A Neural Algorithm of Artistic Style


Brief introduction

This program is using the convolutional neural network to make a new image. It combines the content of one image with the style of another image.



Instruction of Program

After you have installed the project, you may run it using the following command:

#th neural_style.lua -style_image -content_image Here is an example command with options:

#th neural_style.lua -style_image examples/inputs/picasso_selfport1907.jpg -content_image examples/inputs/brad_pitt.jpg -output_image profile.png -model_file models/nin_imagenet_conv.caffemodel -proto_file models/train_val.prototxt -gpu 0

-backend clnn -num_iterations 1000 -seed 123 -content_layers relu0,relu3,relu7,relu12

-style_layers relu0,relu3,relu7,relu12 -content_weight 10 -style_weight 1000 -image_size 512 -optimizer adam

-image_size: Maximum side length (in pixels) of of the generated image. Default is 512.

-style_blend_weights: The weight for blending the style of multiple style images, as a comma-separated list, such as -style_blend_weights 3,7. By default all style images are equally weighted.

-gpu: Zero-indexed ID of the GPU to use; for CPU mode set -gpu to -1.

-content_weight: How much to weight the content reconstruction term. Default is 5e0.

-style_weight: How much to weight the style reconstruction term. Default is 1e2.

-tv_weight: Weight of total-variation (TV) regularization; this helps to smooth the image. Default is 1e-3. Set to 0 to disable TV regularization.

-num_iterations: Default is 1000.

-init: Method for generating the generated image; one of random or image. Default is random which uses a noise initialization as in the paper; image initializes with the content image.

-optimizer: The optimization algorithm to use; either lbfgs or adam; default is lbfgs. L-BFGS tends to give better results, but uses more memory. Switching to ADAM will reduce memory usage; when using ADAM you will probably need to play with other parameters to get good results, especially the style weight, content weight, and learning rate; you may also want to normalize gradients when using ADAM.

-learning_rate: Learning rate to use with the ADAM optimizer. Default is 1e1.

-normalize_gradients: If this flag is present, style and content gradients from each layer will be L1 normalized. Idea from andersbll/neural_artistic_style.

-output_image: Name of the output image. Default is out.png.

-print_iter: Print progress every print_iter iterations. Set to 0 to disable printing.

-save_iter: Save the image every save_iter iterations. Set to 0 to disable saving intermediate results.

-content_layers: Comma-separated list of layer names to use for content reconstruction. Default is relu4_2.

-style_layers: Comman-separated list of layer names to use for style reconstruction. Default is relu1_1,relu2_1,relu3_1,relu4_1,relu5_1.

-style_scale: Scale at which to extract features from the style image. Default is 1.0.

-proto_file: Path to the deploy.txt file for the VGG Caffe model.

-model_file: Path to the .caffemodel file for the VGG Caffe model. Default is the original VGG-19 model; you can also try the normalized VGG-19 model used in the paper.

-pooling: The type of pooling layers to use; one of max or avg. Default is max. The VGG-19 models uses max pooling layers, but the paper mentions that replacing these layers with average pooling layers can improve the results. I haven't been able to get good results using average pooling, but the option is here.

-backend: nn, cudnn, or clnn. Default is nn. cudnn requires cudnn.torch and may reduce memory usage. clnn requires cltorch and clnn

-cudnn_autotune: When using the cuDNN backend, pass this flag to use the built-in cuDNN autotuner to select the best convolution algorithms for your architecture. This will make the first iteration a bit slower and can take a bit more memory, but may significantly speed up the cuDNN backend.


More information





Last Update: 07/09/2016