fix nlp return token_type_ids (#7289)

90e2f2d6 · littletomatodonkey · GitHub · a40f64a7 · 90e2f2d6
Unverified Commit 90e2f2d6 authored Aug 22, 2022 by littletomatodonkey Committed by GitHub Aug 22, 2022
Hide whitespace changes
Inline Side-by-side

Showing with 4 additions and 1 deletion

ppocr/data/imaug/label_ops.py ppocr/data/imaug/label_ops.py +4 -1

No files found.
--- a/ppocr/data/imaug/label_ops.py
+++ b/ppocr/data/imaug/label_ops.py
@@ -918,7 +918,10 @@ class VQATokenLabelEncode(object):

            text = info["text"]
            encode_res = self.tokenizer.encode(
-                text, pad_to_max_seq_len=False, return_attention_mask=True)
+                text,
+                pad_to_max_seq_len=False,
+                return_attention_mask=True,
+                return_token_type_ids=True)

            if not self.add_special_ids:
                # TODO: use tok.all_special_ids to remove