from datasets import load_dataset from pathlib import Path from PIL import Image REPO = "jamiewjm/sam-tp" # change to your dataset repo id ds_imgs = load_dataset( "imagefolder", data_dir=".", data_files={"image": f"hf://datasets/{REPO}/images/**"}, split="train", ) ds_msks = load_dataset( "imagefolder", data_dir=".", data_files={"mask": f"hf://datasets/{REPO}/annotations/**"}, split="train", ) mask_index = {Path(r["image"]["path"]).name: r["image"]["path"] for r in ds_msks} row = ds_imgs[0] img_path = Path(row["image"]["path"]) msk_path = Path(mask_index[img_path.name]) print("Image:", img_path) print("Mask: ", msk_path) Image.open(img_path).show() Image.open(msk_path).show()