search

TongkunGuan / CCD

[ICCV2023] Self-supervised Character-to-Character Distillation for Text Recognition
https://openaccess.thecvf.com/content/ICCV2023/papers/Guan_Self-Supervised_Character-to-Character_Distillation_for_Text_Recognition_ICCV_2023_paper.pdf
140 stars 7 forks source link

Is it possible to run a single image Demo? #6

Closed Shawn9257 closed 9 months ago

Shawn9257 commented 9 months ago

Hi, thank for your great work!

I have read the paper and now I am trying to test a single image OCR. Is it possible to run a single image test?

TongkunGuan commented 9 months ago

Hi, thank for your great work!

I have read the paper and now I am trying to test a single image OCR. Is it possible to run a single image test?

Sorry, the script isn't provided, please modify the test.py (replaced dataloader with a single image).

Shawn9257 commented 9 months ago

Thx for your answer.

0-Maxwei-0 commented 7 months ago

Thx for your answer.

hi, have you solved this?

bowen-upenn commented 3 months ago

Could you please advise us on what data transformations, like transforms.Normalize, we should apply to a single user-input image? In your test.py: _get_databaunch function, we couldn't find your 'data_aug': config.dataset_data_aug in the config files provided, and what config.dataset_scheme should we use by default for a new test image? Thanks.