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
- 2017/12/2 added light model
- 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
- training data (additional, download it from here, extract it and place the extracted directory in dir
How to use
please change the line 15 of
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.
output.py . converted images will be output at
You can select light model by change the line 13, 14 of
model_path = "model/model_light.json" weight_path = "model/weight_light.hdf5"
The pre-trained models and the other files we have provided are licensed under the MIT License.