sunshine

@mikelzc1990

@mikelzc1990, I have fixed the bug that the pre-trained model is not loaded in the code, and got Acc@1 97.7 by using net.config and net.init in net-flops@468. I guess that...

@taokong ，Hey, much thanks for your great work. During the train, I have some questions if you don't mind. when i change the batchszie=10， I got the following problem： F1112...

You can try increasing the batchsize.

Thanks for your suggestion, we will consider google cloud disk.

@lovecambi , As you said，the multi-scale loss is the following line. https://github.com/HCIILAB/Scene-Text-Removal/blob/master/train.py#L142

@neouyghur,Both PSNR and l2 scores are based on the average scores of the all test images.

@neouyghur, l2 score is mse. We use the compare_mse and compare_ssim and compare_psnr functions in the skimage.measure module.

@naoto0804, Sorry for not explaining it clearly. we use AGE, pEPs, pCEPS in the PythonCode.zip. We use the compare_mse and compare_ssim and compare_psnr functions in the skimage.measure module. The default...

@neouyghur ,The pre-trained weights will be released soon.