SwinTextSpotter
SwinTextSpotter copied to clipboard
Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)
自定义中文数据集
你好,在生成自定义的中文数据集的generator_json.py中,是否要将cV2修改成这样呢?  这样生成的rec好像不太对,想知道是什么原因 
 你好,想请问这可能是什么原因呢
您好,请问text_result.json中的rec是指预测出的文字吗,为什么使用中文数据集评估的时候rec中只有字母或者数字呀?需要哪里做调整吗?还有polys是预测框的点坐标吗?期待您的回复
你好,我执行以下语句后结果并不是很好,想知道会是什么原因? python projects/SWINTS/train_net.py --config-file projects/SWINTS/configs/SWINTS-swin-chn_finetune.yaml --eval-only MODEL.WEIGHTS ./output/rects_model_final.pth 
 在测试自己的数据集时报错,不知是哪里的问题,求答复
Hello, there are many datasets to download, how can I place them according to the dataset path?
hello,i can not find your dataLoader in train_net.py。i need construct my code to train custom dataset?
I use Anaconda for installation, and there are no errors until the step `python setup.py build develop`. And the command line cannot compile successfully. The following are the errors that...
python demo/demo.py \ --config-file projects/SWINTS/configs/SWINTS-swin-pretrain.yaml \ --input datasets/ocr_en_422k/GCC_train_171460144.jpg \ --output output/ocr_en \ --confidence-threshold 0.4 \ --opts MODEL.WEIGHTS work_dirs/swin_imagenet_pretrain.pth
I have check on detectron2 folder and there is no setup.py file. How can i run the command %cd detectron2 !python setup.py build develop