From 866e1f91f8dacca86429f695dd1f6d1ee812a8a1 Mon Sep 17 00:00:00 2001 From: Eric Liang Date: Fri, 27 Jan 2023 11:26:54 -0800 Subject: [PATCH] fix iter batch Signed-off-by: Eric Liang --- python/ray/data/dataset.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/python/ray/data/dataset.py b/python/ray/data/dataset.py index f2f9db25753d..6a5b8a2c9211 100644 --- a/python/ray/data/dataset.py +++ b/python/ray/data/dataset.py @@ -2786,7 +2786,7 @@ def iter_batches( self, *, prefetch_blocks: int = 0, - batch_size: Optional[int] = 256, + batch_size: Optional[int] = None, batch_format: str = "default", drop_last: bool = False, local_shuffle_buffer_size: Optional[int] = None, @@ -2807,7 +2807,7 @@ def iter_batches( batch_size: The number of rows in each batch, or None to use entire blocks as batches (blocks may contain different number of rows). The final batch may include fewer than ``batch_size`` rows if - ``drop_last`` is ``False``. Defaults to 256. + ``drop_last`` is ``False``. Defaults to None. batch_format: The format in which to return each batch. Specify "default" to use the default block format (promoting tables to Pandas and tensors to NumPy), "pandas" to select