thvl_textrecog_data_root = 'data/recog/synTH'
thvl_textrecog_train = dict(
    type='OCRDataset',
    data_root='data/recog/synTH',
    ann_file='textrecog_train.json',
    pipeline=None)
thvl_textrecog_test = dict(
    type='OCRDataset',
    data_root='data/recog/synTH',
    ann_file='textrecog_test.json',
    test_mode=True,
    pipeline=None)
default_scope = 'mmocr'
env_cfg = dict(
    cudnn_benchmark=True,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'))
randomness = dict(seed=None)
default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=100),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(type='CheckpointHook', interval=1),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    sync_buffer=dict(type='SyncBuffersHook'),
    visualization=dict(
        type='VisualizationHook',
        interval=1,
        enable=False,
        show=False,
        draw_gt=False,
        draw_pred=False))
log_level = 'INFO'
log_processor = dict(type='LogProcessor', window_size=10, by_epoch=True)
load_from = None
resume = False
val_evaluator = dict(
    type='MultiDatasetsEvaluator',
    metrics=[
        dict(
            type='WordMetric',
            mode=['exact', 'ignore_case', 'ignore_case_symbol']),
        dict(type='CharMetric')
    ],
    dataset_prefixes=None)
test_evaluator = dict(
    type='MultiDatasetsEvaluator',
    metrics=[
        dict(
            type='WordMetric',
            mode=['exact', 'ignore_case', 'ignore_case_symbol']),
        dict(type='CharMetric')
    ],
    dataset_prefixes=None)
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
    type='TextRecogLocalVisualizer',
    name='visualizer',
    vis_backends=[dict(type='LocalVisBackend')])
optim_wrapper = dict(
    type='OptimWrapper', optimizer=dict(type='Adam', lr=0.0003))
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=50, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
param_scheduler = [dict(type='MultiStepLR', milestones=[3, 4], end=6)]
file_client_args = dict(backend='disk')
dictionary = dict(
    type='Dictionary',
    dict_file=
    'th_dict.txt',
    with_padding=True,
    with_unknown=True,
    same_start_end=True,
    with_start=True,
    with_end=True)
model = dict(
    type='NRTR',
    backbone=dict(type='NRTRModalityTransform'),
    encoder=dict(type='NRTREncoder', n_layers=12),
    decoder=dict(
        type='NRTRDecoder',
        module_loss=dict(
            type='CEModuleLoss', ignore_first_char=True, flatten=True),
        postprocessor=dict(type='AttentionPostprocessor'),
        dictionary=dict(
            type='Dictionary',
            dict_file=
            'th_dict.txt',
            with_padding=True,
            with_unknown=True,
            same_start_end=True,
            with_start=True,
            with_end=True),
        max_seq_len=30),
    data_preprocessor=dict(
        type='TextRecogDataPreprocessor',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375]))
train_pipeline = [
    dict(
        type='LoadImageFromFile',
        file_client_args=dict(backend='disk'),
        ignore_empty=True,
        min_size=2),
    dict(type='LoadOCRAnnotations', with_text=True),
    dict(
        type='RescaleToHeight',
        height=32,
        min_width=32,
        max_width=160,
        width_divisor=4),
    dict(type='PadToWidth', width=160),
    dict(
        type='PackTextRecogInputs',
        meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
]
test_pipeline = [
    dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
    dict(
        type='RescaleToHeight',
        height=32,
        min_width=32,
        max_width=160,
        width_divisor=16),
    dict(type='PadToWidth', width=160),
    dict(type='LoadOCRAnnotations', with_text=True),
    dict(
        type='PackTextRecogInputs',
        meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
]
train_list = [
    dict(
        type='OCRDataset',
        data_root='data/recog/synTH',
        ann_file='textrecog_train.json',
        pipeline=None)
]
test_list = [
    dict(
        type='OCRDataset',
        data_root='data/recog/synTH',
        ann_file='textrecog_test.json',
        test_mode=True,
        pipeline=None)
]
train_dataset = dict(
    type='ConcatDataset',
    datasets=[
        dict(
            type='OCRDataset',
            data_root='data/recog/synTH',
            ann_file='textrecog_train.json',
