updates

scripts/prepare_polyvore.py

@@ -84,6 +84,9 @@ def load_outfits_json(root: str, split: str) -> List[Dict[str, Any]]:
         os.path.join(root, f"{split}_no_dup.json"),
         os.path.join(root, "splits", f"{split}.json"),
         os.path.join(root, "splits", f"{split}_no_dup.json"),
+        # Official Polyvore often ships splits under nondisjoint/ or disjoint/
+        os.path.join(root, "nondisjoint", f"{split}.json"),
+        os.path.join(root, "disjoint", f"{split}.json"),
     ]
     for p in candidates:
         if os.path.exists(p):
@@ -114,6 +117,16 @@ def try_load_any_outfits(root: str) -> List[Dict[str, Any]]:
             data = _normalize_outfits(raw)
             if data:
                 return data
+    # Last resort: check nondisjoint/disjoint JSONs directly
+    for sub in ("nondisjoint", "disjoint"):
+        for name in ("train.json", "valid.json", "test.json"):
+            p = os.path.join(root, sub, name)
+            if os.path.exists(p):
+                with open(p, "r") as f:
+                    raw = json.load(f)
+                data = _normalize_outfits(raw)
+                if data:
+                    return data
     return []
 
 

utils/data_fetch.py

@@ -44,9 +44,18 @@ def ensure_dataset_ready() -> Optional[str]:
         # Only fetch what's needed to run and prepare splits
         allow = [
             "images.zip",
+            # root-level (some mirrors place jsons here)
             "train.json",
             "valid.json",
             "test.json",
+            # official splits often live here
+            "nondisjoint/train.json",
+            "nondisjoint/valid.json",
+            "nondisjoint/test.json",
+            "disjoint/train.json",
+            "disjoint/valid.json",
+            "disjoint/test.json",
+            # light metadata
             "polyvore_item_metadata.json",
             "polyvore_outfit_titles.json",
             "categories.csv",
@@ -61,9 +70,16 @@ def ensure_dataset_ready() -> Optional[str]:
             "**/*.tar.gz",
             "**/*.7z",
         ]
-        need_meta = not all(os.path.exists(os.path.join(root, f)) for f in [
-            "train.json", "valid.json", "test.json", "categories.csv"
-        ])
+        need_meta = not (
+            all(os.path.exists(os.path.join(root, f)) for f in [
+                "categories.csv",
+            ]) and (
+                # any location providing official splits is acceptable
+                all(os.path.exists(os.path.join(root, f)) for f in ["train.json", "valid.json", "test.json"]) or
+                all(os.path.exists(os.path.join(root, "nondisjoint", f)) for f in ["train.json", "valid.json", "test.json"]) or
+                all(os.path.exists(os.path.join(root, "disjoint", f)) for f in ["train.json", "valid.json", "test.json"]) 
+            )
+        )
         if need_meta or not os.path.isdir(os.path.join(root, "images")):
             snapshot_download(
                 "Stylique/Polyvore",