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

[Feature] Improve dbnet r50 by fixing std (#578)

Browse Source
This commit is contained in:
Tong Gao 2021-11-11 19:10:12 +08:00 committed by GitHub
parent 51f2d9a4c3
commit a9fde9146f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 5 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/textdet/dbnet/README.md
View File

@ -20,4 +20,4 @@
| Method | Pretrained Model | Training set | Test set | #epochs | Test size | Recall | Precision | Hmean | Download |
| :--------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------: | :-------------: | :------------: | :-----: | :-------: | :----: | :-------: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [DBNet_r18](/configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py) | ImageNet | ICDAR2015 Train | ICDAR2015 Test | 1200 | 736 | 0.731 | 0.871 | 0.795 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r18_fpnc_sbn_1200e_icdar2015_20210329-ba3ab597.log.json) |
| [DBNet_r50dcn](/configs/textdet/dbnet/dbnet_r50dcnv2_fpnc_1200e_icdar2015.py) | [Synthtext](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_2e_synthtext_20210325-aa96e477.pth) | ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.796 | 0.866 | 0.830 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20210325-91cef9af.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20210325-91cef9af.log.json) |
| [DBNet_r50dcn](/configs/textdet/dbnet/dbnet_r50dcnv2_fpnc_1200e_icdar2015.py) | [Synthtext](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_2e_synthtext_20210325-aa96e477.pth) | ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.814 | 0.868 | 0.840 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20211025-9fe3b590.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20211025-9fe3b590.log.json) |

5
configs/textdet/dbnet/dbnet_r50dcnv2_fpnc_1200e_icdar2015.py
View File

@ -29,12 +29,9 @@ model = dict(
dataset_type = 'IcdarDataset'
data_root = 'data/icdar2015/'
# img_norm_cfg = dict(
# mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
# from official dbnet code
img_norm_cfg = dict(
mean=[122.67891434, 116.66876762, 104.00698793],
std=[255, 255, 255],
std=[58.395, 57.12, 57.375],
to_rgb=False)
# for visualizing img, pls uncomment it.
# img_norm_cfg = dict(mean=[0, 0, 0], std=[1, 1, 1], to_rgb=True)

4
configs/textdet/dbnet/metafile.yml
View File

@ -36,5 +36,5 @@ Models:
- Task: Text Detection
Dataset: ICDAR2015
Metrics:
hmean-iou: 0.830
Weights: https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20210325-91cef9af.pth
hmean-iou: 0.840
Weights: https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20211025-9fe3b590.pth

2
mmocr/utils/ocr.py
View File

@ -189,7 +189,7 @@ class MMOCR:
'dbnet/dbnet_r50dcnv2_fpnc_1200e_icdar2015.py',
'ckpt':
'dbnet/'
'dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20210325-91cef9af.pth'
'dbnet_r50dcnv2_fpnc_sbn_1200e_icdar2015_20211025-9fe3b590.pth'
},
'DRRG': {
'config':