TextZoom icon indicating copy to clipboard operation
TextZoom copied to clipboard

A super-resolution dataset of paired LR-HR scene text images

Results 37 TextZoom issues
Sort by recently updated
recently updated
newest added

I would like to remove "TypeError: cannot pickle 'Environment' object" error by making changes in the code .

![image](https://user-images.githubusercontent.com/30209495/115200280-9e347800-a126-11eb-85c4-346432585041.png) ![image](https://user-images.githubusercontent.com/30209495/115200321-abe9fd80-a126-11eb-9ad4-e8543d406875.png) ![image](https://user-images.githubusercontent.com/30209495/115200352-b4423880-a126-11eb-863d-3526d7af2692.png) ![image](https://user-images.githubusercontent.com/30209495/115200480-db990580-a126-11eb-9074-d70960ac5d37.png) 每个图中从上到下依次是LR、SR、HR,可以看到SR图像的背景颜色很奇怪,我不知道这是不是导致训练中image loss一直是0的原因,希望能得到解答,谢谢~~

Hi, I tried to execute demo version. python3 main.py --demo --demo_dir='dataset' --resume='model_best.pth' --STN --mask But there is one issue. ![1](https://user-images.githubusercontent.com/72849922/131271754-a382ef2b-40c7-4001-ac83-f00960047730.PNG) So, first I found the same issue in this github...

Hi everyone, I really appreciate the work done both by the proposed paper and within code. I'm trying to reproduce the performance showed in the paper for a Thesis work...

@JasonBoy1 can you release pre-trained models?

用训练好的textzoom的权重 测试的时候达到了70%以上的准确度 但是在跑demo.py时 依旧测试textzoom数据时 输出的预测结果 lr---》sr lr的预测结果准确很多 sr的结果基本上都是错的 都是the 这种单词 是怎么回事呀 求助!

I can start test successfully using Moran and CRNN. However,when I tried to use Aster to test,a problem occured. Have you ever met this problem before? Please help me. ![微信图片_20230215183954](https://user-images.githubusercontent.com/58348982/219004824-7771f41c-256c-44a4-9d8b-1e3b50153c1d.png)