Darwin Bautista
Darwin Bautista
During the Orientation Robustness Benchmark test, an error occurs when applying rotation operations.
Seems to be a persistent issue with Windows installations. I'll try if I could make a fix this weekend, but this is the offending code if you're interested: https://github.com/baudm/parseq/blob/83abcc0522829c49a3a0932a95baf5c3c3f95465/strhub/data/module.py#L61 Making...
@Preethse try early stopping. Your training is collapsing after a while. You could also try tuning the learning rates. The training dynamics drastically changes if you change the training data,...
@Chenxx017 Sorry, but no. That's outside the scope of this project.
Hello. We also provide the LMDB for the 1811 subset of IC15. You can just directly extract and save the images from it. You can check the following references for...
Kind refer to our ECCV presentation: https://drive.google.com/file/d/11VoZW4QC5tbMwVIjKB44447uTiuCJAAD/view It contains a brief step-by-step walkthrough of the decoding process.
To reproduce Table 17, you need to use a dataset which contains arbitrarily-oriented text (e.g. the real datasets). Text in MJ+ST are primarily horizontally-oriented. I guess you could also augment...
Hello, please provide more details such as the model and weights used as well as the exact image you're using.
Sorry but I can't help you since: 1. I have no access to and am not familiar with the specific model you're referring to. 2. I have no access to...
Off the top of my head, I could only hypothesize that the repeated characters are caused by NAR decoding failing to recognize the end of sequence. In short, `[E]` is...
I also notice that you're trying to decode whitespace characters. That could also be a potential cause of the issue with NAR decoding. Another thing you could try is increasing...