Skip to content

Deep Convolutional Generative Adversarial Network (DCGAN) to generate human-like faces which was trained for over 8 hours using 25,000 images on NVIDIA Tesla P100 GPU.

License

Notifications You must be signed in to change notification settings

notsanidhyak/Humans-Are-Fake

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Frame 66

Humans-Are-Fake


All humans are fake, atleast the ones generated by this GAN!


Humans-Are-Fake is a Deep Convolutional Generative Adversarial Network (DCGAN) to generate human-like faces which was trained for over 8 hours using 25,000 images on NVIDIA Tesla P100 GPU. In the stable model, losses for the Discriminator Network were less than 0.018 while losses for the Generator Network were less than 6.282.


View notebook on Kaggle


⚡ How to use the trained model?


  • Both, the generator models and the discriminator models were stored along with their indexes after every 5 epoch of training.
  • Unzip the zip file containing all the checkpoints.
  • Download and use the stable version (ckpt-6).

⚒️ Architecture


  • Overall GAN workflow -

image


  • Generator Network Architecture -

Screenshot 2023-06-27 153557


  • Discriminator Network Architecture -

Screenshot 2023-06-27 153630


🔥 Results


After training for around 35 Epochs, the GAN produced the results listed below. The following pictures were created by the GAN entirely out of its own imagination; they were never observed by it during its training phase.


WhatsApp Image 2023-06-21 at 10 48 11 PM

WhatsApp Image 2023-06-22 at 11 02 23 PM


📚 Dataset


View dataset (Credits: GREATGAMEDOTA)


❤️ Feedback


If you have any feedback or suggestions please reach out to the project admin sanidhyak or you can create an issue and mention there which new features can be added to make Humans-Are-Fake better.

About

Deep Convolutional Generative Adversarial Network (DCGAN) to generate human-like faces which was trained for over 8 hours using 25,000 images on NVIDIA Tesla P100 GPU.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published