checkpoint 15_05

src/datasets/gtauav_dataset.py

@@ -37,6 +37,10 @@ _EMPTY_CAPTION = ""
 # Regex to split P1/P2/P3 sections.
 _P_SPLIT = re.compile(r"\*\*P[123][^*]*\*\*\s*:?\s*")
 
+# TODO: Transforms
+# sat_transforms = ...
+# drone_transforms = ...
+
 
 def _parse_caption_levels(output: str) -> tuple[str, str, str]:
     """Split VLM caption output into L1, L2, L3 levels.