IEEE 2941.2-2023
$30.33
IEEE Standard for Application Programming Interfaces (APIs) for Deep Learning (DL) Inference Engines (Approved Draft)
Published By | Publication Date | Number of Pages |
IEEE | 2023 |
New IEEE Standard – Active. A set of application programming interfaces (APIs) that is aimed at breaking down the barriers between different deep learning (DL) inference engines and applications is defined in this standard. The APIs are comprised of functional interfaces including parameter reading, model compilation optimization, operator registration, thread management, input/output data acquisition, inference instance creation, and inference execution.
PDF Catalog
PDF Pages | PDF Title |
---|---|
1 | IEEE Std 2941.2™-2023 Front cover |
2 | Title page |
4 | Important Notices and Disclaimers Concerning IEEE Standards Documents |
8 | Participants |
10 | Introduction |
11 | Contents |
12 | 1. Overview 1.1 Scope 1.2 Purpose 1.3 Word usage |
13 | 2. Normative references 3. Definitions, acronyms, and abbreviations 3.1 Definitions 3.2 Acronyms and abbreviations |
14 | 4. Framework for the API of the inference engine |
15 | 5. General principles 5.1 Classification of interfaces 5.2 Requirements for interface 5.3 Hierarchical difference 6. Model management interface 6.1 Overview of the interface 6.2 Network interfaces and parameters reading |
18 | 7. Device management interface 7.1 Interface of power management (optional interface) |
19 | 7.2 Interface of number of working threads (optional interface) 8. Input and output interface 8.1 Inference objects and corresponding interface |
20 | 8.2 Get the input data |
21 | 8.3 Get the output data 9. Inference interface 9.1 Create an inference instance 9.2 Execution |
22 | Annex A (informative) C++ reference for APIs of DL inference engine A.1 Network interface and parameter reading |
26 | A.2 Device management interface |
27 | A.3 Input and output interface |
30 | A.4 Inference interface |
31 | Back cover |