[Enhancement] Add SynthText dataset config (#983)

* add synthtext config; add db pretrain config; move checkpoint config to schedule

* add db_r50 synthtext config

* fix r50 eval iter

* fix lint

* fix

configs/_base_/default_runtime.py

@@ -1,10 +1,8 @@
-checkpoint_config = dict(interval=1)
 # yapf:disable
 log_config = dict(
     interval=5,
     hooks=[
         dict(type='TextLoggerHook')
-
     ])
 # yapf:enable
 dist_params = dict(backend='nccl')

configs/_base_/det_datasets/synthtext.py

@@ -0,0 +1,18 @@
+dataset_type = 'TextDetDataset'
+data_root = 'data/synthtext'
+
+train = dict(
+    type=dataset_type,
+    ann_file=f'{data_root}/instances_training.lmdb',
+    loader=dict(
+        type='AnnFileLoader',
+        repeat=1,
+        file_format='lmdb',
+        parser=dict(
+            type='LineJsonParser',
+            keys=['file_name', 'height', 'width', 'annotations'])),
+    img_prefix=f'{data_root}/imgs',
+    pipeline=None)
+
+train_list = [train]
+test_list = [train]

configs/_base_/runtime_10e.py

@@ -1,19 +0,0 @@
-checkpoint_config = dict(interval=10)
-# yapf:disable
-log_config = dict(
-    interval=5,
-    hooks=[
-        dict(type='TextLoggerHook')
-        # dict(type='TensorboardLoggerHook')
-    ])
-# yapf:enable
-dist_params = dict(backend='nccl')
-log_level = 'INFO'
-load_from = None
-resume_from = None
-workflow = [('train', 1)]
-
-# disable opencv multithreading to avoid system being overloaded
-opencv_num_threads = 0
-# set multi-process start method as `fork` to speed up the training
-mp_start_method = 'fork'

configs/_base_/schedules/schedule_adadelta_18e.py

@@ -3,4 +3,6 @@ optimizer = dict(type='Adadelta', lr=0.5)
 optimizer_config = dict(grad_clip=dict(max_norm=0.5))
 # learning policy
 lr_config = dict(policy='step', step=[8, 14, 16])
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=18)
+checkpoint_config = dict(interval=1)

configs/_base_/schedules/schedule_adadelta_5e.py

@@ -3,4 +3,6 @@ optimizer = dict(type='Adadelta', lr=1.0)
 optimizer_config = dict(grad_clip=None)
 # learning policy
 lr_config = dict(policy='step', step=[])
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=5)
+checkpoint_config = dict(interval=1)

configs/_base_/schedules/schedule_adam_600e.py

@@ -3,4 +3,6 @@ optimizer = dict(type='Adam', lr=1e-3)
 optimizer_config = dict(grad_clip=None)
 # learning policy
 lr_config = dict(policy='poly', power=0.9)
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=600)
+checkpoint_config = dict(interval=100)

configs/_base_/schedules/schedule_adam_step_20e.py

@@ -1,5 +1,7 @@
+# optimizer
 optimizer = dict(type='Adam', lr=1e-4)
 optimizer_config = dict(grad_clip=None)
+# learning policy
 lr_config = dict(
     policy='step',
     step=[16, 18],
@@ -7,4 +9,6 @@ lr_config = dict(
     warmup_iters=1,
     warmup_ratio=0.001,
     warmup_by_epoch=True)
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=20)
+checkpoint_config = dict(interval=1)

configs/_base_/schedules/schedule_adam_step_5e.py

@@ -3,4 +3,6 @@ optimizer = dict(type='Adam', lr=1e-3)
 optimizer_config = dict(grad_clip=None)
 # learning policy
 lr_config = dict(policy='step', step=[3, 4])
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=5)
+checkpoint_config = dict(interval=1)

configs/_base_/schedules/schedule_adam_step_600e.py

@@ -3,4 +3,6 @@ optimizer = dict(type='Adam', lr=1e-4)
 optimizer_config = dict(grad_clip=None)
 # learning policy
 lr_config = dict(policy='step', step=[200, 400])
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=600)
+checkpoint_config = dict(interval=100)

configs/_base_/schedules/schedule_adam_step_6e.py

@@ -3,4 +3,6 @@ optimizer = dict(type='Adam', lr=1e-3)
 optimizer_config = dict(grad_clip=None)
 # learning policy
 lr_config = dict(policy='step', step=[3, 4])
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=6)
+checkpoint_config = dict(interval=1)

configs/_base_/schedules/schedule_sgd_100k_iters.py

@@ -0,0 +1,8 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.007, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-7, by_epoch=False)
+# running settings
+runner = dict(type='IterBasedRunner', max_iters=100000)
+checkpoint_config = dict(interval=10000)

