configs/textrecog/nrtr/nrtr_modality-transform_6e_st_mj.py

_base_ = [
    '../_base_/datasets/mjsynth.py',
    '../_base_/datasets/synthtext.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_modality-transform.py',
]

# optimizer settings
train_cfg = dict(max_epochs=6)
# learning policy
param_scheduler = [
    dict(type='MultiStepLR', milestones=[3, 4], end=6),
]

# dataset settings
train_list = [_base_.mjsynth_textrecog_train, _base_.synthtext_textrecog_train]
test_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
]

train_dataset = dict(
    type='ConcatDataset', datasets=train_list, pipeline=_base_.train_pipeline)
test_dataset = dict(
    type='ConcatDataset', datasets=test_list, pipeline=_base_.test_pipeline)

train_dataloader = dict(
    batch_size=384,
    num_workers=24,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=train_dataset)

test_dataloader = dict(
    batch_size=1,
    num_workers=4,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=test_dataset)

val_dataloader = test_dataloader

val_evaluator = dict(
    dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15'])
test_evaluator = val_evaluator

auto_scale_lr = dict(base_batch_size=384)