facebookresearch / facebookresearch/sam2

Missing method `clear_non_cond_mem_around_input`

Open
#571 3 comments 3 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
19.9k
Forks
2.5k
PR merge metrics
No merged PRs in 30d

Description

SAM2VideoPredictor is missing a method `self._clear_obj_non_cond_mem_around_input` that is referenced in `propagate_in_video`.
```
if self.clear_non_cond_mem_around_input:
# clear non-conditioning memory of the surrounding frames
self._clear_obj_non_cond_mem_around_input(
inference_state, frame_idx, obj_idx)
```
I ask because SAM2VideoPredictor's inference_state grows endlessly with video length, I am trying to reduce memory consumption on inference_state, and it seems like this was considered but maybe forgotten?

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.