Skip to content

Differences and usage of outputSegmentationMasks optiom when using  #5530

Open
@theguaz

Description

@theguaz

Have I written custom code (as opposed to using a stock example script provided in MediaPipe)

Yes

OS Platform and Distribution

Mac OS

Mobile device if the issue happens on mobile device

No response

Browser and version if the issue happens on browser

Chrome

Programming Language and version

javascript

MediaPipe version

0.10.14

Bazel version

No response

Solution

Pose

Android Studio, NDK, SDK versions (if issue is related to building in Android environment)

No response

Xcode & Tulsi version (if issue is related to building for iOS)

No response

Describe the actual behavior

Not being able to consistenly get to know how to use the outputSegmentationMasks option

Describe the expected behaviour

Getting an example on how to get the mask as a bitmap information

Standalone code/steps you may have used to try to get what you need

Followed the CodePen example, and it works nicely to get the landmarks, but when enabling the outputSegmentationMasks I cannot figure how to access the segmentation mask and draw it on the canvas where I'm already drawing the bones.

Also, the logged result of this, changes a lot when switching between GPU and CPU:
const mask = result.segmentationMasks[0];

Other info / Complete Logs

No response

Metadata

Metadata

Assignees

Labels

os:macOSIssues on MacOSplatform:javascriptMediaPipe Javascript issuestask:pose landmarkerIssues related to Pose Landmarker: Find people and body positionstype:bugBug in the Source Code of MediaPipe Solution

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions