Khawar Islam

Reproduce results using training

4

Thank you @zhongyy for your pre-trained models. I verified all **ViTP12S8** results in the paper and all results are the same as the paper. Thank you @zhongyy. After seeing your...

Training days time

5

I am doing training as same as your GPU Tesla V100. How many days are required for one epoch?

Data Accessibility problem

2

Hi Dear, I am outside of China and I am unable to access datasets because they require a mobile number. Please upload the testing datasets on google drive or dropbox.

Hello @parksunwoo, Thank you for your great work. I keep trying to implement another thing in your repository like PaddleOCR. When the model detects the Korean text in an image...

BPG image format is not supported in PILLOW library. could you please help me how to calculate it?

Dear @andyzoujm, Thank you for your contribution. Are you planning to evaluate model robustness on ROBIN dataset? ROBIN dataset is presented at ECCV 2022 Regards, Khawar

Training is extremely slow on Gluonts [Torch]

1

## Description I am quite frustrating because I am training a model and training is very very slow on RTX 3080. I am training on 500 CSV files. If anyone...

Fine-Tune on Korean handwritten dataset

6

Dear @JaidedTeam I would like to fine-tune the EASY OCR in the handwritten Korean language, I am assuming that the pre-trained model is already trained in Korean and English vocabulary...

Hi @Belval I am working on generating korean handwritten samples for training dataset. Still, I am unable to achieve it. **Does anyone have an idea?** ``` trdg -l ko -c...

Images are very distorted

7

Hello @moonbings During synthetic dataset generation, some image are very distorted and i don't have any idea how to fix it. I played with some parameters but it didnt work...