AoE

Documentation | Publishing Records | Roadmap | English

1. Introduction

AoE (AI on Edge) is an open source terminal-side AI integrated runtime environment (IRE) . Help developers easily deploy deep learning algorithms from different frameworks to terminals for efficient execution.

2. Use documents & examples & resources

• Android User Guide
• iOS User Guide
• Android Demo
• iOS Demo
• Official model:
  • SeesawNet_pytorch face comparison model, https://arxiv.org/abs/1908.09124

3. Adaptation information

AoE version	Reasoning framework	Relying on information	Reasoning framework version
1.1.4 (2020/03/17)	TensorFlow Lite	[Android] com.didi.aoe.runtime-tensorflow-lite:1.1.4 [ iOS ] pod 'AoERuntime/TensorFlowLite','~> 1.1.3',	2.1.0
	PyTorch	[Android] com.didi.aoe.runtime-pytorch:1.1.4	1.4.0
	MNN	[Android] com.didi.aoe.runtime-mnn:1.1.4 [ iOS ] pod 'AoERuntime/MNN','~> 1.1.3',	0.2.1.7
	NCNN	[Android] com.didi.aoe.runtime-ncnn:1.1.4 [ iOS ] pod 'AoERuntime/NCNN','~> 1.1.3',	20200106
	Tengine	[Android] com.didi.aoe.runtime-tengine:1.1.4	1.12.0

More version adaptation information

4. Q&A

• Add WeChat to the group: Puhui Travel Product Technology (Note AoE )

5. Project members

Core Members

kuloud, dingc, coleman.zou, yangke1120, cvtower

6. Friendly links

• Dokit, a fully functional client (iOS, Android) R&D assistant, you deserve it :)

• The public account of Puhui Travel Product Technology, welcome to follow.