nielsr/coco-panoptic-val2017
Viewer • Updated • 5k • 299 • 1
How to use sshibinthomass/sam2-household-train-20260709-100604 with sam2:
# Use SAM2 with images
import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor
predictor = SAM2ImagePredictor.from_pretrained(sshibinthomass/sam2-household-train-20260709-100604)
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
predictor.set_image(<your_image>)
masks, _, _ = predictor.predict(<input_prompts>) # Use SAM2 with videos
import torch
from sam2.sam2_video_predictor import SAM2VideoPredictor
predictor = SAM2VideoPredictor.from_pretrained(sshibinthomass/sam2-household-train-20260709-100604)
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
state = predictor.init_state(<your_video>)
# add new prompts and instantly get the output on the same frame
frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>):
# propagate the prompts to get masklets throughout the video
for frame_idx, object_ids, masks in predictor.propagate_in_video(state):
...Fine-tuned facebook/sam2.1-hiera-small for household object masks with bbox prompts.
facebook/sam2.1-hiera-smallnielsr/coco-panoptic-val2017sam2-household-modal-trainsshibinthomass/sam2-household-train-20260709-100604Base model
facebook/sam2.1-hiera-small