fast-neural-doodle 0,0

Faster neural doodle

3 years after

Faster neural doodle

This is my try on drawing with neural networks, which is faster than Alex J. Champandard's version, and similar in quality. This approach is based on neural artistic style method (L. Gatys), whereas Alex's version uses CNN+MRF approach of Chuan Li.

It takes several minutes to redraw Renoir example using GPU and it will easily fit in 4GB GPUs. If you were able to work with Justin Johnson's code for artistic style then this code should work for you too.

You can find even faster version here.


  • torch
  • torch.cudnn (optional)
  • torch-hdf5
  • python + numpy + scipy + h5py + sklearn

Tested with python2.7 and latest conda packages.

Do it yourself

First download VGG-19.

cd data/pretrained && bash && cd ../..

Use this script to get intermediate representations for masks.

python --n_colors=4 --style_image=data/Renoir/style.png --style_mask=data/Renoir/style_mask.png --target_mask=data/Renoir/target_mask.png

Now run doodle.

th fast_neural_doodle.lua -masks_hdf5 masks.hdf5

And here is the result. Renoir First row: original, second -- result.

And Monet. Monet


Processing the image at low resolution first can provide a significant speed-up. You can pass a list of resolutions to use when processing. Passing 256 means that the images and masks should be resized to 256x256 resolution. With 0 passed no resizing is done. Here is an example for cmd parameters:

  • -num_iterations 450,100 -resolutions 256,0 Which means: work for 450 iterations at 256x256 resolution and 100 iterations at original.

Monet and Renoir examples take ~1.5 min to process with these options.

Style transfer

You can also provide target image to use in content loss (in the same way as in neural artisctic style algorithm) via --target_image option of get\_mask\ script.


python --n_colors=4 --style_image=data/Renoir/style.png --style_mask=data/Renoir/style_mask.png --target_mask=data/Renoir/creek_mask.jpg --target_image=data/Renoir/creek.jpg
th fast_neural_doodle.lua -masks_hdf5 masks.hdf5

Renoir Upper left: target image. Upper right: neural doodle with target image, i.e. both the masks and content loss were used. Lower left: regular neural doodle without content loss. Lower right: stylization without masks, with high style weight, obtained via neural style code. With high style weight, stylization tends to mix unrelated parts of image, such as patches of grass floating in the sky on last picture. Neural doodle with content loss allows to generate highly stylized images without this problem.


  • Supported backends:

    • nn (CPU/GPU mode)
    • cudnn
    • clnn (not tested yet..)
  • When using -backend cudnn do not forget to switch -cudnn_autotune.


The code is heavily based on Justin Johnson's great code for artistic style.

Related Repositories



Deep Learning papers reading roadmap for anyone who are eager to learn this amaz ...



Turn your two-bit doodles into fine artworks with deep neural networks, generate ...



A list of popular github projects related to deep learning ...



The Top-Starred Python GitHub Devs, Orgs, and Repos to Follow (All-Time and Tren ...



A curated list of awesome Torch tutorials, projects and communities ...

Top Contributors

DmitryUlyanov vadim-v-lebedev