mirrors
/
mmocr
mirror of https://github.com/open-mmlab/mmocr.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[Checkpoints] Add ST-pretrained DB-series models and logs (#1635) 

* [Fix] Auto scale lr

* update
pull/1708/head
Tong Gao 2023-02-06 15:16:08 +08:00 committed by GitHub
parent c870046a4a
commit 2a2cab3c8c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 91 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
configs/textdet/_base_/pretrain_runtime.py 100644
View File

@ -0,0 +1,14 @@
_base_ = 'default_runtime.py'
default_hooks = dict(
logger=dict(type='LoggerHook', interval=1000),
checkpoint=dict(
type='CheckpointHook',
interval=10000,
by_epoch=False,
max_keep_ckpts=1),
)
# Evaluation
val_evaluator = None
test_evaluator = None

2
configs/textdet/_base_/schedules/schedule_sgd_100k.py
View File

@ -4,7 +4,7 @@ optim_wrapper = dict(
optimizer=dict(type='SGD', lr=0.007, momentum=0.9, weight_decay=0.0001))
train_cfg = dict(type='IterBasedTrainLoop', max_iters=100000)
test_cfg = dict(type='TestLoop')
test_cfg = None
val_cfg = None
# learning policy
param_scheduler = [

6
configs/textdet/dbnet/README.md
View File

@ -14,6 +14,12 @@ Recently, segmentation-based methods are quite popular in scene text detection,
## Results and models
### SynthText
| Method | Backbone | Training set | #iters | Download |
| :-----------------------------------------------------------------------: | :------: | :----------: | :-----: | :--------------------------------------------------------------------------------------------------: |
| [DBNet_r18](/configs/textdet/dbnet/dbnet_resnet18_fpnc_100k_synthtext.py) | ResNet18 | SynthText | 100,000 | [model](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_resnet18_fpnc_100k_synthtext/dbnet_resnet18_fpnc_100k_synthtext-2e9bf392.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnet/dbnet_resnet18_fpnc_100k_synthtext/20221214_150351.log) |
### ICDAR2015
| Method | Backbone | Pretrained Model | Training set | Test set | #epochs | Test size | Precision | Recall | Hmean | Download |

46
configs/textdet/dbnet/dbnet_resnet18_fpnc_100k_synthtext.py
View File

@ -1,15 +1,44 @@
_base_ = [
'_base_dbnet_resnet18_fpnc.py',
'../_base_/datasets/synthtext.py',
'../_base_/default_runtime.py',
'../_base_/pretrain_runtime.py',
'../_base_/schedules/schedule_sgd_100k.py',
]
file_client_args = dict(backend='disk')
train_pipeline = [
dict(
type='LoadImageFromFile',
file_client_args=file_client_args,
color_type='color_ignore_orientation'),
dict(
type='LoadOCRAnnotations',
with_polygon=True,
with_bbox=True,
with_label=True,
),
dict(type='FixInvalidPolygon'),
dict(
type='TorchVisionWrapper',
op='ColorJitter',
brightness=32.0 / 255,
saturation=0.5),
dict(
type='ImgAugWrapper',
args=[['Fliplr', 0.5],
dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
dict(type='RandomCrop', min_side_ratio=0.1),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(type='Pad', size=(640, 640)),
dict(
type='PackTextDetInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape'))
]
# dataset settings
synthtext_textdet_train = _base_.synthtext_textdet_train
synthtext_textdet_train.pipeline = _base_.train_pipeline
synthtext_textdet_test = _base_.synthtext_textdet_test
synthtext_textdet_test.pipeline = _base_.test_pipeline
synthtext_textdet_train.pipeline = train_pipeline
train_dataloader = dict(
batch_size=16,
@ -18,13 +47,4 @@ train_dataloader = dict(
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=synthtext_textdet_train)
val_dataloader = dict(
batch_size=1,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=synthtext_textdet_test)
test_dataloader = val_dataloader
auto_scale_lr = dict(base_batch_size=16)

