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
12.41k
stars
1.14k
forks
source link
sam2 gave the complement of the target object #446
Hi! I am feeding bounding box to SAM2ImagePredictor, but for this specific image, it gives the exact complement of the target object (human). This frame was taken from a video, and all the images before this frame works fine. I was wondering if anyone has any insights into why this might be happening? Thank!
for reference, this is a similar frame which works fine
Hi! I am feeding bounding box to
SAM2ImagePredictor, but for this specific image, it gives the exact complement of the target object (human). This frame was taken from a video, and all the images before this frame works fine. I was wondering if anyone has any insights into why this might be happening? Thank!