Segment Anything in High Quality
Paper • 2306.01567 • Published • 8
How to use ductai199x/sam_hq_vit_large with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("mask-generation", model="ductai199x/sam_hq_vit_large", trust_remote_code=True) # Load model directly
from transformers import AutoProcessor, AutoModelForMaskGeneration
processor = AutoProcessor.from_pretrained("ductai199x/sam_hq_vit_large", trust_remote_code=True)
model = AutoModelForMaskGeneration.from_pretrained("ductai199x/sam_hq_vit_large", trust_remote_code=True)Directly converted weights from https://github.com/SysCV/sam-hq/tree/main to huggingface format. This work does not belong to me. Please checkout the authors' github for more information and updates.
Segment Anything in High Quality
NeurIPS 2023
ETH Zurich & HKUST