Run custom pose detection model in tflite?

I’m new to using tflite, and am currently using an external tflite plugin for Flutter that seemingly runs on top of the native counterpart. I noticed the runModelOnImage method is only for classification models, is there anyway I can run a custom pose detection model? I know I can use runPoseNetOnImage, but for my project, I’m using movenet (from tensorflow). Do I have no choice but to use the PoseNet method?

Some users are tracking this in:

You could also check if this is working (not tested):

1 Like

Thank you! I’ll check it out and let you know if it works
edit: The owner of the repository didn’t push anything past the initial commit, I guess I’ll use posenet for now

Hi, iam also trying to use moveNet model with flutter but i didnot know how?
and there is a problem with tflite plugin

The plugin tflite uses a deprecated version of the Android embedding.
To avoid unexpected runtime failures, or future build failures, try to see if this plugin supports the Android V2 embedding. Otherwise, consider removing it since a future release of Flutter will remove these deprecated APIs.
If you are plugin author, take a look at the docs for migrating the plugin to the V2 embedding: Supporting the new Android plugins APIs | Flutter.

so did you managed to get rid of this problem?

Have you tried;