeAN Deeper DCGAN with AE stabilization Parallel training of generative adversarial network as an autoencoder with dedicated losses for each stage.

Tyler Kvochick 36 Feb 17, 2022
A fast python implementation of Ray Tracing in One Weekend using python and Taichi

ray-tracing-one-weekend-taichi A fast python implementation of Ray Tracing in One Weekend using python and Taichi. Taichi is a simple "Domain specific

157 Dec 26, 2022
Orthogonal Over-Parameterized Training

The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural network is of great impo

Weiyang Liu 11 Apr 18, 2022
Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

This repository contains code for the following two papers: VisualBERT: A Simple and Performant Baseline for Vision and Language (arxiv) with a short

Natural Language Processing @UCLA 463 Dec 09, 2022
Spatio-Temporal Entropy Model (STEM) for end-to-end leaned video compression.

Spatio-Temporal Entropy Model A Pytorch Reproduction of Spatio-Temporal Entropy Model (STEM) for end-to-end leaned video compression. More details can

16 Nov 28, 2022
Scalable and Elastic Deep Reinforcement Learning Using PyTorch. Please star. 🔥

ElegantRL “小雅”: Scalable and Elastic Deep Reinforcement Learning ElegantRL is developed for researchers and practitioners with the following advantage

AI4Finance Foundation 2.5k Jan 05, 2023
This repository contains the code for our fast polygonal building extraction from overhead images pipeline.

Polygonal Building Segmentation by Frame Field Learning We add a frame field output to an image segmentation neural network to improve segmentation qu

Nicolas Girard 186 Jan 04, 2023
Quantify the difference between two arbitrary curves in space

similaritymeasures Quantify the difference between two arbitrary curves Curves in this case are: discretized by inidviudal data points ordered from a

Charles Jekel 175 Jan 08, 2023
PyTorch implementation of federated learning framework based on the acceleration of global momentum

Federated Learning with Acceleration of Global Momentum PyTorch implementation of federated learning framework based on the acceleration of global mom

0 Dec 23, 2021
Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

NeuralTextures This is repository with inference code for paper "StylePeople: A Generative Model of Fullbody Human Avatars" (CVPR21). This code is for

Visual Understanding Lab @ Samsung AI Center Moscow 18 Oct 06, 2022
Final report with code for KAIST Course KSE 801.

Orthogonal collocation is a method for the numerical solution of partial differential equations

Chuanbo HUA 4 Apr 06, 2022
3DV 2021: Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry

SynergyNet 3DV 2021: Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry Cho-Ying Wu, Qiangeng Xu, Ulrich Neumann, CGIT Lab at Unive

Cho-Ying Wu 239 Jan 06, 2023
Pytorch0.4.1 codes for InsightFace

InsightFace_Pytorch Pytorch0.4.1 codes for InsightFace 1. Intro This repo is a reimplementation of Arcface(paper), or Insightface(github) For models,

1.5k Jan 01, 2023