2.1、基于并行上下文注意网络的场景文本图像超分辨率（代码理解与实验进度+报告）

代码链接：GitHub - Vill-Lab/2021-ACMMM-PCAN

代码有以下链接改写而成：GitHub - JasonBoy1/TextZoom: A super-resolution dataset of paired LR-HR scene text images

---

2. Train

Prepare training datasets

1. Download the TextZoom dataset (1.7w+ LR-HR pair images) from the link TextZoom.
2. Set '--dataset/lmdb/str/TextZoom' as the HR and LR image path.
3. download the Aster model from GitHub - ayumiymk/aster.pytorch: ASTER in Pytorch,
   Moran model from GitHub - Canjie-Luo/MORAN_v2: MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition,
   CRNN model from GitHub - meijieru/crnn.pytorch: Convolutional recurrent network in pytorch.
4. Set '--pth/crnn.pth', '--pth/demo.pth.tar', '--pth/moran.pth' as the file path of ocr metrics.

training

1. Change your own yaml file under 'src/config/all/own.yaml'
2. Run the following code.

CUDA_VISIBLE_DEVICES=1 python3 main.py --STN --mask --edge --config 'all/own.yaml'