Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

confusion matrix #18

Open
zaghdoud2019 opened this issue Jun 15, 2022 · 3 comments
Open

confusion matrix #18

zaghdoud2019 opened this issue Jun 15, 2022 · 3 comments

Comments

@zaghdoud2019
Copy link

thanks for this greet job Please help me, I have tested scrabbleGAN with arabic text in image scene it worked for me with 49000 images with arabic and latin text it gives me a result is not good enough, I am going to do an error analysis on the data can you please help me how I can display the confusion matrix
biggan
image_at_epoch_0003

@Nikolai10
Copy link
Owner

Hello @zaghdoud2019,

thanks for sharing your results. Have you tried learning Arabic and Latin text generative models separately? From the limited information you have provided, it appears that you are trying to achieve a combined generative text model (Arabic, Latin, numbers, punctuation marks, etc.), which is a highly non-trivial learning task.

@zaghdoud2019
Copy link
Author

Hello @zaghdoud2019,

thanks for sharing your results. Have you tried learning Arabic and Latin text generative models separately? From the limited information you have provided, it appears that you are trying to achieve a combined generative text model (Arabic, Latin, numbers, punctuation marks, etc.), which is a highly non-trivial learning task.

Thank you for replying , really, my dataset contains many classes,I will test the model to generate only Arabic text model,I will share with you the result after that.

@dadizak
Copy link

dadizak commented Jul 11, 2022

Hello @zaghdoud2019,
thanks for sharing your results. Have you tried learning Arabic and Latin text generative models separately? From the limited information you have provided, it appears that you are trying to achieve a combined generative text model (Arabic, Latin, numbers, punctuation marks, etc.), which is a highly non-trivial learning task.

Thank you for replying , really, my dataset contains many classes,I will test the model to generate only Arabic text model,I will share with you the result after that.

Thanks a lot for replying,i will share with you my result to run scrabbleGAN with arabic charater,I have reduced the number of classes (special characters, latin letters, etc.)
image_at_epoch_0001_2
I had a question how I can display the letters from right to left

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants