How to perform Semi-supervised VOS inference on LVOS and YTVOS dataset?

facebookresearch / segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Apache License 2.0

10.72k stars 863 forks source link

How to perform Semi-supervised VOS inference on LVOS and YTVOS dataset? #226

Open Mhaiyang opened 1 month ago

Mhaiyang commented 1 month ago

Hello,

I want to perform Semi-supervised VOS inference on LVOS and YTVOS dataset. However, the provided vos_inference.py does not support the inference for videos that objects may appear only in the middle. How should I do or are there any codes I can refer?

Thanks for the help in advance!

RCLaplace commented 4 weeks ago

hey, have you read video_predictor_example.ipynb? Maybe the method there can help you.