We use essential cookies for the website to function, as well as analytics cookies for analyzing and creating statistics of the website performance. To agree to the use of analytics cookies, click "Accept All". You can manage your preferences at any time by clicking "Cookie Settings" on the footer. More Information.

Only Essential Cookies
Accept All
GuidesCANNApp DevelopmentModel Preparation(Optional) AIPPService Introduction

Service Introduction

AI Pre-Process (AIPP) is a module that pre-processes input data for the purpose of AI inference. Model inference in CANN generally depends on standardized input data formats. However, in common model inference scenarios, the input data can be an image in various formats. With AIPP, images in different formats can be converted to the standard format for NPUs. For a trained model, you do not need to retrain it if its input data formats are not supported by the inference and computing platform. Instead, you can complete the adaptation simply by setting AIPP parameters, or calling AIPP APIs in your app. As AIPP is dedicated to hardware, it helps improve the inference performance.

Search in Guides
Enter a keyword.