data_iterators.py: Remove [0] to properly unpack indexed data

This fixes a bug introduced in d87fa5b. 

`[0]` refers specifically to `files = self._data[idx][0]`. By combining the indexes into a single link, the previous commit needed to remove the `[0]` index.

nnunetv2/inference/data_iterators.py

@@ -146,7 +146,7 @@ def __init__(self, list_of_lists: List[List[str]],
 
     def generate_train_batch(self):
         idx = self.get_indices()[0]
-        files, seg_prev_stage, ofile = self._data[idx][0]
+        files, seg_prev_stage, ofile = self._data[idx]
         # if we have a segmentation from the previous stage we have to process it together with the images so that we
         # can crop it appropriately (if needed). Otherwise it would just be resized to the shape of the data after
         # preprocessing and then there might be misalignments
@@ -190,7 +190,7 @@ def __init__(self, list_of_images: List[np.ndarray],
 
     def generate_train_batch(self):
         idx = self.get_indices()[0]
-        image, seg_prev_stage, props, ofname = self._data[idx][0]
+        image, seg_prev_stage, props, ofname = self._data[idx]
         # if we have a segmentation from the previous stage we have to process it together with the images so that we
         # can crop it appropriately (if needed). Otherwise it would just be resized to the shape of the data after
         # preprocessing and then there might be misalignments