修正对label decode时重复字符会消失的bug

4 years ago · a88ce7a5b6
parent ca9ea622a9
commit a88ce7a5b6
1 changed files with 2 additions and 1 deletions
--- a/ppocr/postprocess/rec_postprocess.py
+++ b/ppocr/postprocess/rec_postprocess.py
@ -70,6 +70,7 @@ class BaseRecLabelDecode(object):
                if text_index[batch_idx][idx] in ignored_tokens:
                    continue
                if is_remove_duplicate:
+                    # only for predict
                    if idx > 0 and text_index[batch_idx][idx - 1] == text_index[
                            batch_idx][idx]:
                        continue
@ -107,7 +108,7 @@ class CTCLabelDecode(BaseRecLabelDecode):
        text = self.decode(preds_idx, preds_prob)
        if label is None:
            return text
-        label = self.decode(label)
+        label = self.decode(label, is_remove_duplicate=False)
        return text, label

    def add_special_char(self, dict_character):