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

Type of Dataset images? RGB or Greyscale? #9

Open
Asaad-Pak opened this issue Dec 11, 2022 · 5 comments
Open

Type of Dataset images? RGB or Greyscale? #9

Asaad-Pak opened this issue Dec 11, 2022 · 5 comments

Comments

@Asaad-Pak
Copy link

Can you show the data on which this GAN was trained? Because I am confused that your dataset consisted of either RGB images or greyscale images.

@BakingBrains
Copy link
Owner

BakingBrains commented Dec 11, 2022

@Asaad-Pak I used this data : https://www.kaggle.com/datasets/jessicali9530/stanford-cars-dataset
RGB images of cars

@Asaad-Pak
Copy link
Author

@BakingBrains thank you for the info. Also, I am running this code on google colab. Can you tell me how much EPOCHs are sufficient for producing good data and what parameters I can further change to improve the GAN result?

@BakingBrains
Copy link
Owner

@Asaad-Pak just train with current configuration. If it fails increase the Epochs and GENERATE_RES

@Asaad-Pak
Copy link
Author

@BakingBrains ok thanks :)

@Asaad-Pak
Copy link
Author

I have changed Epochs to 550 and I am working on the human faces data set but it is not producing good results. I am not getting good results I have also checked it by increasing the Generate Res too.
I am using this dataset: https://www.kaggle.com/datasets/ashwingupta3012/human-faces

train-549 (3)

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

2 participants