From 8aae8d3242496e743806532d5e34d28d736d7e44 Mon Sep 17 00:00:00 2001 From: Steffy-zxf Date: Fri, 28 Aug 2020 16:38:20 +0800 Subject: [PATCH] update notation --- paddlehub/datasets/chnsenticorp.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/paddlehub/datasets/chnsenticorp.py b/paddlehub/datasets/chnsenticorp.py index 355f96f0..4a0f177e 100644 --- a/paddlehub/datasets/chnsenticorp.py +++ b/paddlehub/datasets/chnsenticorp.py @@ -36,7 +36,8 @@ class ChnSentiCorp(TextClassificationDataset): tokenizer (:obj:`BertTokenizer` or :obj:`CustomTokenizer`): It tokenizes the text and encodes the data as model needed. max_seq_len (:obj:`int`, `optional`, defaults to :128): - If set to a number, will limit the total sequence returned so that it has a maximum length. + The maximum length (in number of tokens) for the inputs to the selected module, + such as enrie, bert and so on. mode (:obj:`str`, `optional`, defaults to `train`): It identifies the dataset mode (train, test or dev). -- GitLab