-
Notifications
You must be signed in to change notification settings - Fork 751
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[MODEL] Add Union14M trained models (#1960)
* [Update] Add ABINet * [Update] Add NRTR * [Update] Add SATRN * [Update] Add configs
- Loading branch information
1 parent
1dcd6fa
commit e50c5fd
Showing
10 changed files
with
601 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,118 @@ | ||
| _base_ = [ | ||
| '../_base_/datasets/union14m_train.py', | ||
| '../_base_/datasets/union14m_benchmark.py', | ||
| '../_base_/datasets/cute80.py', | ||
| '../_base_/datasets/iiit5k.py', | ||
| '../_base_/datasets/svt.py', | ||
| '../_base_/datasets/svtp.py', | ||
| '../_base_/datasets/icdar2013.py', | ||
| '../_base_/datasets/icdar2015.py', | ||
| '../_base_/default_runtime.py', | ||
| '../_base_/schedules/schedule_adamw_cos_10e.py', | ||
| '_base_abinet.py', | ||
| ] | ||
|
|
||
| load_from = 'https://download.openmmlab.com/mmocr/textrecog/abinet/abinet_pretrain-45deac15.pth' # noqa | ||
|
|
||
| _base_.pop('model') | ||
| dictionary = dict( | ||
| type='Dictionary', | ||
| dict_file= # noqa | ||
| '{{ fileDirname }}/../../../dicts/english_digits_symbols_space.txt', | ||
| with_padding=True, | ||
| with_unknown=True, | ||
| same_start_end=True, | ||
| with_start=True, | ||
| with_end=True) | ||
|
|
||
| model = dict( | ||
| type='ABINet', | ||
| backbone=dict(type='ResNetABI'), | ||
| encoder=dict( | ||
| type='ABIEncoder', | ||
| n_layers=3, | ||
| n_head=8, | ||
| d_model=512, | ||
| d_inner=2048, | ||
| dropout=0.1, | ||
| max_len=8 * 32, | ||
| ), | ||
| decoder=dict( | ||
| type='ABIFuser', | ||
| vision_decoder=dict( | ||
| type='ABIVisionDecoder', | ||
| in_channels=512, | ||
| num_channels=64, | ||
| attn_height=8, | ||
| attn_width=32, | ||
| attn_mode='nearest', | ||
| init_cfg=dict(type='Xavier', layer='Conv2d')), | ||
| module_loss=dict(type='ABIModuleLoss'), | ||
| postprocessor=dict(type='AttentionPostprocessor'), | ||
| dictionary=dictionary, | ||
| max_seq_len=26, | ||
| ), | ||
| data_preprocessor=dict( | ||
| type='TextRecogDataPreprocessor', | ||
| mean=[123.675, 116.28, 103.53], | ||
| std=[58.395, 57.12, 57.375])) | ||
|
|
||
| # dataset settings | ||
| train_list = [ | ||
| _base_.union14m_challenging, _base_.union14m_hard, _base_.union14m_medium, | ||
| _base_.union14m_normal, _base_.union14m_easy | ||
| ] | ||
| val_list = [ | ||
| _base_.cute80_textrecog_test, _base_.iiit5k_textrecog_test, | ||
| _base_.svt_textrecog_test, _base_.svtp_textrecog_test, | ||
| _base_.icdar2013_textrecog_test, _base_.icdar2015_textrecog_test | ||
| ] | ||
| test_list = [ | ||
| _base_.union14m_benchmark_artistic, | ||
| _base_.union14m_benchmark_multi_oriented, | ||
| _base_.union14m_benchmark_contextless, | ||
| _base_.union14m_benchmark_curve, | ||
| _base_.union14m_benchmark_incomplete, | ||
| _base_.union14m_benchmark_incomplete_ori, | ||
| _base_.union14m_benchmark_multi_words, | ||
| _base_.union14m_benchmark_salient, | ||
| _base_.union14m_benchmark_general, | ||
| ] | ||
|
|
||
| train_dataset = dict( | ||
| type='ConcatDataset', datasets=train_list, pipeline=_base_.train_pipeline) | ||
| test_dataset = dict( | ||
| type='ConcatDataset', datasets=test_list, pipeline=_base_.test_pipeline) | ||
| val_dataset = dict( | ||
| type='ConcatDataset', datasets=val_list, pipeline=_base_.test_pipeline) | ||
|
|
||
| train_dataloader = dict( | ||
| batch_size=128, | ||
| num_workers=24, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=True), | ||
| dataset=train_dataset) | ||
|
|
||
| test_dataloader = dict( | ||
| batch_size=128, | ||
| num_workers=4, | ||
| persistent_workers=True, | ||
| drop_last=False, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=test_dataset) | ||
|
|
||
| val_dataloader = dict( | ||
| batch_size=128, | ||
