未验证 提交 71af7f94 编写于 作者: J Jiawei Wang 提交者: GitHub

Update ocr_reader.py

上级 c83cba90
......@@ -191,7 +191,7 @@ class OCRReader(object):
for rno in range(len(rec_idx_lod) - 1):
beg = rec_idx_lod[rno]
end = rec_idx_lod[rno + 1]
rec_idx_tmp = [rec_idx_batch[i][0] for i in range(beg, end, 1)]
rec_idx_tmp = rec_idx_batch[beg:end, 0]
preds_text = self.char_ops.decode(rec_idx_tmp)
if with_score:
beg = predict_lod[rno]
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册