Use CTD predictions for video output

Fixes a mismatch in `analyze_videos` where the DataFrame export step still used `predictions` instead of `ctd_predictions`. This ensures saved video analysis results use the corrected prediction set from the current processing path.
C-Achard · Oct 23, 2026 · Sep 8, 2026 · Sep 8, 2026 · Sep 8, 2026 · Sep 9, 2026
commit c57dd354c009c94e8a2186246dc4b0f2967fe73d
diff --git a/deeplabcut/pose_estimation_pytorch/apis/videos.py b/deeplabcut/pose_estimation_pytorch/apis/videos.py
@@ -666,7 +666,7 @@ def analyze_videos(
 
                     if predictions:
                         create_df_from_prediction(
-                            predictions=predictions,
+                            predictions=ctd_predictions,
                             multi_animal=multi_animal,
                             model_cfg=loader.model_cfg,
                             dlc_scorer=dlc_scorer,