| num_workers=4, | ||
| persistent_workers=True, | ||
| pin_memory=True, | ||
| drop_last=False, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=val_dataset) | ||
|
|
||
| val_evaluator = dict( | ||
| dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15']) | ||
| test_evaluator = dict(dataset_prefixes=[ | ||
| 'artistic', 'multi-oriented', 'contextless', 'curve', 'incomplete', | ||
| 'incomplete-ori', 'multi-words', 'salient', 'general' | ||
| ]) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,91 @@ | ||
| # training schedule for 1x | ||
| _base_ = [ | ||
| '_base_aster.py', | ||
| '../_base_/datasets/union14m_train.py', | ||
| '../_base_/datasets/union14m_benchmark.py', | ||
| '../_base_/datasets/cute80.py', | ||
| '../_base_/datasets/iiit5k.py', | ||
| '../_base_/datasets/svt.py', | ||
| '../_base_/datasets/svtp.py', | ||
| '../_base_/datasets/icdar2013.py', | ||
| '../_base_/datasets/icdar2015.py', | ||
| '../_base_/default_runtime.py', | ||
| '../_base_/schedules/schedule_adamw_cos_6e.py', | ||
| ] | ||
|
|
||
| dictionary = dict( | ||
| type='Dictionary', | ||
| dict_file= # noqa | ||
| '{{ fileDirname }}/../../../dicts/english_digits_symbols_space.txt', | ||
| with_padding=True, | ||
| with_unknown=True, | ||
| same_start_end=True, | ||
| with_start=True, | ||
| with_end=True) | ||
|
|
||
| # dataset settings | ||
| train_list = [ | ||
| _base_.union14m_challenging, _base_.union14m_hard, _base_.union14m_medium, | ||
| _base_.union14m_normal, _base_.union14m_easy | ||
| ] | ||
| val_list = [ | ||
| _base_.cute80_textrecog_test, _base_.iiit5k_textrecog_test, | ||
| _base_.svt_textrecog_test, _base_.svtp_textrecog_test, | ||
| _base_.icdar2013_textrecog_test, _base_.icdar2015_textrecog_test | ||
| ] | ||
| test_list = [ | ||
| _base_.union14m_benchmark_artistic, | ||
| _base_.union14m_benchmark_multi_oriented, | ||
| _base_.union14m_benchmark_contextless, | ||
| _base_.union14m_benchmark_curve, | ||
| _base_.union14m_benchmark_incomplete, | ||
| _base_.union14m_benchmark_incomplete_ori, | ||
| _base_.union14m_benchmark_multi_words, | ||
| _base_.union14m_benchmark_salient, | ||
| _base_.union14m_benchmark_general, | ||
| ] | ||
|
|
||
| default_hooks = dict(logger=dict(type='LoggerHook', interval=50)) | ||
|
|
||
| auto_scale_lr = dict(base_batch_size=512) | ||
|
|
||
| train_dataset = dict( | ||
| type='ConcatDataset', datasets=train_list, pipeline=_base_.train_pipeline) | ||
| test_dataset = dict( | ||
| type='ConcatDataset', datasets=test_list, pipeline=_base_.test_pipeline) | ||
| val_dataset = dict( | ||
| type='ConcatDataset', datasets=val_list, pipeline=_base_.test_pipeline) | ||
|
|
||
| train_dataloader = dict( | ||
| batch_size=512, | ||
| num_workers=12, | ||
| persistent_workers=True, | ||
| pin_memory=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=True), | ||
| dataset=train_dataset) | ||
|
|
||
| test_dataloader = dict( | ||
| batch_size=128, | ||
| num_workers=4, | ||
| persistent_workers=True, | ||
| pin_memory=True, | ||
| drop_last=False, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=test_dataset) | ||
|
|
||
| val_dataloader = dict( | ||
| batch_size=128, | ||
| num_workers=4, | ||
| persistent_workers=True, | ||
| pin_memory=True, | ||
| drop_last=False, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=val_dataset) | ||
|
|
||
| val_evaluator = dict( | ||
| dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15']) | ||
|
|
||
| test_evaluator = dict(dataset_prefixes=[ | ||
| 'artistic', 'multi-oriented', 'contextless', 'curve', 'incomplete', | ||
| 'incomplete-ori', 'multi-words', 'salient', 'general' | ||
| ]) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
114 changes: 114 additions & 0 deletions
114
configs/textrecog/nrtr/nrtr_resnet31-1by8-1by4_union14m.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,114 @@ | ||
