Mohamed Nabil

icon indicating a website link https://www.linkedin.com/in/professionalnabil/ icon indicating an email [email protected]

icon company IN3 Technology icon location Alexandria , Egypt icon location A curious ML Engineer, interested in AI, Business, Psychology, Physics, and Mathematics Overall I want to have a pretty good model of how the world works

Results 23 comments of Mohamed Nabil

Training ABINET on Custom Dataset

so the num_chars should be the exact number? because I have to add 1 for the training to run

404 page not found error

@waqarsqureshi Sorry for the late reply, I'm getting this error when I use the out of the box, docker-compose.yml when I run docker-compose up -d on the azure remote machine...

Only integers, slices (`:`), ellipsis (`...`), tf.newaxis (`None`) and scalar tf.int32/tf.int64 tensors are valid indices, got [1, 3]

same error here

parser error

i tried to add a configuration file using this command `!python3 -m segmentation.train --config config.py` but it appears that it shouldn't be done this way

Bi-lingual OCR Model Training

For example in Arabic, For some basic fonts it works well, however in fonts like Cairo the ratio of language confusion is heightened. I'll try to increase the volume of...

识别v3确实会比v2好吗？

I didn't run this test, but I think It's an interesting point of view In their paper they compare the two: https://arxiv.org/pdf/2206.03001 Part of the improvement was in the dataset...

Using DB++ in PP-OCRv3

@LDOUBLEV any idea how i can do that?

PP-OCRv3 recognition model training

@an1018 Any idea how can I do that?

PP-OCRv3 recognition model training

> Hi, bely66 > > Congratulation， 80% accuracy is already a good model！ Regarding your question, here are a few suggestions for reference： > > > > 1. Yes, if...

best metric, acc: 0.0 on recognition

@Yosiiiiiiiiiiiiiiii Hi man, I have a question did you disable RecConAug on purpose? and what was the training data size you used for training? I can see the training accuracy...