configs/_base_/schedules/schedule_sgd_1200e.py

@@ -3,4 +3,6 @@ optimizer = dict(type='SGD', lr=0.007, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=None)
 # learning policy
 lr_config = dict(policy='poly', power=0.9, min_lr=1e-7, by_epoch=True)
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=1200)
+checkpoint_config = dict(interval=100)

configs/_base_/schedules/schedule_sgd_1500e.py

@@ -1,5 +1,8 @@
 # optimizer
 optimizer = dict(type='SGD', lr=1e-3, momentum=0.90, weight_decay=5e-4)
 optimizer_config = dict(grad_clip=None)
+# learning policy
 lr_config = dict(policy='poly', power=0.9, min_lr=1e-7, by_epoch=True)
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=1500)
+checkpoint_config = dict(interval=100)

configs/_base_/schedules/schedule_sgd_160e.py

@@ -8,4 +8,6 @@ lr_config = dict(
     warmup_iters=500,
     warmup_ratio=0.001,
     step=[80, 128])
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=160)
+checkpoint_config = dict(interval=10)

configs/_base_/schedules/schedule_sgd_600e.py

@@ -3,4 +3,6 @@ optimizer = dict(type='SGD', lr=1e-3, momentum=0.99, weight_decay=5e-4)
 optimizer_config = dict(grad_clip=None)
 # learning policy
 lr_config = dict(policy='step', step=[200, 400])
+# running settings
 runner = dict(type='EpochBasedRunner', max_epochs=600)
+checkpoint_config = dict(interval=100)

configs/textdet/dbnet/dbnet_r18_fpnc_100k_iters_synthtext.py

@@ -0,0 +1,33 @@
+_base_ = [
+    '../../_base_/default_runtime.py',
+    '../../_base_/schedules/schedule_sgd_100k_iters.py',
+    '../../_base_/det_models/dbnet_r18_fpnc.py',
+    '../../_base_/det_datasets/synthtext.py',
+    '../../_base_/det_pipelines/dbnet_pipeline.py'
+]
+
+train_list = {{_base_.train_list}}
+test_list = {{_base_.test_list}}
+
+train_pipeline_r18 = {{_base_.train_pipeline_r18}}
+test_pipeline_1333_736 = {{_base_.test_pipeline_1333_736}}
+
+data = dict(
+    samples_per_gpu=16,
+    workers_per_gpu=8,
+    val_dataloader=dict(samples_per_gpu=1),
+    test_dataloader=dict(samples_per_gpu=1),
+    train=dict(
+        type='UniformConcatDataset',
+        datasets=train_list,
+        pipeline=train_pipeline_r18),
+    val=dict(
+        type='UniformConcatDataset',
+        datasets=test_list,
+        pipeline=test_pipeline_1333_736),
+    test=dict(
+        type='UniformConcatDataset',
+        datasets=test_list,
+        pipeline=test_pipeline_1333_736))
+
+evaluation = dict(interval=999999, metric='hmean-iou')  # do not evaluate

configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../../_base_/runtime_10e.py',
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_sgd_1200e.py',
     '../../_base_/det_models/dbnet_r18_fpnc.py',
     '../../_base_/det_datasets/icdar2015.py',

configs/textdet/dbnet/dbnet_r50dcnv2_fpnc_100k_iters_synthtext.py

@@ -0,0 +1,33 @@
+_base_ = [
+    '../../_base_/default_runtime.py',
+    '../../_base_/schedules/schedule_sgd_100k_iters.py',
+    '../../_base_/det_models/dbnet_r50dcnv2_fpnc.py',
+    '../../_base_/det_datasets/synthtext.py',
+    '../../_base_/det_pipelines/dbnet_pipeline.py'
+]
+
+train_list = {{_base_.train_list}}
+test_list = {{_base_.test_list}}
+
+train_pipeline_r50dcnv2 = {{_base_.train_pipeline_r50dcnv2}}
+test_pipeline_4068_1024 = {{_base_.test_pipeline_4068_1024}}
+
+data = dict(
+    samples_per_gpu=16,
+    workers_per_gpu=8,
+    val_dataloader=dict(samples_per_gpu=1),
+    test_dataloader=dict(samples_per_gpu=1),
+    train=dict(
+        type='UniformConcatDataset',
+        datasets=train_list,
+        pipeline=train_pipeline_r50dcnv2),
+    val=dict(
+        type='UniformConcatDataset',
+        datasets=test_list,
+        pipeline=test_pipeline_4068_1024),
+    test=dict(
+        type='UniformConcatDataset',
+        datasets=test_list,
+        pipeline=test_pipeline_4068_1024))
+
+evaluation = dict(interval=999999, metric='hmean-iou')  # do not evaluate

configs/textdet/dbnet/dbnet_r50dcnv2_fpnc_1200e_icdar2015.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../../_base_/runtime_10e.py',
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_sgd_1200e.py',
     '../../_base_/det_models/dbnet_r50dcnv2_fpnc.py',
     '../../_base_/det_datasets/icdar2015.py',

configs/textdet/drrg/drrg_r50_fpn_unet_1200e_ctw1500.py

@@ -1,6 +1,6 @@
 _base_ = [
-    '../../_base_/schedules/schedule_sgd_1200e.py',
     '../../_base_/default_runtime.py',
+    '../../_base_/schedules/schedule_sgd_1200e.py',
     '../../_base_/det_models/drrg_r50_fpn_unet.py',
     '../../_base_/det_datasets/ctw1500.py',
     '../../_base_/det_pipelines/drrg_pipeline.py'

configs/textdet/fcenet/fcenet_r50_fpn_1500e_icdar2015.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../../_base_/runtime_10e.py',
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_sgd_1500e.py',
     '../../_base_/det_models/fcenet_r50_fpn.py',
     '../../_base_/det_datasets/icdar2015.py',

configs/textdet/fcenet/fcenet_r50dcnv2_fpn_1500e_ctw1500.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../../_base_/runtime_10e.py',
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_sgd_1500e.py',
     '../../_base_/det_models/fcenet_r50dcnv2_fpn.py',
     '../../_base_/det_datasets/ctw1500.py',

configs/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_ctw1500.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../../_base_/runtime_10e.py',
+    '../../_base_/default_runtime.py',
     '../../_base_/det_models/ocr_mask_rcnn_r50_fpn_ohem_poly.py',
     '../../_base_/schedules/schedule_sgd_160e.py',
     '../../_base_/det_datasets/ctw1500.py',

configs/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_icdar2015.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../../_base_/runtime_10e.py',
+    '../../_base_/default_runtime.py',
     '../../_base_/det_models/ocr_mask_rcnn_r50_fpn_ohem.py',
     '../../_base_/schedules/schedule_sgd_160e.py',
     '../../_base_/det_datasets/icdar2015.py',

configs/textdet/maskrcnn/mask_rcnn_r50_fpn_160e_icdar2017.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../../_base_/runtime_10e.py',
+    '../../_base_/default_runtime.py',
     '../../_base_/det_models/ocr_mask_rcnn_r50_fpn_ohem.py',
     '../../_base_/schedules/schedule_sgd_160e.py',
     '../../_base_/det_datasets/icdar2017.py',

configs/textdet/panet/panet_r18_fpem_ffm_600e_ctw1500.py

@@ -1,6 +1,6 @@
 _base_ = [
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_adam_600e.py',
-    '../../_base_/runtime_10e.py',
     '../../_base_/det_models/panet_r18_fpem_ffm.py',
     '../../_base_/det_datasets/ctw1500.py',
     '../../_base_/det_pipelines/panet_pipeline.py'

configs/textdet/panet/panet_r18_fpem_ffm_600e_icdar2015.py

@@ -1,6 +1,6 @@
 _base_ = [
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_adam_600e.py',
-    '../../_base_/runtime_10e.py',
     '../../_base_/det_models/panet_r18_fpem_ffm.py',
     '../../_base_/det_datasets/icdar2015.py',
     '../../_base_/det_pipelines/panet_pipeline.py'

configs/textdet/panet/panet_r50_fpem_ffm_600e_icdar2017.py

@@ -1,6 +1,6 @@
 _base_ = [
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_adam_600e.py',
-    '../../_base_/runtime_10e.py',
     '../../_base_/det_models/panet_r50_fpem_ffm.py',
     '../../_base_/det_datasets/icdar2017.py',
     '../../_base_/det_pipelines/panet_pipeline.py'

configs/textdet/psenet/psenet_r50_fpnf_600e_icdar2015.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../../_base_/runtime_10e.py',
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_adam_step_600e.py',
     '../../_base_/det_models/psenet_r50_fpnf.py',
     '../../_base_/det_datasets/icdar2015.py',

configs/textdet/psenet/psenet_r50_fpnf_600e_icdar2017.py

@@ -1,6 +1,6 @@
 _base_ = [
+    '../../_base_/default_runtime.py',
     '../../_base_/schedules/schedule_sgd_600e.py',
-    '../../_base_/runtime_10e.py',
     '../../_base_/det_models/psenet_r50_fpnf.py',
     '../../_base_/det_datasets/icdar2017.py',
     '../../_base_/det_pipelines/psenet_pipeline.py'

configs/textdet/textsnake/textsnake_r50_fpn_unet_1200e_ctw1500.py

@@ -1,6 +1,6 @@
 _base_ = [
-    '../../_base_/schedules/schedule_sgd_1200e.py',
     '../../_base_/default_runtime.py',
+    '../../_base_/schedules/schedule_sgd_1200e.py',
     '../../_base_/det_models/textsnake_r50_fpn_unet.py',
     '../../_base_/det_datasets/ctw1500.py',
     '../../_base_/det_pipelines/textsnake_pipeline.py'