| _base_ = [ | ||
| '../_base_/datasets/union14m_train.py', | ||
| '../_base_/datasets/union14m_benchmark.py', | ||
| '../_base_/datasets/cute80.py', | ||
| '../_base_/datasets/iiit5k.py', | ||
| '../_base_/datasets/svt.py', | ||
| '../_base_/datasets/svtp.py', | ||
| '../_base_/datasets/icdar2013.py', | ||
| '../_base_/datasets/icdar2015.py', | ||
| '../_base_/default_runtime.py', | ||
| '../_base_/schedules/schedule_adam_base.py', | ||
| '_base_nrtr_resnet31.py', | ||
| ] | ||
|
|
||
| # optimizer settings | ||
| train_cfg = dict(max_epochs=6) | ||
| # learning policy | ||
| param_scheduler = [ | ||
| dict(type='MultiStepLR', milestones=[3, 4], end=6), | ||
| ] | ||
|
|
||
| _base_.pop('model') | ||
| dictionary = dict( | ||
| type='Dictionary', | ||
| dict_file= # noqa | ||
| '{{ fileDirname }}/../../../dicts/english_digits_symbols_space.txt', | ||
| with_padding=True, | ||
| with_unknown=True, | ||
| same_start_end=True, | ||
| with_start=True, | ||
| with_end=True) | ||
|
|
||
| model = dict( | ||
| type='NRTR', | ||
| backbone=dict( | ||
| type='ResNet31OCR', | ||
| layers=[1, 2, 5, 3], | ||
| channels=[32, 64, 128, 256, 512, 512], | ||
| stage4_pool_cfg=dict(kernel_size=(2, 1), stride=(2, 1)), | ||
| last_stage_pool=False), | ||
| encoder=dict(type='NRTREncoder'), | ||
| decoder=dict( | ||
| type='NRTRDecoder', | ||
| module_loss=dict( | ||
| type='CEModuleLoss', ignore_first_char=True, flatten=True), | ||
| postprocessor=dict(type='AttentionPostprocessor'), | ||
| dictionary=dictionary, | ||
| max_seq_len=30, | ||
| ), | ||
| data_preprocessor=dict( | ||
| type='TextRecogDataPreprocessor', | ||
| mean=[123.675, 116.28, 103.53], | ||
| std=[58.395, 57.12, 57.375])) | ||
|
|
||
| # dataset settings | ||
| train_list = [ | ||
| _base_.union14m_challenging, _base_.union14m_hard, _base_.union14m_medium, | ||
| _base_.union14m_normal, _base_.union14m_easy | ||
| ] | ||
| val_list = [ | ||
| _base_.cute80_textrecog_test, _base_.iiit5k_textrecog_test, | ||
| _base_.svt_textrecog_test, _base_.svtp_textrecog_test, | ||
| _base_.icdar2013_textrecog_test, _base_.icdar2015_textrecog_test | ||
| ] | ||
| test_list = [ | ||
| _base_.union14m_benchmark_artistic, | ||
| _base_.union14m_benchmark_multi_oriented, | ||
| _base_.union14m_benchmark_contextless, | ||
| _base_.union14m_benchmark_curve, | ||
| _base_.union14m_benchmark_incomplete, | ||
| _base_.union14m_benchmark_incomplete_ori, | ||
| _base_.union14m_benchmark_multi_words, | ||
| _base_.union14m_benchmark_salient, | ||
| _base_.union14m_benchmark_general, | ||
| ] | ||
|
|
||
| train_dataset = dict( | ||
| type='ConcatDataset', datasets=train_list, pipeline=_base_.train_pipeline) | ||
| test_dataset = dict( | ||
| type='ConcatDataset', datasets=test_list, pipeline=_base_.test_pipeline) | ||
| val_dataset = dict( | ||
| type='ConcatDataset', datasets=val_list, pipeline=_base_.test_pipeline) | ||
|
|
||
| train_dataloader = dict( | ||
| batch_size=128, | ||
| num_workers=24, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=True), | ||
| dataset=train_dataset) | ||
|
|
||
| test_dataloader = dict( | ||
| batch_size=128, | ||
| num_workers=4, | ||
| persistent_workers=True, | ||
| drop_last=False, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=test_dataset) | ||
|
|
||
| val_dataloader = dict( | ||
| batch_size=128, | ||
| num_workers=4, | ||
| persistent_workers=True, | ||
| pin_memory=True, | ||
| drop_last=False, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=val_dataset) | ||
|
|
||
| val_evaluator = dict( | ||
| dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15']) | ||
|
|
||
| test_evaluator = dict(dataset_prefixes=[ | ||
| 'artistic', 'multi-oriented', 'contextless', 'curve', 'incomplete', | ||
| 'incomplete-ori', 'multi-words', 'salient', 'general' | ||
| ]) |
Oops, something went wrong.