The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Apache License 2.0
47.5k
stars
5.62k
forks
source link
Type of argument 'crop-overlap-ratio' should be changed from int to float #259
In script/amg.py
amg_settings.add_argument( "--crop-overlap-ratio", type=int, default=None, help="Larger numbers mean image crops will overlap more.", )
conflicts with SamAutomaticMaskGenerator in segment_anything/automatic_mask_generator.pyclass SamAutomaticMaskGenerator: def __init__( self, model: Sam, ..., crop_overlap_ratio: float = 512 / 1500, ...):