liukuikun

``` test_list = [ _base_.iiit5k_rec_test, _base_.svt_rec_test, _base_.ic13_rec_test, _base_.ic15_rec_test, _base_.svtp_rec_test, _base_.cute80_rec_test] val_dataloader = dict( # _delete_=True, batch_size=1, num_workers=4, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='ConcatDataset', datasets=test_list, pipeline=test_pipeline)) test_dataloader = val_dataloader val_evaluator =...

Text spotter postprocess

1

## Motivation Design a BasePostProcessor for text spotter ## Modification

WIP:[Feature] add a new pipeline for text recognition

2

# Motivation In the latest paper and text recognition, TR tend to be using more information for recognition, like position information in RobustScanner, language information in ABINet and VisionLAN ,...

我的email是[email protected] 万分感谢！