neural-style-pt

This is a PyTorch implementation of the paper A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. The code is based on Justin Johnson's Neural-Style.

The paper presents an algorithm for combining the content of one image with the style of another image using convolutional neural networks. Here's an example that maps the artistic style of The Starry Night onto a night-time photograph of the Stanford campus:

Applying the style of different images to the same content image gives interesting results. Here we reproduce Figure 2 from the paper, which renders a photograph of the Tubingen in Germany in a variety of styles:

Here are the results of applying the style of various pieces of artwork to this photograph of the golden gate bridge:

<div align="center"

Content / Style Tradeoff

The algorithm allows the user to trade-off the relative weight of the style and content reconstruction terms, as shown in this example where we port the style of Picasso's 1907 self-portrait onto Brad Pitt:

Style Scale

By resizing the style image before extracting style features, we can control the types of artistic features that are transfered from the style image; you can control this behavior with the -style_scale flag. Below we see three examples of rendering the Golden Gate Bridge in the style of The Starry Night. From left to right, -style_scale is 2.0, 1.0, and 0.5.

Multiple Style Images

You can use more than one style image to blend multiple artistic styles.

Clockwise from upper left: "The Starry Night" + "The Scream", "The Scream" + "Composition VII", "Seated Nude" + "Composition VII", and "Seated Nude" + "The Starry Night"

Style Interpolation

When using multiple style images, you can control the degree to which they are blended:

Transfer style but not color

If you add the flag -original_colors 1 then the output image will retain the colors of the original image.

Setup:

Dependencies:

Optional dependencies:

After installing the dependencies, you'll need to run the following script to download the VGG model:

python models/download_models.py

This will download the original VGG-19 model. The original VGG-16 model will also be downloaded. By default the original VGG-19 model is used.

If you have a smaller memory GPU then using NIN Imagenet model will be better and gives slightly worse yet comparable results. You can get the details on the model from BVLC Caffe ModelZoo. The NIN model is downloaded when you run the download_models.py script.

You can find detailed installation instructions for Ubuntu and Windows in the installation guide.

Usage

Basic usage:

python neural_style.py -style_image <image.jpg> -content_image <image.jpg>

cuDNN usage with NIN Model:

python neural_style.py -style_image examples/inputs/picasso_selfport1907.jpg -content_image examples/inputs/brad_pitt.jpg -output_image profile.png -model_file models/nin_imagenet.pth -gpu 0 -backend cudnn -num_iterations 1000 -seed 123 -content_layers relu0,relu3,relu7,relu12 -style_layers relu0,relu3,relu7,relu12 -content_weight 10 -style_weight 500 -image_size 512 -optimizer adam

cuDNN NIN Model Picasso Brad Pitt

To use multiple style images, pass a comma-separated list like this:

-style_image starry_night.jpg,the_scream.jpg.

Note that paths to images should not contain the ~ character to represent your home directory; you should instead use a relative path or a full absolute path.

Options:

Optimization options:

Output options:

Layer options:

Other options:

Frequently Asked Questions

Problem: The program runs out of memory and dies

Solution: Try reducing the image size: -image_size 256 (or lower). Note that different image sizes will likely require non-default values for -style_weight and -content_weight for optimal results. If you are running on a GPU, you can also try running with -backend cudnn to reduce memory usage.

Problem: -backend cudnn is slower than default NN backend

Solution: Add the flag -cudnn_autotune; this will use the built-in cuDNN autotuner to select the best convolution algorithms.

Problem: Get the following error message:

Missing key(s) in state_dict: "classifier.0.bias", "classifier.0.weight", "classifier.3.bias", "classifier.3.weight". Unexpected key(s) in state_dict: "classifier.1.weight", "classifier.1.bias", "classifier.4.weight", "classifier.4.bias".

Solution: Due to a mix up with layer locations, older models require a fix to be compatible with newer versions of PyTorch. The included donwload_models.py script will automatically perform these fixes after downloading the models.

Memory Usage

By default, neural-style-pt uses the nn backend for convolutions and L-BFGS for optimization. These give good results, but can both use a lot of memory. You can reduce memory usage with the following:

With the default settings, neural-style-pt uses about 3.7 GB of GPU memory on my system; switching to ADAM and cuDNN reduces the GPU memory footprint to about 1GB.

Speed

Speed can vary a lot depending on the backend and the optimizer. Here are some times for running 500 iterations with -image_size=512 on a Tesla K80 with different settings:

Here are the same benchmarks on a GTX 1080:

Multi-GPU scaling

You can use multiple CPU and GPU devices to process images at higher resolutions; different layers of the network will be computed on different devices. You can control which GPU and CPU devices are used with the -gpu flag, and you can control how to split layers across devices using the -multidevice_strategy flag.

For example in a server with four GPUs, you can give the flag -gpu 0,1,2,3 to process on GPUs 0, 1, 2, and 3 in that order; by also giving the flag -multidevice_strategy 3,6,12 you indicate that the first two layers should be computed on GPU 0, layers 3 to 5 should be computed on GPU 1, layers 6 to 11 should be computed on GPU 2, and the remaining layers should be computed on GPU 3. You will need to tune the -multidevice_strategy for your setup in order to achieve maximal resolution.

We can achieve very high quality results at high resolution by combining multi-GPU processing with multiscale generation as described in the paper Controlling Perceptual Factors in Neural Style Transfer by Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, Aaron Hertzmann and Eli Shechtman.

Here is a 4016 x 2213 image generated on a server with eight Tesla K80 GPUs:

The script used to generate this image can be found here.

Implementation details

Images are initialized with white noise and optimized using L-BFGS.

We perform style reconstructions using the conv1_1, conv2_1, conv3_1, conv4_1, and conv5_1 layers and content reconstructions using the conv4_2 layer. As in the paper, the five style reconstruction losses have equal weights.

Citation

If you find this code useful for your research, please cite:

@misc{ProGamerGov2018,
  author = {ProGamerGov},
  title = {neural-style-pt},
  year = {2018},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/ProGamerGov/neural-style-pt}},
}