karandoshi98/facegan

The idea is to in-paint the missing part of the face and address the peculiarities of face using textual description. We intend to achieve the results by applying pixel generation using GAN (Stage 1) combined with text to image conversion using GAN (Stage 2) benchmarking on a custom-made dataset for this task.

FaceGAN

The idea of the project is to in-paint the missing part of the face and address the peculiarities of face using textual description. We intend to achieve the results by applying pixel generation using GAN (Stage 1) combined with text to image conversion using GAN (Stage 2) benchmarking on a custom-made dataset for this task.

Please find the attached PPT and Blackbook for detailed description and understanding of the project.

Our project paper was published in springer - https://link.springer.com/chapter/10.1007/978-981-15-3242-9_50

Dataset Link - https://www.kaggle.com/zuozhaorui/celeba

To run the FaceIT.ipynb -

1. Go to https://colab.research.google.com/
2. Connect your colaboratory with your google drive to prevent loss of data.
3. Upload the code file and run every cell one after the other while waiting for the previous cell to execute.
4. Upload the dataset before executing the file according to the path mentioned in the second cell of the code file.
5. View the output in the custom_test_output folder.