Spaces:
Running on Zero
Running on Zero
| """Evaluation sets outside the training data. | |
| screenspot ScreenSpot (bevaya/ScreenSpot, test, 1,272), shuffled with seed 0: clicks and element boxes | |
| coco17 COCO val2017 photos (RefCOCO is all train2014): objects prompted by category name, for | |
| categories with exactly one instance in the image, at least 1% of it, polygon masks only | |
| fashion Fashionpedia val: one garment per image, by name (a new domain; boxes only) | |
| Point COCO17_DIR at a folder with annotations/instances_val2017.json and val2017/ | |
| (recipes/fetch_coco17.sh). | |
| """ | |
| import json, os, random | |
| COCO17 = os.environ.get("COCO17_DIR", "/workspace/data/coco17") | |
| MIN_AREA = 0.01 | |
| GARMENTS = 27 # Fashionpedia classes 0-26 are whole garments and accessories; the rest are parts | |
| def screenspot(n=0): | |
| from datasets import load_dataset | |
| ds = load_dataset("bevaya/ScreenSpot", split="test").shuffle(seed=0) | |
| ds = ds.select(range(n)) if n else ds | |
| return [dict(image=r["image"], instruction=r["instruction"], box=list(r["bbox"]), norm=True, | |
| group=(r["data_source"], r["data_type"])) for r in ds] | |
| def coco17(n, seed=0): | |
| d = json.load(open(f"{COCO17}/annotations/instances_val2017.json")) | |
| cats = {c["id"]: c["name"] for c in d["categories"]} | |
| imgs = {i["id"]: i for i in d["images"]} | |
| by = {} | |
| for a in d["annotations"]: | |
| by.setdefault((a["image_id"], a["category_id"]), []).append(a) | |
| out = [] | |
| for (iid, cid), anns in sorted(by.items()): | |
| if len(anns) != 1: | |
| continue | |
| a, im = anns[0], imgs[iid] | |
| W, H = im["width"], im["height"] | |
| if a["iscrowd"] or not isinstance(a["segmentation"], list) or a["area"] < MIN_AREA * W * H: | |
| continue | |
| x, y, w, h = a["bbox"] | |
| out.append(dict(image=f"{COCO17}/val2017/{im['file_name']}", size=(W, H), sentence=cats[cid], | |
| instruction=cats[cid], polys=a["segmentation"], bbox=[x, y, x + w, y + h], | |
| box=[x / W, y / H, (x + w) / W, (y + h) / H], norm=True, ref_id=a["id"], source="coco17")) | |
| random.Random(seed).shuffle(out) | |
| return out[:n] if n else out | |
| def fashion(n, seed=0): | |
| from datasets import load_dataset | |
| ds = load_dataset("detection-datasets/fashionpedia", split="val") | |
| names = ds.features["objects"]["category"].feature.names | |
| idx = list(range(len(ds))) | |
| random.Random(seed).shuffle(idx) | |
| out = [] | |
| for i in idx: | |
| r = ds[i] | |
| W, H, o = r["width"], r["height"], r["objects"] | |
| counts = {} | |
| for c in o["category"]: | |
| counts[c] = counts.get(c, 0) + 1 | |
| for c, (x1, y1, x2, y2) in zip(o["category"], o["bbox"]): # x1, y1, x2, y2 in pixels | |
| if c < GARMENTS and counts[c] == 1 and (x2 - x1) * (y2 - y1) >= MIN_AREA * W * H: | |
| out.append(dict(image=r["image"], size=(W, H), instruction=f"the {names[c].split(',')[0]}", | |
| box=[x1 / W, y1 / H, x2 / W, y2 / H], norm=True, source="fashionpedia")) | |
| break # one object per image | |
| if n and len(out) >= n: | |
| break | |
| return out | |