BasicSTISR (Basic Scene Text Image Super Resolution) 是一个基于 PyTorch 的开源场景文本图像超分辨率工具箱.
In this work, we use STISR datasets TextZoom and four STR benchmarks, i.e., ICDAR2015, CUTE80, SVT and SVTP for model comparison.
All the datasets are lmdb
format. One can download these datasets from the this link.
./datasets/TextZoom/
--test
--train1
--train2
NOTE: Please do not forget to accustom your own dataset path in config/super_resolution.yaml
, such as the parameter train_data_dir
and val_data_dir
.
Following previous STISR works, we also use CRNN, MORAN and ASTER as the downstream text recognizer.
.pretrained/
--aster.pth.tar
--crnn.pth
--moran.pth
Download the pre-trained weights and logs at BaiduYunDisk with password: vqg7
Download the pretrain_transformer_stroke_decomposition.pth at BaiduYunDisk with password: mteb
./dataset/
--charset_36.txt
--confuse.pkl
--english_decomposition.txt
--pretrain_transformer_stroke_decomposition.pth
We have set some default hype-parameters in the config/super_resolution.yaml
and main.py
, so you can directly implement training and testing after you modify the path of datasets and pre-trained model.
sh train.sh
sh test.sh
The code of this work is based on TBSRN, TG, TATT, C3-STISR, and LEMMA. Thanks for your contributions.