Faz2: code/meshai_train/dataset.py

code/meshai_train/dataset.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import json
+import zipfile
 from pathlib import Path
 
 import numpy as np
@@ -97,16 +98,12 @@ class PreprocessedMeshDataset(Dataset):
                 )
             )
         except Exception as exc:
-            # 404 / EntryNotFound / RemoteEntryNotFound — manifestte olup HF'de olmayan UID
             msg = str(exc).lower()
             if "404" in msg or "entrynotfound" in msg.replace(" ", "") or "not found" in msg:
                 raise FileNotFoundError(f"HF eksik: {rel}") from exc
             raise
 
     def _load_npz(self, uid: str):
-        """Incomplete HF cache can yield BadZipFile; delete + force redownload once."""
-        import zipfile
-
         path = self._resolve_file(uid, "geometry_latent.npz")
         try:
             return np.load(path)
@@ -116,7 +113,7 @@ class PreprocessedMeshDataset(Dataset):
             except OSError:
                 pass
             if not self.token:
-                raise FileNotFoundError(f"Bozuk latent (token yok, yeniden indirilemez): {uid}") from exc
+                raise FileNotFoundError(f"Bozuk latent: {uid}") from exc
             from huggingface_hub import hf_hub_download
 
             rel = f"{_uid_hf_prefix(uid)}/geometry_latent.npz"
@@ -163,7 +160,6 @@ class PreprocessedMeshDataset(Dataset):
                     continue
         if not views:
             views.append(np.zeros((3, self.render_size, self.render_size), dtype=np.float32))
-        # Collate batch_size>1 icin view sayisini sabitle (eksik render pad).
         while len(views) < self.max_views:
             views.append(views[-1].copy())
         views = views[: self.max_views]
@@ -178,9 +174,6 @@ class PreprocessedMeshDataset(Dataset):
         }
 
     def __getitem__(self, idx: int) -> dict:
-        # Manifest bazen HF'de olmayan / bozuk UID icerir; sonraki ornege kay.
-        import zipfile
-
         if not hasattr(self, "_missing_uids"):
             self._missing_uids = set()
         n = len(self.objects)
@@ -202,7 +195,6 @@ class PreprocessedMeshDataset(Dataset):
 
 
 def collate_preprocessed(batch: list[dict]) -> dict:
-    # Savunmaci pad: eski checkpoint/yamali dataset karisik shape getirebilir.
     max_v = max(int(b["views"].shape[0]) for b in batch)
     views_list = []
     for b in batch: