Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Training from scratch, w/o using Pretrained DeiT? #7

Open
mandal4 opened this issue Jun 17, 2021 · 3 comments
Open

Training from scratch, w/o using Pretrained DeiT? #7

mandal4 opened this issue Jun 17, 2021 · 3 comments

Comments

@mandal4
Copy link

mandal4 commented Jun 17, 2021

Thanks for sharing the source codes!
I found that you exploited 'Pretrained weight file of DeiT' instead of training from scratch.
However, i see you emphasize 'Efficiency' of your model.
I wonder if there exists some issue to train from scratch.

@roatienza
Copy link
Owner

The pre-trained weights were used since transformers do not have inductive bias. However, for the case of STR, since MJSynth and SynText are both big in number (though lacking in diversity in terms of texture), the ViTSTR may not need pre-trained weights but this could result into lower performance. This would be an interesting future work.

@mrtranducdung
Copy link

Hi roatienza,
Currently, there are some Transformer Models we can choose (["vitstr_tiny_patch16_224", "vitstr_small_patch16_224", "vitstr_base_patch16_224", "vitstr_tiny_distilled_patch16_224", "vitstr_small_distilled_patch16_224"]). However, those are not support non-latin lanuages. Do you have any instruction that I can train a Transformer Model that support non-latin languages?
Thank you very much

@roatienza
Copy link
Owner

roatienza commented Dec 8, 2021

Hi, I do not have a set of instructions to train ViTSTR for non-latin chars. Training on non-latin requires:

  1. Labelled train/test dataset in lmbd format
  2. Change the number of characters in train and test: opt.character = string.printable[:-6]
  3. Retrain ViTSTR

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants