mirrors/mmocr
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmocr.git synced 2025-06-03 21:54:47 +08:00
Code Issues Projects Releases Wiki Activity

increase the number of candidates for DBNet to 3000 (#98)

Browse Source 
This solves the issue when dealing with documents with a large number of words per-page.
This commit is contained in:
seekingdeep 2021-04-20 05:18:56 +03:00 committed by GitHub
parent b058fdcb4e
commit 6c1c34fb91
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mmocr/models/textdet/postprocess/wrapper.py
View File

@ -186,7 +186,7 @@ def db_decode(preds,
min_text_score=0.3,
min_text_width=5,
unclip_ratio=1.5,
max_candidates=1000):
max_candidates=3000):
"""Decoding predictions of DbNet to instances. This is partially adapted
from https://github.com/MhLiao/DB.