Multiclass selfie segmentation about mediapipe-samples HOT 5 OPEN

Going to reopen this for tracking. Will be a bit before I'm back from leave and can look into it, but hopefully someone else from my team can check ti out.

from mediapipe-samples.

from mediapipe-samples.

Hey @m22cs058 - I'm not sure I understand the request. Multiclass selfie segmentation should already exist in the category_mask segmentation example. Here's a quick video from that sample: https://photos.app.goo.gl/ia24YF52t7ooHcak9

Edit: So I was just reading an issue for Android and I think I assumed this is for Android :P Do you mean for something like Python? If that's the case, I can add a feature request to my task backlog, but it may not be completed soon.

from mediapipe-samples.

Hi @PaulTR Tested on Android 11T (21081111RG) works well with CPU delegate but catch "Batch size mismatch" error when modify to GPU. I use this device and use mediapipe studio demo, when selecting Multi-class Selfie Segmenter 256 and GPU it seems to have the same error, I think the problem is the GPU model on this device but when testing other models like Selfie Segmenter, Hair Segmenter and Deeplab V3 with the GPU delegate still working as expected

Log Details:

 E  Image segmenter failed to load model with error: invalid argument: CalculatorGraph::Run() failed in Run: 
                                                                                                    Calculator::Open() for node "mediapipe_tasks_vision_image_segmenter_imagesegmentergraph__mediapipe_tasks_core_inferencesubgraph__inferencecalculator__mediapipe_tasks_vision_image_segmenter_imagesegmentergraph__mediapipe_tasks_core_inferencesubgraph__InferenceCalculator" failed: Batch size mismatch, expected 1 but got 8

from mediapipe-samples.

Hi @PaulTR, I'd like to know if there is any update on this?

from mediapipe-samples.