Awesome Open Source
Awesome Open Source

DeepAA

This is convolutional neural networks generating ASCII art. This repository is under construction.

This work is accepted by NIPS 2017 Workshop, Machine Learning for Creativity and Design The paper: ASCII Art Synthesis with Convolutional Networks

Web application (using previous version model) (by tar-bin)

image sample

Change log

  • 2017/12/2 added light model

Requirements

  • TensorFlow (1.3.0)
  • Keras (2.0.8)
  • NumPy (1.13.3)
  • Pillow (4.2.1)
  • Pandas (0.18.0)
  • Scikit-learn (0.19.0)
  • h5py (2.7.1)
  • model's weight (download it from here and place it in dir model.)
  • training data (additional, download it from here, extract it and place the extracted directory in dir data.) )

How to use

please change the line 15 of output.py

image_path = 'sample images/original images/21 original.png' # put the path of the image that you convert.

into the path of image file that you use. You should use a grayscale line image.

then run output.py. converted images will be output at output/.

You can select light model by change the line 13, 14 of output.py into

model_path = "model/model_light.json"
weight_path = "model/weight_light.hdf5"

License

The pre-trained models and the other files we have provided are licensed under the MIT License.


Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
python (55,343
deep-learning (4,059
tensorflow (2,184
keras (779
ascii-art (80