Mahmuod Aboalhassan

does the blurred faces in the dataset for privacy or for training for just you don't need it so you blurred it

now I train the Unet model in 6 classes and i want to get the contours of every segmented class if found how i can do this

Arabic Alphabet shapes

5

first of all I Would to thank you for this awesome project when use the arabic_reshaper repo when generating the the text for fix the Arabic shapes issue , i...

How to prepare data set for training

1

how i can prepare the dataset for training in my case national id card (egy) and what is the best practice to enhance the performance

deform_conv_cuda not found in deform_conv

7


use custom trained layout analysis model

4

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： ubuntu 18 - 版本号/Version： Paddle：2.3.0 PaddleOCR： 问题相关组件/Related components： 2.6.0.1 - 运行指令/Command Code： - from paddleocr import PPStructure...

loading the model into GPU direct

1

there is any way to loading the llm model into the GPU memory direct not in CPU and then switch in GPU as i seen in monitor