8
configs/textdet/dbnetpp/README.md
View File

@ -14,12 +14,18 @@ Recently, segmentation-based scene text detection methods have drawn extensive a
## Results and models
### SynthText
| Method | BackBone | Training set | #iters | Download |
| :--------------------------------------------------------------------------------: | :------------: | :----------: | :-----: | :-----------------------------------------------------------------------------------: |
| [DBNetpp_r50dcn](/configs/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext.py) | ResNet50-dcnv2 | SynthText | 100,000 | [model](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext/dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext-00f0a80b.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext/20221215_013531.log) |
### ICDAR2015
| Method | BackBone | Pretrained Model | Training set | Test set | #epochs | Test size | Precision | Recall | Hmean | Download |
| :----------------------------: | :------------------------------: | :--------------------------------------: | :-------------: | :------------: | :-----: | :-------: | :-------: | :----: | :----: | :------------------------------: |
| [DBNetpp_r50](/configs/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015.py) | ResNet50 | - | ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.9079 | 0.8209 | 0.8622 | [model](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015/dbnetpp_resnet50_fpnc_1200e_icdar2015_20221025_185550-013730aa.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015/20221025_185550.log) |
| [DBNetpp_r50dcn](/configs/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015.py) | ResNet50 | [Synthtext](/configs/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext.py) ([model](https://download.openmmlab.com/mmocr/textdet/dbnetpp/tmp_1.0_pretrain/dbnetpp_r50dcnv2_fpnc_100k_iter_synthtext-20220502-352fec8a.pth)) | ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.9116 | 0.8291 | 0.8684 | [model](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015_20220829_230108-f289bd20.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015/20220829_230108.log) |
| [DBNetpp_r50dcn](/configs/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015.py) | ResNet50-dcnv2 | [Synthtext](/configs/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext.py) ([model](https://download.openmmlab.com/mmocr/textdet/dbnetpp/tmp_1.0_pretrain/dbnetpp_r50dcnv2_fpnc_100k_iter_synthtext-20220502-352fec8a.pth)) | ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.9116 | 0.8291 | 0.8684 | [model](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015_20220829_230108-f289bd20.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015/20220829_230108.log) |
| [DBNetpp_r50-oclip](/configs/textdet/dbnetpp/dbnetpp_resnet50-oclip_fpnc_1200e_icdar2015.py) | [ResNet50-oCLIP](https://download.openmmlab.com/mmocr/backbone/resnet50-oclip-7ba0c533.pth) | - | ICDAR2015 Train | ICDAR2015 Test | 1200 | 1024 | 0.9174 | 0.8609 | 0.8882 | [model](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50-oclip_fpnc_1200e_icdar2015/dbnetpp_resnet50-oclip_fpnc_1200e_icdar2015_20221101_124139-4ecb39ac.pth) \| [log](https://download.openmmlab.com/mmocr/textdet/dbnetpp/dbnetpp_resnet50-oclip_fpnc_1200e_icdar2015/20221101_124139.log) |
## Citation

50
configs/textdet/dbnetpp/dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext.py
View File

@ -1,34 +1,44 @@
_base_ = [
'_base_dbnetpp_resnet50-dcnv2_fpnc.py',
'../_base_/default_runtime.py',
'../_base_/pretrain_runtime.py',
'../_base_/datasets/synthtext.py',
'../_base_/schedules/schedule_sgd_100k.py',
]
# dataset settings
train_list = [_base_.synthtext_textdet_train]
test_list = [_base_.synthtext_textdet_test]
train_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadOCRAnnotations',
with_bbox=True,
with_polygon=True,
with_label=True,
),
dict(type='FixInvalidPolygon'),
dict(
type='TorchVisionWrapper',
op='ColorJitter',
brightness=32.0 / 255,
saturation=0.5),
dict(
type='ImgAugWrapper',
args=[['Fliplr', 0.5],
dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
dict(type='RandomCrop', min_side_ratio=0.1),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(type='Pad', size=(640, 640)),
dict(
type='PackTextDetInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape'))
]
synthtext_textdet_train = _base_.synthtext_textdet_train
synthtext_textdet_train.pipeline = train_pipeline
train_dataloader = dict(
batch_size=16,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type='ConcatDataset',
datasets=train_list,
pipeline=_base_.train_pipeline))
val_dataloader = dict(
batch_size=16,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='ConcatDataset',
datasets=test_list,
pipeline=_base_.test_pipeline))
test_dataloader = val_dataloader
dataset=synthtext_textdet_train)
auto_scale_lr = dict(base_batch_size=16)