Fast Positioning Visual Abnormalities after Inputting Images of Different Sizes

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.

Symptom:

After inputting images of different sizes, visual abnormalities occurred in the fast positioning module, leading to positioning errors.

As shown below, the left figure shows the normal visualized result, while the right one shows the abnormal visualized result.

vision fast positioning visual abnormal

Affected Software Versions:

Mech-DLK 2.4.2 and earlier versions.

Possible Cause:

The size of the input image during deep learning model package inference was different from the size during model training, which led to positioning errors.

Solution:

Use Mech-DLK 2.5.0 to export new fast positioning model package, and then conduct the model package inference.

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.