Skip to content
Graphics. High-resolution Deep Convolutional Generative Adversarial Networks.
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
labels
scripts_tensorflow
HDCGAN_table.png
LICENSE
README.md
frechet.png
generate_subfolders.py
hdcgan.png

README.md

Graphics

High-resolution Deep Convolutional Generative Adversarial Networks

Link to Graphics

Alternate Link to Graphics

For more information visit the website:

http://curto.hk/publication/hdcgan/

If you use Graphics in a publication, please cite the paper below:

    @article{Curto19_2,
      author = "J. D. Curt\'o and H. C. Zarza and T. Kim",
      title = "High-resolution Deep Convolutional Generative Adversarial Networks",
      journal = "arXiv:1711.06491",
      year = "2019",
    }

Change Log

Version 1.0, released on 24/01/2019


File Information

  • Images (graphics/samples/)**
    • 14,248 cropped face images. Balanced in terms of ethnicity. Mirror images included to enhance pose variation.
  • Labels (labels/c&z.csv and labels/c&z.p)
    • CSV file with attribute information: Filename, Age, Ethnicity, Eyes Color, Facial Hair, Gender, Glasses, Hair Color, Hair Covered, Hair Style, Smile and Visible Forehead. We also include Pickle format to load in Python.
  • Code (scripts_tensorflow/classification.py and generate_subfolders.py)
    • Script to do classification benchmarks using Tensorflow.
    • Script to generate adequate subfolder of specific attribute. Useful to load into frameworks of machine learning.
  • HDCGAN Synthetic Images (graphics/hdcgan/)
    • 4,239 face images generated by HDCGAN trained on CelebA. Resized at 128x128.
  • Additional Images (graphics/extra/samples/, labels/extra_c&z.csv and labels/extra_c&z.p)**
    • 3,384 cropped face images with labels. Ethnicity: White.

** Please note that we do not own the copyrights to these images. Their use is RESTRICTED to non-commercial research and educational purposes.

You can’t perform that action at this time.