Mech-DLK SDK

You are viewing an old version of the documentation. You can switch to the documentation of the latest version by clicking the top-right corner of the page.

Welcome to Mech-DLK SDK User Manual. Let’s get started!

Overview

Mech-DLK SDK is a secondary development software kit specifically designed to be used with Mech-DLK. Its main purpose is to help developers easily do deep learning inference in their software systems. With Mech-DLK SDK, developers can rapidly deploy deep learning models and flexibly integrate deep learning functionality into their own applications without reliance on Mech-Vision. You can use the provided APIs to build applications in C and C# languages.

You can apply Mech-DLK SDK for the inference based on models exported from Mech-DLK (version 2.4.2 or above).

Release notes

Mech-DLK SDK 2.0.1

New features

Configuration adjustment

  • Changed the ways of adding environment variables for running samples provided in Mech-DLK SDK. For more details, see the Add environment variables parts in the sample usage guide.

Bug fix

  • Fixed the result parsing problem that occurred during inference using the defect segmentation model.

Contents

This manual consists of the following chapters. Click to view the details according to your needs:

No. Chapter Content

1

Installation guide

View the system requirements and obtain Mech-DLK SDK and the third-party libraries and resources it depend upon.

2

Get started

Learn to use Mech-DLK SDK for inference with a defect segmentation model.

3

Sample usage guide

Learn about the types of samples and prerequisites to run these samples and build and run these samples.

4

API reference

View APIs and structures in C and C# languages.

5

FAQs

View the frequently asked questions.

We Value Your Privacy

We use cookies to provide you with the best possible experience on our website. By continuing to use the site, you acknowledge that you agree to the use of cookies. If you decline, a single cookie will be used to ensure you're not tracked or remembered when you visit this website.