raminrahimi6970

learning rate scheduler

2

hi thanks for your code and best paper I do not see learning rate scheduler in training loop,it don not affect in performance of model?

that is best repository that i see since 3 years ago.......... it is better than paddle ocr,easy ocr,.... thanks for your best work

Small SATRN not learning during training

3

Hi thanks for your code i have problem when training the SATRN the loss not decrease and accuracy is 0 after many iteration? thanks for your replay

Dear Authors, Thanks for your great work. Are your codes support pytorch version 1.5? I get error with pytorch 1.5 when run train.py with cuda device..... My email: [email protected] Best...

the result of infer_rec.py and predict_rec.py not same

3

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment： Ubuntu18.04 - 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components：2.4 - 运行指令/Command Code： - 完整报错/Complete Error Message： hello thanks for your...

hi thanks for your work are you implement the RandAugment? in your paper: geometry = [Rotate(), Perspective(), Shrink()] noise = [GaussianNoise()] blur = [MotionBlur()] augmentations = [geometry, noise, blur] img...

Hi thanks for your great model why inference time in validation phase is so slow? training phase is faster than validation.... thanks best regards

train for other language

2

hello thanks for your paper and released codes I want to train your code for other language but I see in lmdbdataset that you use English char and limit the...

Hi thanks for your codes I check the cdcn++ model and see you are setting theta=0 for that there is a certain reason for that? thanks

Hi, thanks for providing the code examples. I'm using an 11x4 (rows x columns) asymmetric circles pattern for camera calibration, with double_count_in_column set to False. However, I've encountered an issue...