Jeonghun Baek

I met the same problem and solved it by reinstalling AdelaiDet with [prebuilt detectron2](https://github.com/facebookresearch/detectron2/blob/main/INSTALL.md#install-pre-built-detectron2-linux-only). I don't know if this is the right way, but at least I can use demo.py...

Hello, > Should I use python train.py --saved_model pretrained_model? Yes. > Where should I save the new model then? The model is saved in `--exp_name`, see here https://github.com/clovaai/deep-text-recognition-benchmark/blob/32fd91ce9849a1e20636bc713abd34d50ec92ff3/train.py#L219 and if...

Hello, I have two questions to resolve this problem. 1) Does this error occur when you try with batch_size 192? Even if you try with batch_size 192, you would divide...

Hello, Yes, I think that the color image could provide much more information. But in our experiment, the accuracy difference was trivial. In other words, empirically there was no big...

Hello, I guess the training is almost done, thus continue training would be not a good solution. I recommend checking the difference between your custom dataset and the validation dataset....

Hello :) They are open questions, and probably they all are up to the dataset, so they are hard to answer... If I were you, I would start an experiment...

Hello, Could you upload the messages just before the error msg?

Hello, For TPS-ResNet-BiLSTM-Attn-case-sensitive model, I used the same setting in this repo. - no. of iterations: 300K - lr: 1 - batch size: 192 - optimizer: adadelta I don't have...

Yes, decreasing the learning rate would be helpful :)