            pipeline=None)
    ],
    pipeline=[
        dict(
            type='LoadImageFromFile',
            file_client_args=dict(backend='disk'),
            ignore_empty=True,
            min_size=2),
        dict(type='LoadOCRAnnotations', with_text=True),
        dict(
            type='RescaleToHeight',
            height=32,
            min_width=32,
            max_width=160,
            width_divisor=4),
        dict(type='PadToWidth', width=160),
        dict(
            type='PackTextRecogInputs',
            meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
    ])
test_dataset = dict(
    type='ConcatDataset',
    datasets=[
        dict(
            type='OCRDataset',
            data_root='data/recog/synTH',
            ann_file='textrecog_test.json',
            test_mode=True,
            pipeline=None)
    ],
    pipeline=[
        dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
        dict(
            type='RescaleToHeight',
            height=32,
            min_width=32,
            max_width=160,
            width_divisor=16),
        dict(type='PadToWidth', width=160),
        dict(type='LoadOCRAnnotations', with_text=True),
        dict(
            type='PackTextRecogInputs',
            meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
    ])
train_dataloader = dict(
    batch_size=384,
    num_workers=24,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type='ConcatDataset',
        datasets=[
            dict(
                type='OCRDataset',
                data_root='data/recog/synTH',
                ann_file='textrecog_train.json',
                pipeline=None)
        ],
        pipeline=[
            dict(
                type='LoadImageFromFile',
                file_client_args=dict(backend='disk'),
                ignore_empty=True,
                min_size=2),
            dict(type='LoadOCRAnnotations', with_text=True),
            dict(
                type='RescaleToHeight',
                height=32,
                min_width=32,
                max_width=160,
                width_divisor=4),
            dict(type='PadToWidth', width=160),
            dict(
                type='PackTextRecogInputs',
                meta_keys=('img_path', 'ori_shape', 'img_shape',
                           'valid_ratio'))
        ]))
test_dataloader = dict(
    batch_size=1,
    num_workers=4,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='ConcatDataset',
        datasets=[
            dict(
                type='OCRDataset',
                data_root='data/recog/synTH',
                ann_file='textrecog_test.json',
                test_mode=True,
                pipeline=None)
        ],
        pipeline=[
            dict(
                type='LoadImageFromFile',
                file_client_args=dict(backend='disk')),
            dict(
                type='RescaleToHeight',
                height=32,
                min_width=32,
                max_width=160,
                width_divisor=16),
            dict(type='PadToWidth', width=160),
            dict(type='LoadOCRAnnotations', with_text=True),
            dict(
                type='PackTextRecogInputs',
                meta_keys=('img_path', 'ori_shape', 'img_shape',
                           'valid_ratio'))
        ]))
val_dataloader = dict(
    batch_size=1,
    num_workers=4,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='ConcatDataset',
        datasets=[
            dict(
                type='OCRDataset',
                data_root='data/recog/synTH',
                ann_file='textrecog_test.json',
                test_mode=True,
                pipeline=None)
        ],
        pipeline=[
            dict(
                type='LoadImageFromFile',
                file_client_args=dict(backend='disk')),
            dict(
                type='RescaleToHeight',
                height=32,
                min_width=32,
                max_width=160,
                width_divisor=16),
            dict(type='PadToWidth', width=160),
            dict(type='LoadOCRAnnotations', with_text=True),
            dict(
                type='PackTextRecogInputs',
                meta_keys=('img_path', 'ori_shape', 'img_shape',
                           'valid_ratio'))
        ]))
auto_scale_lr = dict(base_batch_size=384)
launcher = 'none'
work_dir = './work_dirs/nrtr_modality-transform_50e_thvl'